2025-08-30 16:20:45 - pico-train - INFO - Step 0 -- 📊 Evaluation Results 2025-08-30 16:20:45 - pico-train - INFO - └── paloma: inf 2025-08-30 16:20:45 - pico-train - INFO - ================================================== 2025-08-30 16:20:45 - pico-train - INFO - ✨ Training Configuration 2025-08-30 16:20:45 - pico-train - INFO - ================================================== 2025-08-30 16:20:45 - pico-train - INFO - ╭─────────────────────────────────────────────────────╮ 2025-08-30 16:20:45 - pico-train - INFO - │ checkpointing: │ 2025-08-30 16:20:45 - pico-train - INFO - │ checkpoints_dir: checkpoints │ 2025-08-30 16:20:45 - pico-train - INFO - │ evaluation: │ 2025-08-30 16:20:45 - pico-train - INFO - │ eval_results_dir: eval_results │ 2025-08-30 16:20:45 - pico-train - INFO - │ fabric_checkpoint_dir: fabric_state │ 2025-08-30 16:20:45 - pico-train - INFO - │ fabric_checkpoint_filename: checkpoint.pt │ 2025-08-30 16:20:45 - pico-train - INFO - │ hf_checkpoint: │ 2025-08-30 16:20:45 - pico-train - INFO - │ collection_slug: null │ 2025-08-30 16:20:45 - pico-train - INFO - │ repo_id: ThomasTheMaker/pico-decoder-tiny │ 2025-08-30 16:20:45 - pico-train - INFO - │ learning_dynamics: │ 2025-08-30 16:20:45 - pico-train - INFO - │ batch_size: 1 │ 2025-08-30 16:20:45 - pico-train - INFO - │ eval_data: null │ 2025-08-30 16:20:45 - pico-train - INFO - │ layer_suffixes: │ 2025-08-30 16:20:45 - pico-train - INFO - │ - attention.v_proj │ 2025-08-30 16:20:45 - pico-train - INFO - │ - attention.o_proj │ 2025-08-30 16:20:45 - pico-train - INFO - │ - swiglu.w_2 │ 2025-08-30 16:20:45 - pico-train - INFO - │ sequence_idx: -1 │ 2025-08-30 16:20:45 - pico-train - INFO - │ learning_dynamics_dir: learning_dynamics │ 2025-08-30 16:20:45 - pico-train - INFO - │ logs_dir: logs │ 2025-08-30 16:20:45 - pico-train - INFO - │ run_name: pico-decoder-tiny-dolma20M-v1 │ 2025-08-30 16:20:45 - pico-train - INFO - │ runs_dir: runs │ 2025-08-30 16:20:45 - pico-train - INFO - │ save_every_n_steps: 1000 │ 2025-08-30 16:20:45 - pico-train - INFO - │ save_to_hf: false │ 2025-08-30 16:20:45 - pico-train - INFO - │ training: │ 2025-08-30 16:20:45 - pico-train - INFO - │ auto_resume: true │ 2025-08-30 16:20:45 - pico-train - INFO - │ data: │ 2025-08-30 16:20:45 - pico-train - INFO - │ dataloader: │ 2025-08-30 16:20:45 - pico-train - INFO - │ batch_size: 16 │ 2025-08-30 16:20:45 - pico-train - INFO - │ dataset: │ 2025-08-30 16:20:45 - pico-train - INFO - │ name: ThomasTheMaker/pretokenized-dolma-20M │ 2025-08-30 16:20:45 - pico-train - INFO - │ tokenizer: │ 2025-08-30 16:20:45 - pico-train - INFO - │ name: allenai/OLMo-7B-0724-hf │ 2025-08-30 16:20:45 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-30 16:20:45 - pico-train - INFO - │ evaluation: │ 2025-08-30 16:20:45 - pico-train - INFO - │ metrics: │ 2025-08-30 16:20:45 - pico-train - INFO - │ - paloma │ 2025-08-30 16:20:45 - pico-train - INFO - │ paloma: │ 2025-08-30 16:20:45 - pico-train - INFO - │ batch_size: 1 │ 2025-08-30 16:20:45 - pico-train - INFO - │ dataset_name: pico-lm/pretokenized-paloma-tinsy │ 2025-08-30 16:20:45 - pico-train - INFO - │ dataset_split: val │ 2025-08-30 16:20:45 - pico-train - INFO - │ max_length: 2048 │ 2025-08-30 16:20:45 - pico-train - INFO - │ model: │ 2025-08-30 16:20:45 - pico-train - INFO - │ activation_hidden_dim: 384 │ 2025-08-30 16:20:45 - pico-train - INFO - │ attention_n_heads: 12 │ 2025-08-30 16:20:45 - pico-train - INFO - │ attention_n_kv_heads: 4 │ 2025-08-30 16:20:45 - pico-train - INFO - │ batch_size: 1024 │ 2025-08-30 16:20:45 - pico-train - INFO - │ d_model: 96 │ 2025-08-30 16:20:45 - pico-train - INFO - │ max_seq_len: 2048 │ 2025-08-30 16:20:45 - pico-train - INFO - │ model_type: pico_decoder │ 2025-08-30 16:20:45 - pico-train - INFO - │ n_layers: 12 │ 2025-08-30 16:20:45 - pico-train - INFO - │ norm_eps: 1.0e-06 │ 2025-08-30 16:20:45 - pico-train - INFO - │ position_emb_theta: 10000.0 │ 2025-08-30 16:20:45 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-30 16:20:45 - pico-train - INFO - │ monitoring: │ 2025-08-30 16:20:45 - pico-train - INFO - │ logging: │ 2025-08-30 16:20:45 - pico-train - INFO - │ log_every_n_steps: 100 │ 2025-08-30 16:20:45 - pico-train - INFO - │ log_level: INFO │ 2025-08-30 16:20:45 - pico-train - INFO - │ save_to_wandb: false │ 2025-08-30 16:20:45 - pico-train - INFO - │ wandb: │ 2025-08-30 16:20:45 - pico-train - INFO - │ entity: boymyc │ 2025-08-30 16:20:45 - pico-train - INFO - │ project: pico-decoder-tiny │ 2025-08-30 16:20:45 - pico-train - INFO - │ training: │ 2025-08-30 16:20:45 - pico-train - INFO - │ fabric: │ 2025-08-30 16:20:45 - pico-train - INFO - │ accelerator: cuda │ 2025-08-30 16:20:45 - pico-train - INFO - │ num_devices: 1 │ 2025-08-30 16:20:45 - pico-train - INFO - │ num_nodes: 1 │ 2025-08-30 16:20:45 - pico-train - INFO - │ precision: bf16-mixed │ 2025-08-30 16:20:45 - pico-train - INFO - │ max_steps: 100000 │ 2025-08-30 16:20:45 - pico-train - INFO - │ optimization: │ 2025-08-30 16:20:45 - pico-train - INFO - │ gradient_accumulation_steps: 1 │ 2025-08-30 16:20:45 - pico-train - INFO - │ lr: 0.0002 │ 2025-08-30 16:20:45 - pico-train - INFO - │ lr_scheduler: cosine │ 2025-08-30 16:20:45 - pico-train - INFO - │ lr_warmup_steps: 2000 │ 2025-08-30 16:20:45 - pico-train - INFO - │ optimizer: adamw │ 2025-08-30 16:20:45 - pico-train - INFO - │ │ 2025-08-30 16:20:45 - pico-train - INFO - ╰─────────────────────────────────────────────────────╯ 2025-08-30 16:20:45 - pico-train - INFO - ================================================== 2025-08-30 16:20:45 - pico-train - INFO - ⛭ Runtime Summary: 2025-08-30 16:20:45 - pico-train - INFO - ================================================== 2025-08-30 16:20:45 - pico-train - INFO - Starting from step: 0 2025-08-30 16:20:45 - pico-train - INFO - Model Setup: 2025-08-30 16:20:45 - pico-train - INFO - └─ Total Parameters: 11,282,784 2025-08-30 16:20:45 - pico-train - INFO - └─ Trainable Parameters: 11,282,784 2025-08-30 16:20:45 - pico-train - INFO - Distributed Setup: 2025-08-30 16:20:45 - pico-train - INFO - └─ Number of Devices: 1 2025-08-30 16:20:45 - pico-train - INFO - └─ Device Type: NVIDIA H100 PCIe 2025-08-30 16:20:45 - pico-train - INFO - └─ Available Memory: 84.94 GB 2025-08-30 16:20:45 - pico-train - INFO - Software Setup: 2025-08-30 16:20:45 - pico-train - INFO - └─ Python Version: 3.10.12 2025-08-30 16:20:45 - pico-train - INFO - └─ PyTorch Version: 2.8.0+cu128 2025-08-30 16:20:45 - pico-train - INFO - └─ CUDA Version: 12.8 2025-08-30 16:20:45 - pico-train - INFO - └─ Operating System: Linux 6.8.0-40-generic 2025-08-30 16:20:45 - pico-train - INFO - Batch Size Configuration: 2025-08-30 16:20:45 - pico-train - INFO - └─ Global Batch Size: 16 2025-08-30 16:20:45 - pico-train - INFO - └─ Per Device Batch Size: 16 2025-08-30 16:20:45 - pico-train - INFO - └─ Gradient Accumulation Steps: 1 2025-08-30 16:20:45 - pico-train - INFO - ================================================== 2025-08-30 16:20:47 - pico-train - INFO - Step 0 -- 🔄 Training Metrics 2025-08-30 16:20:47 - pico-train - INFO - ├── Loss: 10.9884 2025-08-30 16:20:47 - pico-train - INFO - ├── Learning Rate: 0.00e+00 2025-08-30 16:20:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:20:47 - pico-train - INFO - Step 0 -- 📈 Saving Learning Dynamics 2025-08-30 16:22:00 - pico-train - INFO - Step 100 -- 🔄 Training Metrics 2025-08-30 16:22:00 - pico-train - INFO - ├── Loss: 10.9746 2025-08-30 16:22:00 - pico-train - INFO - ├── Learning Rate: 1.00e-05 2025-08-30 16:22:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:23:12 - pico-train - INFO - Step 200 -- 🔄 Training Metrics 2025-08-30 16:23:12 - pico-train - INFO - ├── Loss: 10.7653 2025-08-30 16:23:12 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-30 16:23:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:24:24 - pico-train - INFO - Step 300 -- 🔄 Training Metrics 2025-08-30 16:24:24 - pico-train - INFO - ├── Loss: 10.2902 2025-08-30 16:24:24 - pico-train - INFO - ├── Learning Rate: 3.00e-05 2025-08-30 16:24:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:25:35 - pico-train - INFO - Step 400 -- 🔄 Training Metrics 2025-08-30 16:25:35 - pico-train - INFO - ├── Loss: 9.8373 2025-08-30 16:25:35 - pico-train - INFO - ├── Learning Rate: 4.00e-05 2025-08-30 16:25:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:26:47 - pico-train - INFO - Step 500 -- 🔄 Training Metrics 2025-08-30 16:26:47 - pico-train - INFO - ├── Loss: 9.3629 2025-08-30 16:26:47 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-30 16:26:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:27:57 - pico-train - INFO - Step 600 -- 🔄 Training Metrics 2025-08-30 16:27:57 - pico-train - INFO - ├── Loss: 8.8887 2025-08-30 16:27:57 - pico-train - INFO - ├── Learning Rate: 6.00e-05 2025-08-30 16:27:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:29:09 - pico-train - INFO - Step 700 -- 🔄 Training Metrics 2025-08-30 16:29:09 - pico-train - INFO - ├── Loss: 8.4407 2025-08-30 16:29:09 - pico-train - INFO - ├── Learning Rate: 7.00e-05 2025-08-30 16:29:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:30:21 - pico-train - INFO - Step 800 -- 🔄 Training Metrics 2025-08-30 16:30:21 - pico-train - INFO - ├── Loss: 8.0906 2025-08-30 16:30:21 - pico-train - INFO - ├── Learning Rate: 8.00e-05 2025-08-30 16:30:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:31:32 - pico-train - INFO - Step 900 -- 🔄 Training Metrics 2025-08-30 16:31:32 - pico-train - INFO - ├── Loss: 7.8459 2025-08-30 16:31:32 - pico-train - INFO - ├── Learning Rate: 9.00e-05 2025-08-30 16:31:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:32:42 - pico-train - INFO - Step 1000 -- 💾 Saving Checkpoint 2025-08-30 16:34:45 - pico-train - INFO - Step 1000 -- 📊 Evaluation Results 2025-08-30 16:34:45 - pico-train - INFO - └── paloma: 1.4389863020037474e+19 2025-08-30 16:34:47 - pico-train - INFO - Step 1000 -- 🔄 Training Metrics 2025-08-30 16:34:47 - pico-train - INFO - ├── Loss: 7.6972 2025-08-30 16:34:47 - pico-train - INFO - ├── Learning Rate: 1.00e-04 2025-08-30 16:34:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:34:47 - pico-train - INFO - Step 1000 -- 📈 Saving Learning Dynamics 2025-08-30 16:36:00 - pico-train - INFO - Step 1100 -- 🔄 Training Metrics 2025-08-30 16:36:00 - pico-train - INFO - ├── Loss: 7.5571 2025-08-30 16:36:00 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-30 16:36:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:37:11 - pico-train - INFO - Step 1200 -- 🔄 Training Metrics 2025-08-30 16:37:11 - pico-train - INFO - ├── Loss: 7.4823 2025-08-30 16:37:11 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-30 16:37:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:38:24 - pico-train - INFO - Step 1300 -- 🔄 Training Metrics 2025-08-30 16:38:24 - pico-train - INFO - ├── Loss: 7.3624 2025-08-30 16:38:24 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-30 16:38:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:39:34 - pico-train - INFO - Step 1400 -- 🔄 Training Metrics 2025-08-30 16:39:34 - pico-train - INFO - ├── Loss: 7.2538 2025-08-30 16:39:34 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-30 16:39:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:40:45 - pico-train - INFO - Step 1500 -- 🔄 Training Metrics 2025-08-30 16:40:45 - pico-train - INFO - ├── Loss: 7.1582 2025-08-30 16:40:45 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-30 16:40:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:41:56 - pico-train - INFO - Step 1600 -- 🔄 Training Metrics 2025-08-30 16:41:56 - pico-train - INFO - ├── Loss: 7.0463 2025-08-30 16:41:56 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 16:41:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:43:08 - pico-train - INFO - Step 1700 -- 🔄 Training Metrics 2025-08-30 16:43:08 - pico-train - INFO - ├── Loss: 6.9729 2025-08-30 16:43:08 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 16:43:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:44:19 - pico-train - INFO - Step 1800 -- 🔄 Training Metrics 2025-08-30 16:44:19 - pico-train - INFO - ├── Loss: 6.8826 2025-08-30 16:44:19 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 16:44:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:45:30 - pico-train - INFO - Step 1900 -- 🔄 Training Metrics 2025-08-30 16:45:30 - pico-train - INFO - ├── Loss: 6.8004 2025-08-30 16:45:30 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 16:45:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:46:40 - pico-train - INFO - Step 2000 -- 💾 Saving Checkpoint 2025-08-30 16:48:43 - pico-train - INFO - Step 2000 -- 📊 Evaluation Results 2025-08-30 16:48:43 - pico-train - INFO - └── paloma: 9.921210281541321e+20 2025-08-30 16:48:43 - pico-train - INFO - Step 2000 -- 🔄 Training Metrics 2025-08-30 16:48:43 - pico-train - INFO - ├── Loss: 6.7360 2025-08-30 16:48:43 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:48:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:48:43 - pico-train - INFO - Step 2000 -- 📈 Saving Learning Dynamics 2025-08-30 16:49:57 - pico-train - INFO - Step 2100 -- 🔄 Training Metrics 2025-08-30 16:49:57 - pico-train - INFO - ├── Loss: 6.6659 2025-08-30 16:49:57 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:49:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:51:08 - pico-train - INFO - Step 2200 -- 🔄 Training Metrics 2025-08-30 16:51:08 - pico-train - INFO - ├── Loss: 6.6041 2025-08-30 16:51:08 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:51:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:52:20 - pico-train - INFO - Step 2300 -- 🔄 Training Metrics 2025-08-30 16:52:20 - pico-train - INFO - ├── Loss: 6.5361 2025-08-30 16:52:20 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:52:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:53:30 - pico-train - INFO - Step 2400 -- 🔄 Training Metrics 2025-08-30 16:53:30 - pico-train - INFO - ├── Loss: 6.5012 2025-08-30 16:53:30 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:53:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:54:41 - pico-train - INFO - Step 2500 -- 🔄 Training Metrics 2025-08-30 16:54:41 - pico-train - INFO - ├── Loss: 6.4542 2025-08-30 16:54:41 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:54:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:55:53 - pico-train - INFO - Step 2600 -- 🔄 Training Metrics 2025-08-30 16:55:53 - pico-train - INFO - ├── Loss: 6.4300 2025-08-30 16:55:53 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:55:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:57:04 - pico-train - INFO - Step 2700 -- 🔄 Training Metrics 2025-08-30 16:57:04 - pico-train - INFO - ├── Loss: 6.3678 2025-08-30 16:57:04 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:57:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:58:15 - pico-train - INFO - Step 2800 -- 🔄 Training Metrics 2025-08-30 16:58:15 - pico-train - INFO - ├── Loss: 6.3538 2025-08-30 16:58:15 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:58:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 16:59:26 - pico-train - INFO - Step 2900 -- 🔄 Training Metrics 2025-08-30 16:59:26 - pico-train - INFO - ├── Loss: 6.3226 2025-08-30 16:59:26 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 16:59:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:00:37 - pico-train - INFO - Step 3000 -- 💾 Saving Checkpoint 2025-08-30 17:02:39 - pico-train - INFO - Step 3000 -- 📊 Evaluation Results 2025-08-30 17:02:39 - pico-train - INFO - └── paloma: 1.410569515309224e+22 2025-08-30 17:02:39 - pico-train - INFO - Step 3000 -- 🔄 Training Metrics 2025-08-30 17:02:39 - pico-train - INFO - ├── Loss: 6.2808 2025-08-30 17:02:39 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:02:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:02:39 - pico-train - INFO - Step 3000 -- 📈 Saving Learning Dynamics 2025-08-30 17:03:54 - pico-train - INFO - Step 3100 -- 🔄 Training Metrics 2025-08-30 17:03:54 - pico-train - INFO - ├── Loss: 6.2628 2025-08-30 17:03:54 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:03:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:05:05 - pico-train - INFO - Step 3200 -- 🔄 Training Metrics 2025-08-30 17:05:05 - pico-train - INFO - ├── Loss: 6.2207 2025-08-30 17:05:05 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:05:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:06:15 - pico-train - INFO - Step 3300 -- 🔄 Training Metrics 2025-08-30 17:06:15 - pico-train - INFO - ├── Loss: 6.2142 2025-08-30 17:06:15 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:06:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:07:26 - pico-train - INFO - Step 3400 -- 🔄 Training Metrics 2025-08-30 17:07:26 - pico-train - INFO - ├── Loss: 6.1526 2025-08-30 17:07:26 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:07:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:08:37 - pico-train - INFO - Step 3500 -- 🔄 Training Metrics 2025-08-30 17:08:37 - pico-train - INFO - ├── Loss: 6.1105 2025-08-30 17:08:37 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:08:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:09:49 - pico-train - INFO - Step 3600 -- 🔄 Training Metrics 2025-08-30 17:09:49 - pico-train - INFO - ├── Loss: 6.1327 2025-08-30 17:09:49 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:09:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:11:00 - pico-train - INFO - Step 3700 -- 🔄 Training Metrics 2025-08-30 17:11:00 - pico-train - INFO - ├── Loss: 6.1047 2025-08-30 17:11:00 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:11:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:12:11 - pico-train - INFO - Step 3800 -- 🔄 Training Metrics 2025-08-30 17:12:11 - pico-train - INFO - ├── Loss: 6.0910 2025-08-30 17:12:11 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:12:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:13:23 - pico-train - INFO - Step 3900 -- 🔄 Training Metrics 2025-08-30 17:13:23 - pico-train - INFO - ├── Loss: 6.0370 2025-08-30 17:13:23 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:13:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:14:33 - pico-train - INFO - Step 4000 -- 💾 Saving Checkpoint 2025-08-30 17:16:35 - pico-train - INFO - Step 4000 -- 📊 Evaluation Results 2025-08-30 17:16:35 - pico-train - INFO - └── paloma: 3.516532942334589e+23 2025-08-30 17:16:35 - pico-train - INFO - Step 4000 -- 🔄 Training Metrics 2025-08-30 17:16:35 - pico-train - INFO - ├── Loss: 6.0450 2025-08-30 17:16:35 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:16:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:16:35 - pico-train - INFO - Step 4000 -- 📈 Saving Learning Dynamics 2025-08-30 17:17:49 - pico-train - INFO - Step 4100 -- 🔄 Training Metrics 2025-08-30 17:17:49 - pico-train - INFO - ├── Loss: 6.0121 2025-08-30 17:17:49 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:17:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:19:00 - pico-train - INFO - Step 4200 -- 🔄 Training Metrics 2025-08-30 17:19:00 - pico-train - INFO - ├── Loss: 5.9897 2025-08-30 17:19:00 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:19:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:20:11 - pico-train - INFO - Step 4300 -- 🔄 Training Metrics 2025-08-30 17:20:11 - pico-train - INFO - ├── Loss: 5.9636 2025-08-30 17:20:11 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:20:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:21:22 - pico-train - INFO - Step 4400 -- 🔄 Training Metrics 2025-08-30 17:21:22 - pico-train - INFO - ├── Loss: 5.9760 2025-08-30 17:21:22 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:21:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:22:33 - pico-train - INFO - Step 4500 -- 🔄 Training Metrics 2025-08-30 17:22:33 - pico-train - INFO - ├── Loss: 5.9551 2025-08-30 17:22:33 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:22:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:23:45 - pico-train - INFO - Step 4600 -- 🔄 Training Metrics 2025-08-30 17:23:45 - pico-train - INFO - ├── Loss: 5.9166 2025-08-30 17:23:45 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:23:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:24:55 - pico-train - INFO - Step 4700 -- 🔄 Training Metrics 2025-08-30 17:24:55 - pico-train - INFO - ├── Loss: 5.8940 2025-08-30 17:24:55 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:24:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:26:07 - pico-train - INFO - Step 4800 -- 🔄 Training Metrics 2025-08-30 17:26:07 - pico-train - INFO - ├── Loss: 5.8770 2025-08-30 17:26:07 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:26:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:27:19 - pico-train - INFO - Step 4900 -- 🔄 Training Metrics 2025-08-30 17:27:19 - pico-train - INFO - ├── Loss: 5.8605 2025-08-30 17:27:19 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:27:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:28:29 - pico-train - INFO - Step 5000 -- 💾 Saving Checkpoint 2025-08-30 17:30:32 - pico-train - INFO - Step 5000 -- 📊 Evaluation Results 2025-08-30 17:30:32 - pico-train - INFO - └── paloma: 1.1285856883470545e+25 2025-08-30 17:30:32 - pico-train - INFO - Step 5000 -- 🔄 Training Metrics 2025-08-30 17:30:32 - pico-train - INFO - ├── Loss: 5.8727 2025-08-30 17:30:32 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:30:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:30:32 - pico-train - INFO - Step 5000 -- 📈 Saving Learning Dynamics 2025-08-30 17:31:46 - pico-train - INFO - Step 5100 -- 🔄 Training Metrics 2025-08-30 17:31:46 - pico-train - INFO - ├── Loss: 5.8447 2025-08-30 17:31:46 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 17:31:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:32:58 - pico-train - INFO - Step 5200 -- 🔄 Training Metrics 2025-08-30 17:32:58 - pico-train - INFO - ├── Loss: 5.8290 2025-08-30 17:32:58 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:32:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:34:09 - pico-train - INFO - Step 5300 -- 🔄 Training Metrics 2025-08-30 17:34:09 - pico-train - INFO - ├── Loss: 5.8219 2025-08-30 17:34:09 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:34:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:35:20 - pico-train - INFO - Step 5400 -- 🔄 Training Metrics 2025-08-30 17:35:20 - pico-train - INFO - ├── Loss: 5.8133 2025-08-30 17:35:20 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:35:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:36:31 - pico-train - INFO - Step 5500 -- 🔄 Training Metrics 2025-08-30 17:36:31 - pico-train - INFO - ├── Loss: 5.7878 2025-08-30 17:36:31 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:36:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:37:42 - pico-train - INFO - Step 5600 -- 🔄 Training Metrics 2025-08-30 17:37:42 - pico-train - INFO - ├── Loss: 5.7639 2025-08-30 17:37:42 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:37:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:38:53 - pico-train - INFO - Step 5700 -- 🔄 Training Metrics 2025-08-30 17:38:53 - pico-train - INFO - ├── Loss: 5.7699 2025-08-30 17:38:53 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:38:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:40:04 - pico-train - INFO - Step 5800 -- 🔄 Training Metrics 2025-08-30 17:40:04 - pico-train - INFO - ├── Loss: 5.7458 2025-08-30 17:40:04 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:40:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:41:15 - pico-train - INFO - Step 5900 -- 🔄 Training Metrics 2025-08-30 17:41:15 - pico-train - INFO - ├── Loss: 5.7482 2025-08-30 17:41:15 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:41:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:42:26 - pico-train - INFO - Step 6000 -- 💾 Saving Checkpoint 2025-08-30 17:44:27 - pico-train - INFO - Step 6000 -- 📊 Evaluation Results 2025-08-30 17:44:27 - pico-train - INFO - └── paloma: 5.5635981050246924e+26 2025-08-30 17:44:28 - pico-train - INFO - Step 6000 -- 🔄 Training Metrics 2025-08-30 17:44:28 - pico-train - INFO - ├── Loss: 5.7402 2025-08-30 17:44:28 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:44:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:44:28 - pico-train - INFO - Step 6000 -- 📈 Saving Learning Dynamics 2025-08-30 17:45:41 - pico-train - INFO - Step 6100 -- 🔄 Training Metrics 2025-08-30 17:45:41 - pico-train - INFO - ├── Loss: 5.7377 2025-08-30 17:45:41 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:45:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:46:53 - pico-train - INFO - Step 6200 -- 🔄 Training Metrics 2025-08-30 17:46:53 - pico-train - INFO - ├── Loss: 5.6951 2025-08-30 17:46:53 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:46:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:48:04 - pico-train - INFO - Step 6300 -- 🔄 Training Metrics 2025-08-30 17:48:04 - pico-train - INFO - ├── Loss: 5.6844 2025-08-30 17:48:04 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:48:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:49:17 - pico-train - INFO - Step 6400 -- 🔄 Training Metrics 2025-08-30 17:49:17 - pico-train - INFO - ├── Loss: 5.6903 2025-08-30 17:49:17 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:49:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:50:27 - pico-train - INFO - Step 6500 -- 🔄 Training Metrics 2025-08-30 17:50:27 - pico-train - INFO - ├── Loss: 5.6878 2025-08-30 17:50:27 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:50:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:51:38 - pico-train - INFO - Step 6600 -- 🔄 Training Metrics 2025-08-30 17:51:38 - pico-train - INFO - ├── Loss: 5.6539 2025-08-30 17:51:38 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:51:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:52:49 - pico-train - INFO - Step 6700 -- 🔄 Training Metrics 2025-08-30 17:52:49 - pico-train - INFO - ├── Loss: 5.6436 2025-08-30 17:52:49 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:52:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:54:01 - pico-train - INFO - Step 6800 -- 🔄 Training Metrics 2025-08-30 17:54:01 - pico-train - INFO - ├── Loss: 5.6443 2025-08-30 17:54:01 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:54:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:55:12 - pico-train - INFO - Step 6900 -- 🔄 Training Metrics 2025-08-30 17:55:12 - pico-train - INFO - ├── Loss: 5.6237 2025-08-30 17:55:12 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:55:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:56:22 - pico-train - INFO - Step 7000 -- 💾 Saving Checkpoint 2025-08-30 17:58:23 - pico-train - INFO - Step 7000 -- 📊 Evaluation Results 2025-08-30 17:58:23 - pico-train - INFO - └── paloma: 5.625059129813264e+28 2025-08-30 17:58:24 - pico-train - INFO - Step 7000 -- 🔄 Training Metrics 2025-08-30 17:58:24 - pico-train - INFO - ├── Loss: 5.6189 2025-08-30 17:58:24 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:58:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 17:58:24 - pico-train - INFO - Step 7000 -- 📈 Saving Learning Dynamics 2025-08-30 17:59:37 - pico-train - INFO - Step 7100 -- 🔄 Training Metrics 2025-08-30 17:59:37 - pico-train - INFO - ├── Loss: 5.5781 2025-08-30 17:59:37 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 17:59:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:00:48 - pico-train - INFO - Step 7200 -- 🔄 Training Metrics 2025-08-30 18:00:48 - pico-train - INFO - ├── Loss: 5.6113 2025-08-30 18:00:48 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 18:00:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:01:59 - pico-train - INFO - Step 7300 -- 🔄 Training Metrics 2025-08-30 18:01:59 - pico-train - INFO - ├── Loss: 5.5985 2025-08-30 18:01:59 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 18:01:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:03:11 - pico-train - INFO - Step 7400 -- 🔄 Training Metrics 2025-08-30 18:03:11 - pico-train - INFO - ├── Loss: 5.6009 2025-08-30 18:03:11 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 18:03:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:04:21 - pico-train - INFO - Step 7500 -- 🔄 Training Metrics 2025-08-30 18:04:21 - pico-train - INFO - ├── Loss: 5.5714 2025-08-30 18:04:21 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:04:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:05:32 - pico-train - INFO - Step 7600 -- 🔄 Training Metrics 2025-08-30 18:05:32 - pico-train - INFO - ├── Loss: 5.5714 2025-08-30 18:05:32 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:05:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:06:44 - pico-train - INFO - Step 7700 -- 🔄 Training Metrics 2025-08-30 18:06:44 - pico-train - INFO - ├── Loss: 5.5653 2025-08-30 18:06:44 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:06:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:07:55 - pico-train - INFO - Step 7800 -- 🔄 Training Metrics 2025-08-30 18:07:55 - pico-train - INFO - ├── Loss: 5.5558 2025-08-30 18:07:55 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:07:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:09:06 - pico-train - INFO - Step 7900 -- 🔄 Training Metrics 2025-08-30 18:09:06 - pico-train - INFO - ├── Loss: 5.5568 2025-08-30 18:09:06 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:09:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:10:16 - pico-train - INFO - Step 8000 -- 💾 Saving Checkpoint 2025-08-30 18:12:18 - pico-train - INFO - Step 8000 -- 📊 Evaluation Results 2025-08-30 18:12:18 - pico-train - INFO - └── paloma: 2.8189708405471985e+30 2025-08-30 18:12:19 - pico-train - INFO - Step 8000 -- 🔄 Training Metrics 2025-08-30 18:12:19 - pico-train - INFO - ├── Loss: 5.5268 2025-08-30 18:12:19 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:12:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:12:19 - pico-train - INFO - Step 8000 -- 📈 Saving Learning Dynamics 2025-08-30 18:13:32 - pico-train - INFO - Step 8100 -- 🔄 Training Metrics 2025-08-30 18:13:32 - pico-train - INFO - ├── Loss: 5.5294 2025-08-30 18:13:32 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:13:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:14:43 - pico-train - INFO - Step 8200 -- 🔄 Training Metrics 2025-08-30 18:14:43 - pico-train - INFO - ├── Loss: 5.5350 2025-08-30 18:14:43 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:14:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:15:54 - pico-train - INFO - Step 8300 -- 🔄 Training Metrics 2025-08-30 18:15:54 - pico-train - INFO - ├── Loss: 5.5279 2025-08-30 18:15:54 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:15:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:17:05 - pico-train - INFO - Step 8400 -- 🔄 Training Metrics 2025-08-30 18:17:05 - pico-train - INFO - ├── Loss: 5.4997 2025-08-30 18:17:05 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:17:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:18:16 - pico-train - INFO - Step 8500 -- 🔄 Training Metrics 2025-08-30 18:18:16 - pico-train - INFO - ├── Loss: 5.4873 2025-08-30 18:18:16 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:18:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:19:27 - pico-train - INFO - Step 8600 -- 🔄 Training Metrics 2025-08-30 18:19:27 - pico-train - INFO - ├── Loss: 5.5047 2025-08-30 18:19:27 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:19:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:20:38 - pico-train - INFO - Step 8700 -- 🔄 Training Metrics 2025-08-30 18:20:38 - pico-train - INFO - ├── Loss: 5.4809 2025-08-30 18:20:38 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:20:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:21:49 - pico-train - INFO - Step 8800 -- 🔄 Training Metrics 2025-08-30 18:21:49 - pico-train - INFO - ├── Loss: 5.4858 2025-08-30 18:21:49 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:21:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:23:00 - pico-train - INFO - Step 8900 -- 🔄 Training Metrics 2025-08-30 18:23:00 - pico-train - INFO - ├── Loss: 5.4689 2025-08-30 18:23:00 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 18:23:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:24:12 - pico-train - INFO - Step 9000 -- 💾 Saving Checkpoint 2025-08-30 18:26:13 - pico-train - INFO - Step 9000 -- 📊 Evaluation Results 2025-08-30 18:26:13 - pico-train - INFO - └── paloma: 3.5931189083569604e+33 2025-08-30 18:26:14 - pico-train - INFO - Step 9000 -- 🔄 Training Metrics 2025-08-30 18:26:14 - pico-train - INFO - ├── Loss: 5.4476 2025-08-30 18:26:14 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:26:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:26:14 - pico-train - INFO - Step 9000 -- 📈 Saving Learning Dynamics 2025-08-30 18:27:28 - pico-train - INFO - Step 9100 -- 🔄 Training Metrics 2025-08-30 18:27:28 - pico-train - INFO - ├── Loss: 5.4383 2025-08-30 18:27:28 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:27:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:28:38 - pico-train - INFO - Step 9200 -- 🔄 Training Metrics 2025-08-30 18:28:38 - pico-train - INFO - ├── Loss: 5.4568 2025-08-30 18:28:38 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:28:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:29:50 - pico-train - INFO - Step 9300 -- 🔄 Training Metrics 2025-08-30 18:29:50 - pico-train - INFO - ├── Loss: 5.4368 2025-08-30 18:29:50 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:29:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:31:01 - pico-train - INFO - Step 9400 -- 🔄 Training Metrics 2025-08-30 18:31:01 - pico-train - INFO - ├── Loss: 5.4623 2025-08-30 18:31:01 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:31:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:32:12 - pico-train - INFO - Step 9500 -- 🔄 Training Metrics 2025-08-30 18:32:12 - pico-train - INFO - ├── Loss: 5.4268 2025-08-30 18:32:12 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:32:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:33:24 - pico-train - INFO - Step 9600 -- 🔄 Training Metrics 2025-08-30 18:33:24 - pico-train - INFO - ├── Loss: 5.4640 2025-08-30 18:33:24 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:33:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:34:34 - pico-train - INFO - Step 9700 -- 🔄 Training Metrics 2025-08-30 18:34:34 - pico-train - INFO - ├── Loss: 5.4520 2025-08-30 18:34:34 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:34:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:35:45 - pico-train - INFO - Step 9800 -- 🔄 Training Metrics 2025-08-30 18:35:45 - pico-train - INFO - ├── Loss: 5.4139 2025-08-30 18:35:45 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:35:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:36:56 - pico-train - INFO - Step 9900 -- 🔄 Training Metrics 2025-08-30 18:36:56 - pico-train - INFO - ├── Loss: 5.4025 2025-08-30 18:36:56 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:36:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:38:07 - pico-train - INFO - Step 10000 -- 💾 Saving Checkpoint 2025-08-30 18:40:09 - pico-train - INFO - Step 10000 -- 📊 Evaluation Results 2025-08-30 18:40:09 - pico-train - INFO - └── paloma: 9.887912407124033e+34 2025-08-30 18:40:10 - pico-train - INFO - Step 10000 -- 🔄 Training Metrics 2025-08-30 18:40:10 - pico-train - INFO - ├── Loss: 5.4191 2025-08-30 18:40:10 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:40:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:40:10 - pico-train - INFO - Step 10000 -- 📈 Saving Learning Dynamics 2025-08-30 18:41:23 - pico-train - INFO - Step 10100 -- 🔄 Training Metrics 2025-08-30 18:41:23 - pico-train - INFO - ├── Loss: 5.3756 2025-08-30 18:41:23 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:41:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:42:34 - pico-train - INFO - Step 10200 -- 🔄 Training Metrics 2025-08-30 18:42:34 - pico-train - INFO - ├── Loss: 5.3976 2025-08-30 18:42:34 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 18:42:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:43:46 - pico-train - INFO - Step 10300 -- 🔄 Training Metrics 2025-08-30 18:43:46 - pico-train - INFO - ├── Loss: 5.4048 2025-08-30 18:43:46 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:43:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:44:57 - pico-train - INFO - Step 10400 -- 🔄 Training Metrics 2025-08-30 18:44:57 - pico-train - INFO - ├── Loss: 5.3990 2025-08-30 18:44:57 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:44:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:46:08 - pico-train - INFO - Step 10500 -- 🔄 Training Metrics 2025-08-30 18:46:08 - pico-train - INFO - ├── Loss: 5.4016 2025-08-30 18:46:08 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:46:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:47:19 - pico-train - INFO - Step 10600 -- 🔄 Training Metrics 2025-08-30 18:47:19 - pico-train - INFO - ├── Loss: 5.3924 2025-08-30 18:47:19 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:47:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:48:30 - pico-train - INFO - Step 10700 -- 🔄 Training Metrics 2025-08-30 18:48:30 - pico-train - INFO - ├── Loss: 5.3780 2025-08-30 18:48:30 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:48:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:49:41 - pico-train - INFO - Step 10800 -- 🔄 Training Metrics 2025-08-30 18:49:41 - pico-train - INFO - ├── Loss: 5.3432 2025-08-30 18:49:41 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:49:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:50:52 - pico-train - INFO - Step 10900 -- 🔄 Training Metrics 2025-08-30 18:50:52 - pico-train - INFO - ├── Loss: 5.3610 2025-08-30 18:50:52 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:50:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:52:03 - pico-train - INFO - Step 11000 -- 💾 Saving Checkpoint 2025-08-30 18:54:05 - pico-train - INFO - Step 11000 -- 📊 Evaluation Results 2025-08-30 18:54:05 - pico-train - INFO - └── paloma: inf 2025-08-30 18:54:06 - pico-train - INFO - Step 11000 -- 🔄 Training Metrics 2025-08-30 18:54:06 - pico-train - INFO - ├── Loss: 5.3561 2025-08-30 18:54:06 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:54:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:54:06 - pico-train - INFO - Step 11000 -- 📈 Saving Learning Dynamics 2025-08-30 18:55:19 - pico-train - INFO - Step 11100 -- 🔄 Training Metrics 2025-08-30 18:55:19 - pico-train - INFO - ├── Loss: 5.3818 2025-08-30 18:55:19 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:55:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:56:30 - pico-train - INFO - Step 11200 -- 🔄 Training Metrics 2025-08-30 18:56:30 - pico-train - INFO - ├── Loss: 5.3595 2025-08-30 18:56:30 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:56:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:57:42 - pico-train - INFO - Step 11300 -- 🔄 Training Metrics 2025-08-30 18:57:42 - pico-train - INFO - ├── Loss: 5.3557 2025-08-30 18:57:42 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 18:57:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 18:58:53 - pico-train - INFO - Step 11400 -- 🔄 Training Metrics 2025-08-30 18:58:53 - pico-train - INFO - ├── Loss: 5.3483 2025-08-30 18:58:53 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 18:58:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:00:04 - pico-train - INFO - Step 11500 -- 🔄 Training Metrics 2025-08-30 19:00:04 - pico-train - INFO - ├── Loss: 5.3398 2025-08-30 19:00:04 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:00:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:01:15 - pico-train - INFO - Step 11600 -- 🔄 Training Metrics 2025-08-30 19:01:15 - pico-train - INFO - ├── Loss: 5.3252 2025-08-30 19:01:15 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:01:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:02:27 - pico-train - INFO - Step 11700 -- 🔄 Training Metrics 2025-08-30 19:02:27 - pico-train - INFO - ├── Loss: 5.3194 2025-08-30 19:02:27 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:02:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:03:38 - pico-train - INFO - Step 11800 -- 🔄 Training Metrics 2025-08-30 19:03:38 - pico-train - INFO - ├── Loss: 5.3386 2025-08-30 19:03:38 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:03:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:04:49 - pico-train - INFO - Step 11900 -- 🔄 Training Metrics 2025-08-30 19:04:49 - pico-train - INFO - ├── Loss: 5.3458 2025-08-30 19:04:49 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:04:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:05:59 - pico-train - INFO - Step 12000 -- 💾 Saving Checkpoint 2025-08-30 19:08:01 - pico-train - INFO - Step 12000 -- 📊 Evaluation Results 2025-08-30 19:08:01 - pico-train - INFO - └── paloma: inf 2025-08-30 19:08:01 - pico-train - INFO - Step 12000 -- 🔄 Training Metrics 2025-08-30 19:08:01 - pico-train - INFO - ├── Loss: 5.3216 2025-08-30 19:08:01 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:08:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:08:01 - pico-train - INFO - Step 12000 -- 📈 Saving Learning Dynamics 2025-08-30 19:09:15 - pico-train - INFO - Step 12100 -- 🔄 Training Metrics 2025-08-30 19:09:15 - pico-train - INFO - ├── Loss: 5.3164 2025-08-30 19:09:15 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:09:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:10:26 - pico-train - INFO - Step 12200 -- 🔄 Training Metrics 2025-08-30 19:10:26 - pico-train - INFO - ├── Loss: 5.3075 2025-08-30 19:10:26 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:10:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:11:38 - pico-train - INFO - Step 12300 -- 🔄 Training Metrics 2025-08-30 19:11:38 - pico-train - INFO - ├── Loss: 5.2907 2025-08-30 19:11:38 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 19:11:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:12:49 - pico-train - INFO - Step 12400 -- 🔄 Training Metrics 2025-08-30 19:12:49 - pico-train - INFO - ├── Loss: 5.2970 2025-08-30 19:12:49 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:12:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:14:00 - pico-train - INFO - Step 12500 -- 🔄 Training Metrics 2025-08-30 19:14:00 - pico-train - INFO - ├── Loss: 5.2849 2025-08-30 19:14:00 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:14:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:15:12 - pico-train - INFO - Step 12600 -- 🔄 Training Metrics 2025-08-30 19:15:12 - pico-train - INFO - ├── Loss: 5.3026 2025-08-30 19:15:12 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:15:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:16:23 - pico-train - INFO - Step 12700 -- 🔄 Training Metrics 2025-08-30 19:16:23 - pico-train - INFO - ├── Loss: 5.2792 2025-08-30 19:16:23 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:16:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:17:35 - pico-train - INFO - Step 12800 -- 🔄 Training Metrics 2025-08-30 19:17:35 - pico-train - INFO - ├── Loss: 5.3026 2025-08-30 19:17:35 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:17:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:18:46 - pico-train - INFO - Step 12900 -- 🔄 Training Metrics 2025-08-30 19:18:46 - pico-train - INFO - ├── Loss: 5.2918 2025-08-30 19:18:46 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:18:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:19:56 - pico-train - INFO - Step 13000 -- 💾 Saving Checkpoint 2025-08-30 19:21:58 - pico-train - INFO - Step 13000 -- 📊 Evaluation Results 2025-08-30 19:21:58 - pico-train - INFO - └── paloma: inf 2025-08-30 19:21:59 - pico-train - INFO - Step 13000 -- 🔄 Training Metrics 2025-08-30 19:21:59 - pico-train - INFO - ├── Loss: 5.3032 2025-08-30 19:21:59 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:21:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:21:59 - pico-train - INFO - Step 13000 -- 📈 Saving Learning Dynamics 2025-08-30 19:23:13 - pico-train - INFO - Step 13100 -- 🔄 Training Metrics 2025-08-30 19:23:13 - pico-train - INFO - ├── Loss: 5.2888 2025-08-30 19:23:13 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:23:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:24:24 - pico-train - INFO - Step 13200 -- 🔄 Training Metrics 2025-08-30 19:24:24 - pico-train - INFO - ├── Loss: 5.2853 2025-08-30 19:24:24 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:24:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:25:35 - pico-train - INFO - Step 13300 -- 🔄 Training Metrics 2025-08-30 19:25:35 - pico-train - INFO - ├── Loss: 5.2828 2025-08-30 19:25:35 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 19:25:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:26:46 - pico-train - INFO - Step 13400 -- 🔄 Training Metrics 2025-08-30 19:26:46 - pico-train - INFO - ├── Loss: 5.2770 2025-08-30 19:26:46 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:26:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:27:57 - pico-train - INFO - Step 13500 -- 🔄 Training Metrics 2025-08-30 19:27:57 - pico-train - INFO - ├── Loss: 5.2645 2025-08-30 19:27:57 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:27:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:29:08 - pico-train - INFO - Step 13600 -- 🔄 Training Metrics 2025-08-30 19:29:08 - pico-train - INFO - ├── Loss: 5.2692 2025-08-30 19:29:08 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:29:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:30:19 - pico-train - INFO - Step 13700 -- 🔄 Training Metrics 2025-08-30 19:30:19 - pico-train - INFO - ├── Loss: 5.2500 2025-08-30 19:30:19 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:30:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:31:31 - pico-train - INFO - Step 13800 -- 🔄 Training Metrics 2025-08-30 19:31:31 - pico-train - INFO - ├── Loss: 5.2655 2025-08-30 19:31:31 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:31:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:32:41 - pico-train - INFO - Step 13900 -- 🔄 Training Metrics 2025-08-30 19:32:41 - pico-train - INFO - ├── Loss: 5.2590 2025-08-30 19:32:41 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:32:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:33:52 - pico-train - INFO - Step 14000 -- 💾 Saving Checkpoint 2025-08-30 19:35:59 - pico-train - INFO - Step 14000 -- 📊 Evaluation Results 2025-08-30 19:35:59 - pico-train - INFO - └── paloma: inf 2025-08-30 19:36:00 - pico-train - INFO - Step 14000 -- 🔄 Training Metrics 2025-08-30 19:36:00 - pico-train - INFO - ├── Loss: 5.2630 2025-08-30 19:36:00 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:36:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:36:00 - pico-train - INFO - Step 14000 -- 📈 Saving Learning Dynamics 2025-08-30 19:37:15 - pico-train - INFO - Step 14100 -- 🔄 Training Metrics 2025-08-30 19:37:15 - pico-train - INFO - ├── Loss: 5.2382 2025-08-30 19:37:15 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 19:37:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:38:25 - pico-train - INFO - Step 14200 -- 🔄 Training Metrics 2025-08-30 19:38:25 - pico-train - INFO - ├── Loss: 5.2504 2025-08-30 19:38:25 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:38:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:39:37 - pico-train - INFO - Step 14300 -- 🔄 Training Metrics 2025-08-30 19:39:37 - pico-train - INFO - ├── Loss: 5.2443 2025-08-30 19:39:37 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:39:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:40:48 - pico-train - INFO - Step 14400 -- 🔄 Training Metrics 2025-08-30 19:40:48 - pico-train - INFO - ├── Loss: 5.2409 2025-08-30 19:40:48 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:40:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:41:59 - pico-train - INFO - Step 14500 -- 🔄 Training Metrics 2025-08-30 19:41:59 - pico-train - INFO - ├── Loss: 5.2553 2025-08-30 19:41:59 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:41:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:43:10 - pico-train - INFO - Step 14600 -- 🔄 Training Metrics 2025-08-30 19:43:10 - pico-train - INFO - ├── Loss: 5.2326 2025-08-30 19:43:10 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:43:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:44:21 - pico-train - INFO - Step 14700 -- 🔄 Training Metrics 2025-08-30 19:44:21 - pico-train - INFO - ├── Loss: 5.2397 2025-08-30 19:44:21 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:44:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:45:33 - pico-train - INFO - Step 14800 -- 🔄 Training Metrics 2025-08-30 19:45:33 - pico-train - INFO - ├── Loss: 5.2355 2025-08-30 19:45:33 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:45:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:46:44 - pico-train - INFO - Step 14900 -- 🔄 Training Metrics 2025-08-30 19:46:44 - pico-train - INFO - ├── Loss: 5.2328 2025-08-30 19:46:44 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 19:46:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:47:54 - pico-train - INFO - Step 15000 -- 💾 Saving Checkpoint 2025-08-30 19:49:56 - pico-train - INFO - Step 15000 -- 📊 Evaluation Results 2025-08-30 19:49:56 - pico-train - INFO - └── paloma: inf 2025-08-30 19:49:56 - pico-train - INFO - Step 15000 -- 🔄 Training Metrics 2025-08-30 19:49:56 - pico-train - INFO - ├── Loss: 5.2308 2025-08-30 19:49:56 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:49:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:49:56 - pico-train - INFO - Step 15000 -- 📈 Saving Learning Dynamics 2025-08-30 19:51:11 - pico-train - INFO - Step 15100 -- 🔄 Training Metrics 2025-08-30 19:51:11 - pico-train - INFO - ├── Loss: 5.2283 2025-08-30 19:51:11 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:51:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:52:21 - pico-train - INFO - Step 15200 -- 🔄 Training Metrics 2025-08-30 19:52:21 - pico-train - INFO - ├── Loss: 5.2300 2025-08-30 19:52:21 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:52:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:53:32 - pico-train - INFO - Step 15300 -- 🔄 Training Metrics 2025-08-30 19:53:32 - pico-train - INFO - ├── Loss: 5.2523 2025-08-30 19:53:32 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:53:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:54:44 - pico-train - INFO - Step 15400 -- 🔄 Training Metrics 2025-08-30 19:54:44 - pico-train - INFO - ├── Loss: 5.2163 2025-08-30 19:54:44 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:54:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:55:55 - pico-train - INFO - Step 15500 -- 🔄 Training Metrics 2025-08-30 19:55:55 - pico-train - INFO - ├── Loss: 5.2331 2025-08-30 19:55:55 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:55:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:57:06 - pico-train - INFO - Step 15600 -- 🔄 Training Metrics 2025-08-30 19:57:06 - pico-train - INFO - ├── Loss: 5.2262 2025-08-30 19:57:06 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:57:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:58:17 - pico-train - INFO - Step 15700 -- 🔄 Training Metrics 2025-08-30 19:58:17 - pico-train - INFO - ├── Loss: 5.2087 2025-08-30 19:58:17 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 19:58:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 19:59:28 - pico-train - INFO - Step 15800 -- 🔄 Training Metrics 2025-08-30 19:59:28 - pico-train - INFO - ├── Loss: 5.2198 2025-08-30 19:59:28 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 19:59:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:00:40 - pico-train - INFO - Step 15900 -- 🔄 Training Metrics 2025-08-30 20:00:40 - pico-train - INFO - ├── Loss: 5.2056 2025-08-30 20:00:40 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 20:00:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:01:50 - pico-train - INFO - Step 16000 -- 💾 Saving Checkpoint 2025-08-30 20:03:52 - pico-train - INFO - Step 16000 -- 📊 Evaluation Results 2025-08-30 20:03:52 - pico-train - INFO - └── paloma: inf 2025-08-30 20:03:53 - pico-train - INFO - Step 16000 -- 🔄 Training Metrics 2025-08-30 20:03:53 - pico-train - INFO - ├── Loss: 5.2087 2025-08-30 20:03:53 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 20:03:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:03:53 - pico-train - INFO - Step 16000 -- 📈 Saving Learning Dynamics 2025-08-30 20:05:06 - pico-train - INFO - Step 16100 -- 🔄 Training Metrics 2025-08-30 20:05:06 - pico-train - INFO - ├── Loss: 5.1931 2025-08-30 20:05:06 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 20:05:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:06:18 - pico-train - INFO - Step 16200 -- 🔄 Training Metrics 2025-08-30 20:06:18 - pico-train - INFO - ├── Loss: 5.1773 2025-08-30 20:06:18 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 20:06:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:07:29 - pico-train - INFO - Step 16300 -- 🔄 Training Metrics 2025-08-30 20:07:29 - pico-train - INFO - ├── Loss: 5.2031 2025-08-30 20:07:29 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 20:07:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:08:40 - pico-train - INFO - Step 16400 -- 🔄 Training Metrics 2025-08-30 20:08:40 - pico-train - INFO - ├── Loss: 5.1868 2025-08-30 20:08:40 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 20:08:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:09:52 - pico-train - INFO - Step 16500 -- 🔄 Training Metrics 2025-08-30 20:09:52 - pico-train - INFO - ├── Loss: 5.1763 2025-08-30 20:09:52 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 20:09:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:11:02 - pico-train - INFO - Step 16600 -- 🔄 Training Metrics 2025-08-30 20:11:02 - pico-train - INFO - ├── Loss: 5.2021 2025-08-30 20:11:02 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 20:11:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:12:15 - pico-train - INFO - Step 16700 -- 🔄 Training Metrics 2025-08-30 20:12:15 - pico-train - INFO - ├── Loss: 5.1796 2025-08-30 20:12:15 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 20:12:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:13:26 - pico-train - INFO - Step 16800 -- 🔄 Training Metrics 2025-08-30 20:13:26 - pico-train - INFO - ├── Loss: 5.1488 2025-08-30 20:13:26 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 20:13:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:14:37 - pico-train - INFO - Step 16900 -- 🔄 Training Metrics 2025-08-30 20:14:37 - pico-train - INFO - ├── Loss: 5.1805 2025-08-30 20:14:37 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 20:14:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:15:47 - pico-train - INFO - Step 17000 -- 💾 Saving Checkpoint 2025-08-30 20:17:49 - pico-train - INFO - Step 17000 -- 📊 Evaluation Results 2025-08-30 20:17:49 - pico-train - INFO - └── paloma: inf 2025-08-30 20:17:50 - pico-train - INFO - Step 17000 -- 🔄 Training Metrics 2025-08-30 20:17:50 - pico-train - INFO - ├── Loss: 5.1846 2025-08-30 20:17:50 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 20:17:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:17:50 - pico-train - INFO - Step 17000 -- 📈 Saving Learning Dynamics 2025-08-30 20:19:04 - pico-train - INFO - Step 17100 -- 🔄 Training Metrics 2025-08-30 20:19:04 - pico-train - INFO - ├── Loss: 5.1825 2025-08-30 20:19:04 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 20:19:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:20:16 - pico-train - INFO - Step 17200 -- 🔄 Training Metrics 2025-08-30 20:20:16 - pico-train - INFO - ├── Loss: 5.1567 2025-08-30 20:20:16 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 20:20:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:21:27 - pico-train - INFO - Step 17300 -- 🔄 Training Metrics 2025-08-30 20:21:27 - pico-train - INFO - ├── Loss: 5.2075 2025-08-30 20:21:27 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 20:21:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:22:39 - pico-train - INFO - Step 17400 -- 🔄 Training Metrics 2025-08-30 20:22:39 - pico-train - INFO - ├── Loss: 5.1649 2025-08-30 20:22:39 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 20:22:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:23:49 - pico-train - INFO - Step 17500 -- 🔄 Training Metrics 2025-08-30 20:23:49 - pico-train - INFO - ├── Loss: 5.1506 2025-08-30 20:23:49 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 20:23:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:25:01 - pico-train - INFO - Step 17600 -- 🔄 Training Metrics 2025-08-30 20:25:01 - pico-train - INFO - ├── Loss: 5.1757 2025-08-30 20:25:01 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 20:25:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:26:12 - pico-train - INFO - Step 17700 -- 🔄 Training Metrics 2025-08-30 20:26:12 - pico-train - INFO - ├── Loss: 5.1580 2025-08-30 20:26:12 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 20:26:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:27:24 - pico-train - INFO - Step 17800 -- 🔄 Training Metrics 2025-08-30 20:27:24 - pico-train - INFO - ├── Loss: 5.1308 2025-08-30 20:27:24 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 20:27:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:28:35 - pico-train - INFO - Step 17900 -- 🔄 Training Metrics 2025-08-30 20:28:35 - pico-train - INFO - ├── Loss: 5.1600 2025-08-30 20:28:35 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 20:28:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:29:45 - pico-train - INFO - Step 18000 -- 💾 Saving Checkpoint 2025-08-30 20:31:47 - pico-train - INFO - Step 18000 -- 📊 Evaluation Results 2025-08-30 20:31:47 - pico-train - INFO - └── paloma: inf 2025-08-30 20:31:48 - pico-train - INFO - Step 18000 -- 🔄 Training Metrics 2025-08-30 20:31:48 - pico-train - INFO - ├── Loss: 5.1611 2025-08-30 20:31:48 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 20:31:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:31:48 - pico-train - INFO - Step 18000 -- 📈 Saving Learning Dynamics 2025-08-30 20:33:02 - pico-train - INFO - Step 18100 -- 🔄 Training Metrics 2025-08-30 20:33:02 - pico-train - INFO - ├── Loss: 5.1555 2025-08-30 20:33:02 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 20:33:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:34:13 - pico-train - INFO - Step 18200 -- 🔄 Training Metrics 2025-08-30 20:34:13 - pico-train - INFO - ├── Loss: 5.1405 2025-08-30 20:34:13 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 20:34:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:35:25 - pico-train - INFO - Step 18300 -- 🔄 Training Metrics 2025-08-30 20:35:25 - pico-train - INFO - ├── Loss: 5.1411 2025-08-30 20:35:25 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 20:35:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:36:35 - pico-train - INFO - Step 18400 -- 🔄 Training Metrics 2025-08-30 20:36:35 - pico-train - INFO - ├── Loss: 5.1467 2025-08-30 20:36:35 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 20:36:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:37:46 - pico-train - INFO - Step 18500 -- 🔄 Training Metrics 2025-08-30 20:37:46 - pico-train - INFO - ├── Loss: 5.1310 2025-08-30 20:37:46 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 20:37:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:38:58 - pico-train - INFO - Step 18600 -- 🔄 Training Metrics 2025-08-30 20:38:58 - pico-train - INFO - ├── Loss: 5.1406 2025-08-30 20:38:58 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 20:38:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:40:09 - pico-train - INFO - Step 18700 -- 🔄 Training Metrics 2025-08-30 20:40:09 - pico-train - INFO - ├── Loss: 5.1456 2025-08-30 20:40:09 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 20:40:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:41:21 - pico-train - INFO - Step 18800 -- 🔄 Training Metrics 2025-08-30 20:41:21 - pico-train - INFO - ├── Loss: 5.1176 2025-08-30 20:41:21 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 20:41:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:42:31 - pico-train - INFO - Step 18900 -- 🔄 Training Metrics 2025-08-30 20:42:31 - pico-train - INFO - ├── Loss: 5.1282 2025-08-30 20:42:31 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 20:42:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:43:42 - pico-train - INFO - Step 19000 -- 💾 Saving Checkpoint 2025-08-30 20:45:44 - pico-train - INFO - Step 19000 -- 📊 Evaluation Results 2025-08-30 20:45:44 - pico-train - INFO - └── paloma: inf 2025-08-30 20:45:45 - pico-train - INFO - Step 19000 -- 🔄 Training Metrics 2025-08-30 20:45:45 - pico-train - INFO - ├── Loss: 5.1459 2025-08-30 20:45:45 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 20:45:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:45:45 - pico-train - INFO - Step 19000 -- 📈 Saving Learning Dynamics 2025-08-30 20:46:59 - pico-train - INFO - Step 19100 -- 🔄 Training Metrics 2025-08-30 20:46:59 - pico-train - INFO - ├── Loss: 5.1400 2025-08-30 20:46:59 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 20:46:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:48:10 - pico-train - INFO - Step 19200 -- 🔄 Training Metrics 2025-08-30 20:48:10 - pico-train - INFO - ├── Loss: 5.1267 2025-08-30 20:48:10 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 20:48:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:49:21 - pico-train - INFO - Step 19300 -- 🔄 Training Metrics 2025-08-30 20:49:21 - pico-train - INFO - ├── Loss: 5.1289 2025-08-30 20:49:21 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 20:49:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:50:32 - pico-train - INFO - Step 19400 -- 🔄 Training Metrics 2025-08-30 20:50:32 - pico-train - INFO - ├── Loss: 5.1263 2025-08-30 20:50:32 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 20:50:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:51:44 - pico-train - INFO - Step 19500 -- 🔄 Training Metrics 2025-08-30 20:51:44 - pico-train - INFO - ├── Loss: 5.1383 2025-08-30 20:51:44 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 20:51:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:52:55 - pico-train - INFO - Step 19600 -- 🔄 Training Metrics 2025-08-30 20:52:55 - pico-train - INFO - ├── Loss: 5.1403 2025-08-30 20:52:55 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 20:52:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:54:06 - pico-train - INFO - Step 19700 -- 🔄 Training Metrics 2025-08-30 20:54:06 - pico-train - INFO - ├── Loss: 5.1260 2025-08-30 20:54:06 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 20:54:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:55:17 - pico-train - INFO - Step 19800 -- 🔄 Training Metrics 2025-08-30 20:55:17 - pico-train - INFO - ├── Loss: 5.1311 2025-08-30 20:55:17 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 20:55:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:56:28 - pico-train - INFO - Step 19900 -- 🔄 Training Metrics 2025-08-30 20:56:28 - pico-train - INFO - ├── Loss: 5.1058 2025-08-30 20:56:28 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 20:56:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:57:38 - pico-train - INFO - Step 20000 -- 💾 Saving Checkpoint 2025-08-30 20:59:40 - pico-train - INFO - Step 20000 -- 📊 Evaluation Results 2025-08-30 20:59:40 - pico-train - INFO - └── paloma: inf 2025-08-30 20:59:41 - pico-train - INFO - Step 20000 -- 🔄 Training Metrics 2025-08-30 20:59:41 - pico-train - INFO - ├── Loss: 5.1196 2025-08-30 20:59:41 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 20:59:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 20:59:41 - pico-train - INFO - Step 20000 -- 📈 Saving Learning Dynamics 2025-08-30 21:00:55 - pico-train - INFO - Step 20100 -- 🔄 Training Metrics 2025-08-30 21:00:55 - pico-train - INFO - ├── Loss: 5.1019 2025-08-30 21:00:55 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 21:00:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:02:06 - pico-train - INFO - Step 20200 -- 🔄 Training Metrics 2025-08-30 21:02:06 - pico-train - INFO - ├── Loss: 5.1164 2025-08-30 21:02:06 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 21:02:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:03:17 - pico-train - INFO - Step 20300 -- 🔄 Training Metrics 2025-08-30 21:03:17 - pico-train - INFO - ├── Loss: 5.1355 2025-08-30 21:03:17 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 21:03:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:04:28 - pico-train - INFO - Step 20400 -- 🔄 Training Metrics 2025-08-30 21:04:28 - pico-train - INFO - ├── Loss: 5.1157 2025-08-30 21:04:28 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 21:04:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:05:40 - pico-train - INFO - Step 20500 -- 🔄 Training Metrics 2025-08-30 21:05:40 - pico-train - INFO - ├── Loss: 5.1164 2025-08-30 21:05:40 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 21:05:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:06:51 - pico-train - INFO - Step 20600 -- 🔄 Training Metrics 2025-08-30 21:06:51 - pico-train - INFO - ├── Loss: 5.1290 2025-08-30 21:06:51 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 21:06:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:08:02 - pico-train - INFO - Step 20700 -- 🔄 Training Metrics 2025-08-30 21:08:02 - pico-train - INFO - ├── Loss: 5.1013 2025-08-30 21:08:02 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 21:08:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:09:13 - pico-train - INFO - Step 20800 -- 🔄 Training Metrics 2025-08-30 21:09:13 - pico-train - INFO - ├── Loss: 5.1103 2025-08-30 21:09:13 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 21:09:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:10:24 - pico-train - INFO - Step 20900 -- 🔄 Training Metrics 2025-08-30 21:10:24 - pico-train - INFO - ├── Loss: 5.1041 2025-08-30 21:10:24 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 21:10:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:11:34 - pico-train - INFO - Step 21000 -- 💾 Saving Checkpoint 2025-08-30 21:13:36 - pico-train - INFO - Step 21000 -- 📊 Evaluation Results 2025-08-30 21:13:36 - pico-train - INFO - └── paloma: inf 2025-08-30 21:13:37 - pico-train - INFO - Step 21000 -- 🔄 Training Metrics 2025-08-30 21:13:37 - pico-train - INFO - ├── Loss: 5.1056 2025-08-30 21:13:37 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 21:13:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:13:37 - pico-train - INFO - Step 21000 -- 📈 Saving Learning Dynamics 2025-08-30 21:14:50 - pico-train - INFO - Step 21100 -- 🔄 Training Metrics 2025-08-30 21:14:50 - pico-train - INFO - ├── Loss: 5.0963 2025-08-30 21:14:50 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 21:14:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:16:01 - pico-train - INFO - Step 21200 -- 🔄 Training Metrics 2025-08-30 21:16:01 - pico-train - INFO - ├── Loss: 5.1159 2025-08-30 21:16:01 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 21:16:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:17:12 - pico-train - INFO - Step 21300 -- 🔄 Training Metrics 2025-08-30 21:17:12 - pico-train - INFO - ├── Loss: 5.1047 2025-08-30 21:17:12 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 21:17:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:18:23 - pico-train - INFO - Step 21400 -- 🔄 Training Metrics 2025-08-30 21:18:23 - pico-train - INFO - ├── Loss: 5.0805 2025-08-30 21:18:23 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 21:18:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:19:35 - pico-train - INFO - Step 21500 -- 🔄 Training Metrics 2025-08-30 21:19:35 - pico-train - INFO - ├── Loss: 5.1073 2025-08-30 21:19:35 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 21:19:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:20:45 - pico-train - INFO - Step 21600 -- 🔄 Training Metrics 2025-08-30 21:20:45 - pico-train - INFO - ├── Loss: 5.0786 2025-08-30 21:20:45 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 21:20:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:21:56 - pico-train - INFO - Step 21700 -- 🔄 Training Metrics 2025-08-30 21:21:56 - pico-train - INFO - ├── Loss: 5.0965 2025-08-30 21:21:56 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 21:21:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:23:09 - pico-train - INFO - Step 21800 -- 🔄 Training Metrics 2025-08-30 21:23:09 - pico-train - INFO - ├── Loss: 5.1086 2025-08-30 21:23:09 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 21:23:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:24:20 - pico-train - INFO - Step 21900 -- 🔄 Training Metrics 2025-08-30 21:24:20 - pico-train - INFO - ├── Loss: 5.1030 2025-08-30 21:24:20 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 21:24:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:25:30 - pico-train - INFO - Step 22000 -- 💾 Saving Checkpoint 2025-08-30 21:27:31 - pico-train - INFO - Step 22000 -- 📊 Evaluation Results 2025-08-30 21:27:31 - pico-train - INFO - └── paloma: inf 2025-08-30 21:27:32 - pico-train - INFO - Step 22000 -- 🔄 Training Metrics 2025-08-30 21:27:32 - pico-train - INFO - ├── Loss: 5.0792 2025-08-30 21:27:32 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 21:27:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:27:32 - pico-train - INFO - Step 22000 -- 📈 Saving Learning Dynamics 2025-08-30 21:28:46 - pico-train - INFO - Step 22100 -- 🔄 Training Metrics 2025-08-30 21:28:46 - pico-train - INFO - ├── Loss: 5.0833 2025-08-30 21:28:46 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 21:28:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:29:57 - pico-train - INFO - Step 22200 -- 🔄 Training Metrics 2025-08-30 21:29:57 - pico-train - INFO - ├── Loss: 5.0819 2025-08-30 21:29:57 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 21:29:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:31:08 - pico-train - INFO - Step 22300 -- 🔄 Training Metrics 2025-08-30 21:31:08 - pico-train - INFO - ├── Loss: 5.0940 2025-08-30 21:31:08 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 21:31:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:32:20 - pico-train - INFO - Step 22400 -- 🔄 Training Metrics 2025-08-30 21:32:20 - pico-train - INFO - ├── Loss: 5.0780 2025-08-30 21:32:20 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 21:32:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:33:30 - pico-train - INFO - Step 22500 -- 🔄 Training Metrics 2025-08-30 21:33:30 - pico-train - INFO - ├── Loss: 5.0809 2025-08-30 21:33:30 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 21:33:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:34:42 - pico-train - INFO - Step 22600 -- 🔄 Training Metrics 2025-08-30 21:34:42 - pico-train - INFO - ├── Loss: 5.0869 2025-08-30 21:34:42 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 21:34:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:35:53 - pico-train - INFO - Step 22700 -- 🔄 Training Metrics 2025-08-30 21:35:53 - pico-train - INFO - ├── Loss: 5.0751 2025-08-30 21:35:53 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 21:35:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:37:04 - pico-train - INFO - Step 22800 -- 🔄 Training Metrics 2025-08-30 21:37:04 - pico-train - INFO - ├── Loss: 5.0663 2025-08-30 21:37:04 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 21:37:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:38:15 - pico-train - INFO - Step 22900 -- 🔄 Training Metrics 2025-08-30 21:38:15 - pico-train - INFO - ├── Loss: 5.0716 2025-08-30 21:38:15 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 21:38:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:39:25 - pico-train - INFO - Step 23000 -- 💾 Saving Checkpoint 2025-08-30 21:41:27 - pico-train - INFO - Step 23000 -- 📊 Evaluation Results 2025-08-30 21:41:27 - pico-train - INFO - └── paloma: inf 2025-08-30 21:41:27 - pico-train - INFO - Step 23000 -- 🔄 Training Metrics 2025-08-30 21:41:27 - pico-train - INFO - ├── Loss: 5.0719 2025-08-30 21:41:27 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 21:41:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:41:27 - pico-train - INFO - Step 23000 -- 📈 Saving Learning Dynamics 2025-08-30 21:42:42 - pico-train - INFO - Step 23100 -- 🔄 Training Metrics 2025-08-30 21:42:42 - pico-train - INFO - ├── Loss: 5.0658 2025-08-30 21:42:42 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 21:42:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:43:53 - pico-train - INFO - Step 23200 -- 🔄 Training Metrics 2025-08-30 21:43:53 - pico-train - INFO - ├── Loss: 5.0631 2025-08-30 21:43:53 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 21:43:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:45:05 - pico-train - INFO - Step 23300 -- 🔄 Training Metrics 2025-08-30 21:45:05 - pico-train - INFO - ├── Loss: 5.0873 2025-08-30 21:45:05 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 21:45:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:46:16 - pico-train - INFO - Step 23400 -- 🔄 Training Metrics 2025-08-30 21:46:16 - pico-train - INFO - ├── Loss: 5.0612 2025-08-30 21:46:16 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 21:46:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:47:27 - pico-train - INFO - Step 23500 -- 🔄 Training Metrics 2025-08-30 21:47:27 - pico-train - INFO - ├── Loss: 5.0464 2025-08-30 21:47:27 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 21:47:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:48:38 - pico-train - INFO - Step 23600 -- 🔄 Training Metrics 2025-08-30 21:48:38 - pico-train - INFO - ├── Loss: 5.0612 2025-08-30 21:48:38 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 21:48:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:49:50 - pico-train - INFO - Step 23700 -- 🔄 Training Metrics 2025-08-30 21:49:50 - pico-train - INFO - ├── Loss: 5.0501 2025-08-30 21:49:50 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 21:49:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:51:01 - pico-train - INFO - Step 23800 -- 🔄 Training Metrics 2025-08-30 21:51:01 - pico-train - INFO - ├── Loss: 5.0517 2025-08-30 21:51:01 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 21:51:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:52:12 - pico-train - INFO - Step 23900 -- 🔄 Training Metrics 2025-08-30 21:52:12 - pico-train - INFO - ├── Loss: 5.0439 2025-08-30 21:52:12 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 21:52:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:53:22 - pico-train - INFO - Step 24000 -- 💾 Saving Checkpoint 2025-08-30 21:55:24 - pico-train - INFO - Step 24000 -- 📊 Evaluation Results 2025-08-30 21:55:24 - pico-train - INFO - └── paloma: inf 2025-08-30 21:55:25 - pico-train - INFO - Step 24000 -- 🔄 Training Metrics 2025-08-30 21:55:25 - pico-train - INFO - ├── Loss: 5.0522 2025-08-30 21:55:25 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 21:55:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:55:25 - pico-train - INFO - Step 24000 -- 📈 Saving Learning Dynamics 2025-08-30 21:56:39 - pico-train - INFO - Step 24100 -- 🔄 Training Metrics 2025-08-30 21:56:39 - pico-train - INFO - ├── Loss: 5.0476 2025-08-30 21:56:39 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 21:56:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:57:50 - pico-train - INFO - Step 24200 -- 🔄 Training Metrics 2025-08-30 21:57:50 - pico-train - INFO - ├── Loss: 5.0433 2025-08-30 21:57:50 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 21:57:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 21:59:01 - pico-train - INFO - Step 24300 -- 🔄 Training Metrics 2025-08-30 21:59:01 - pico-train - INFO - ├── Loss: 5.0522 2025-08-30 21:59:01 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 21:59:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:00:12 - pico-train - INFO - Step 24400 -- 🔄 Training Metrics 2025-08-30 22:00:12 - pico-train - INFO - ├── Loss: 5.0452 2025-08-30 22:00:12 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 22:00:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:01:24 - pico-train - INFO - Step 24500 -- 🔄 Training Metrics 2025-08-30 22:01:24 - pico-train - INFO - ├── Loss: 5.0628 2025-08-30 22:01:24 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 22:01:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:02:35 - pico-train - INFO - Step 24600 -- 🔄 Training Metrics 2025-08-30 22:02:35 - pico-train - INFO - ├── Loss: 5.0439 2025-08-30 22:02:35 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 22:02:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:03:46 - pico-train - INFO - Step 24700 -- 🔄 Training Metrics 2025-08-30 22:03:46 - pico-train - INFO - ├── Loss: 5.0321 2025-08-30 22:03:46 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 22:03:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:04:57 - pico-train - INFO - Step 24800 -- 🔄 Training Metrics 2025-08-30 22:04:57 - pico-train - INFO - ├── Loss: 5.0503 2025-08-30 22:04:57 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 22:04:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:06:08 - pico-train - INFO - Step 24900 -- 🔄 Training Metrics 2025-08-30 22:06:08 - pico-train - INFO - ├── Loss: 5.0360 2025-08-30 22:06:08 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 22:06:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:07:18 - pico-train - INFO - Step 25000 -- 💾 Saving Checkpoint 2025-08-30 22:09:20 - pico-train - INFO - Step 25000 -- 📊 Evaluation Results 2025-08-30 22:09:20 - pico-train - INFO - └── paloma: inf 2025-08-30 22:09:21 - pico-train - INFO - Step 25000 -- 🔄 Training Metrics 2025-08-30 22:09:21 - pico-train - INFO - ├── Loss: 5.0212 2025-08-30 22:09:21 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 22:09:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:09:21 - pico-train - INFO - Step 25000 -- 📈 Saving Learning Dynamics 2025-08-30 22:10:35 - pico-train - INFO - Step 25100 -- 🔄 Training Metrics 2025-08-30 22:10:35 - pico-train - INFO - ├── Loss: 5.0438 2025-08-30 22:10:35 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 22:10:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:11:46 - pico-train - INFO - Step 25200 -- 🔄 Training Metrics 2025-08-30 22:11:46 - pico-train - INFO - ├── Loss: 5.0433 2025-08-30 22:11:46 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 22:11:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:12:56 - pico-train - INFO - Step 25300 -- 🔄 Training Metrics 2025-08-30 22:12:56 - pico-train - INFO - ├── Loss: 5.0521 2025-08-30 22:12:56 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 22:12:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:14:08 - pico-train - INFO - Step 25400 -- 🔄 Training Metrics 2025-08-30 22:14:08 - pico-train - INFO - ├── Loss: 5.0397 2025-08-30 22:14:08 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 22:14:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:15:19 - pico-train - INFO - Step 25500 -- 🔄 Training Metrics 2025-08-30 22:15:19 - pico-train - INFO - ├── Loss: 5.0390 2025-08-30 22:15:19 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 22:15:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:16:31 - pico-train - INFO - Step 25600 -- 🔄 Training Metrics 2025-08-30 22:16:31 - pico-train - INFO - ├── Loss: 5.0488 2025-08-30 22:16:31 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 22:16:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:17:42 - pico-train - INFO - Step 25700 -- 🔄 Training Metrics 2025-08-30 22:17:42 - pico-train - INFO - ├── Loss: 5.0378 2025-08-30 22:17:42 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 22:17:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:18:53 - pico-train - INFO - Step 25800 -- 🔄 Training Metrics 2025-08-30 22:18:53 - pico-train - INFO - ├── Loss: 5.0415 2025-08-30 22:18:53 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 22:18:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:20:04 - pico-train - INFO - Step 25900 -- 🔄 Training Metrics 2025-08-30 22:20:04 - pico-train - INFO - ├── Loss: 5.0105 2025-08-30 22:20:04 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 22:20:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:21:15 - pico-train - INFO - Step 26000 -- 💾 Saving Checkpoint 2025-08-30 22:23:16 - pico-train - INFO - Step 26000 -- 📊 Evaluation Results 2025-08-30 22:23:16 - pico-train - INFO - └── paloma: inf 2025-08-30 22:23:17 - pico-train - INFO - Step 26000 -- 🔄 Training Metrics 2025-08-30 22:23:17 - pico-train - INFO - ├── Loss: 5.0128 2025-08-30 22:23:17 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 22:23:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:23:17 - pico-train - INFO - Step 26000 -- 📈 Saving Learning Dynamics 2025-08-30 22:24:31 - pico-train - INFO - Step 26100 -- 🔄 Training Metrics 2025-08-30 22:24:31 - pico-train - INFO - ├── Loss: 5.0559 2025-08-30 22:24:31 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 22:24:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:25:42 - pico-train - INFO - Step 26200 -- 🔄 Training Metrics 2025-08-30 22:25:42 - pico-train - INFO - ├── Loss: 5.0232 2025-08-30 22:25:42 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 22:25:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:26:53 - pico-train - INFO - Step 26300 -- 🔄 Training Metrics 2025-08-30 22:26:53 - pico-train - INFO - ├── Loss: 5.0204 2025-08-30 22:26:53 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 22:26:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:28:04 - pico-train - INFO - Step 26400 -- 🔄 Training Metrics 2025-08-30 22:28:04 - pico-train - INFO - ├── Loss: 5.0435 2025-08-30 22:28:04 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 22:28:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:29:15 - pico-train - INFO - Step 26500 -- 🔄 Training Metrics 2025-08-30 22:29:15 - pico-train - INFO - ├── Loss: 5.0079 2025-08-30 22:29:15 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 22:29:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:30:26 - pico-train - INFO - Step 26600 -- 🔄 Training Metrics 2025-08-30 22:30:26 - pico-train - INFO - ├── Loss: 5.0246 2025-08-30 22:30:26 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 22:30:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:31:37 - pico-train - INFO - Step 26700 -- 🔄 Training Metrics 2025-08-30 22:31:37 - pico-train - INFO - ├── Loss: 5.0400 2025-08-30 22:31:37 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 22:31:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:32:49 - pico-train - INFO - Step 26800 -- 🔄 Training Metrics 2025-08-30 22:32:49 - pico-train - INFO - ├── Loss: 5.0357 2025-08-30 22:32:49 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 22:32:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:34:01 - pico-train - INFO - Step 26900 -- 🔄 Training Metrics 2025-08-30 22:34:01 - pico-train - INFO - ├── Loss: 4.9973 2025-08-30 22:34:01 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 22:34:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:35:11 - pico-train - INFO - Step 27000 -- 💾 Saving Checkpoint 2025-08-30 22:37:12 - pico-train - INFO - Step 27000 -- 📊 Evaluation Results 2025-08-30 22:37:12 - pico-train - INFO - └── paloma: inf 2025-08-30 22:37:13 - pico-train - INFO - Step 27000 -- 🔄 Training Metrics 2025-08-30 22:37:13 - pico-train - INFO - ├── Loss: 5.0186 2025-08-30 22:37:13 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 22:37:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:37:13 - pico-train - INFO - Step 27000 -- 📈 Saving Learning Dynamics 2025-08-30 22:38:27 - pico-train - INFO - Step 27100 -- 🔄 Training Metrics 2025-08-30 22:38:27 - pico-train - INFO - ├── Loss: 5.0100 2025-08-30 22:38:27 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 22:38:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:39:38 - pico-train - INFO - Step 27200 -- 🔄 Training Metrics 2025-08-30 22:39:38 - pico-train - INFO - ├── Loss: 5.0227 2025-08-30 22:39:38 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 22:39:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:40:49 - pico-train - INFO - Step 27300 -- 🔄 Training Metrics 2025-08-30 22:40:49 - pico-train - INFO - ├── Loss: 5.0293 2025-08-30 22:40:49 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 22:40:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:42:00 - pico-train - INFO - Step 27400 -- 🔄 Training Metrics 2025-08-30 22:42:00 - pico-train - INFO - ├── Loss: 5.0011 2025-08-30 22:42:00 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 22:42:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:43:11 - pico-train - INFO - Step 27500 -- 🔄 Training Metrics 2025-08-30 22:43:11 - pico-train - INFO - ├── Loss: 5.0173 2025-08-30 22:43:11 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 22:43:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:44:22 - pico-train - INFO - Step 27600 -- 🔄 Training Metrics 2025-08-30 22:44:22 - pico-train - INFO - ├── Loss: 4.9923 2025-08-30 22:44:22 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 22:44:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:45:34 - pico-train - INFO - Step 27700 -- 🔄 Training Metrics 2025-08-30 22:45:34 - pico-train - INFO - ├── Loss: 5.0067 2025-08-30 22:45:34 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 22:45:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:46:45 - pico-train - INFO - Step 27800 -- 🔄 Training Metrics 2025-08-30 22:46:45 - pico-train - INFO - ├── Loss: 5.0232 2025-08-30 22:46:45 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 22:46:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:47:56 - pico-train - INFO - Step 27900 -- 🔄 Training Metrics 2025-08-30 22:47:56 - pico-train - INFO - ├── Loss: 5.0189 2025-08-30 22:47:56 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 22:47:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:49:06 - pico-train - INFO - Step 28000 -- 💾 Saving Checkpoint 2025-08-30 22:51:07 - pico-train - INFO - Step 28000 -- 📊 Evaluation Results 2025-08-30 22:51:07 - pico-train - INFO - └── paloma: inf 2025-08-30 22:51:08 - pico-train - INFO - Step 28000 -- 🔄 Training Metrics 2025-08-30 22:51:08 - pico-train - INFO - ├── Loss: 5.0086 2025-08-30 22:51:08 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 22:51:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:51:08 - pico-train - INFO - Step 28000 -- 📈 Saving Learning Dynamics 2025-08-30 22:52:22 - pico-train - INFO - Step 28100 -- 🔄 Training Metrics 2025-08-30 22:52:22 - pico-train - INFO - ├── Loss: 4.9984 2025-08-30 22:52:22 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 22:52:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:53:34 - pico-train - INFO - Step 28200 -- 🔄 Training Metrics 2025-08-30 22:53:34 - pico-train - INFO - ├── Loss: 5.0119 2025-08-30 22:53:34 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 22:53:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:54:45 - pico-train - INFO - Step 28300 -- 🔄 Training Metrics 2025-08-30 22:54:45 - pico-train - INFO - ├── Loss: 4.9886 2025-08-30 22:54:45 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 22:54:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:55:56 - pico-train - INFO - Step 28400 -- 🔄 Training Metrics 2025-08-30 22:55:56 - pico-train - INFO - ├── Loss: 5.0118 2025-08-30 22:55:56 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 22:55:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:57:07 - pico-train - INFO - Step 28500 -- 🔄 Training Metrics 2025-08-30 22:57:07 - pico-train - INFO - ├── Loss: 5.0120 2025-08-30 22:57:07 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 22:57:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:58:18 - pico-train - INFO - Step 28600 -- 🔄 Training Metrics 2025-08-30 22:58:18 - pico-train - INFO - ├── Loss: 5.0077 2025-08-30 22:58:18 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 22:58:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 22:59:30 - pico-train - INFO - Step 28700 -- 🔄 Training Metrics 2025-08-30 22:59:30 - pico-train - INFO - ├── Loss: 5.0100 2025-08-30 22:59:30 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 22:59:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:00:41 - pico-train - INFO - Step 28800 -- 🔄 Training Metrics 2025-08-30 23:00:41 - pico-train - INFO - ├── Loss: 5.0086 2025-08-30 23:00:41 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 23:00:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:01:52 - pico-train - INFO - Step 28900 -- 🔄 Training Metrics 2025-08-30 23:01:52 - pico-train - INFO - ├── Loss: 4.9909 2025-08-30 23:01:52 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 23:01:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:03:02 - pico-train - INFO - Step 29000 -- 💾 Saving Checkpoint 2025-08-30 23:05:04 - pico-train - INFO - Step 29000 -- 📊 Evaluation Results 2025-08-30 23:05:04 - pico-train - INFO - └── paloma: inf 2025-08-30 23:05:05 - pico-train - INFO - Step 29000 -- 🔄 Training Metrics 2025-08-30 23:05:05 - pico-train - INFO - ├── Loss: 4.9947 2025-08-30 23:05:05 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 23:05:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:05:05 - pico-train - INFO - Step 29000 -- 📈 Saving Learning Dynamics 2025-08-30 23:06:20 - pico-train - INFO - Step 29100 -- 🔄 Training Metrics 2025-08-30 23:06:20 - pico-train - INFO - ├── Loss: 5.0001 2025-08-30 23:06:20 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 23:06:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:07:31 - pico-train - INFO - Step 29200 -- 🔄 Training Metrics 2025-08-30 23:07:31 - pico-train - INFO - ├── Loss: 4.9992 2025-08-30 23:07:31 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 23:07:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:08:43 - pico-train - INFO - Step 29300 -- 🔄 Training Metrics 2025-08-30 23:08:43 - pico-train - INFO - ├── Loss: 4.9885 2025-08-30 23:08:43 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 23:08:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:09:53 - pico-train - INFO - Step 29400 -- 🔄 Training Metrics 2025-08-30 23:09:53 - pico-train - INFO - ├── Loss: 5.0013 2025-08-30 23:09:53 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 23:09:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:11:06 - pico-train - INFO - Step 29500 -- 🔄 Training Metrics 2025-08-30 23:11:06 - pico-train - INFO - ├── Loss: 4.9933 2025-08-30 23:11:06 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 23:11:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:12:17 - pico-train - INFO - Step 29600 -- 🔄 Training Metrics 2025-08-30 23:12:17 - pico-train - INFO - ├── Loss: 5.0078 2025-08-30 23:12:17 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 23:12:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:13:28 - pico-train - INFO - Step 29700 -- 🔄 Training Metrics 2025-08-30 23:13:28 - pico-train - INFO - ├── Loss: 4.9921 2025-08-30 23:13:28 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 23:13:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:14:39 - pico-train - INFO - Step 29800 -- 🔄 Training Metrics 2025-08-30 23:14:39 - pico-train - INFO - ├── Loss: 5.0129 2025-08-30 23:14:39 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 23:14:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:15:50 - pico-train - INFO - Step 29900 -- 🔄 Training Metrics 2025-08-30 23:15:50 - pico-train - INFO - ├── Loss: 4.9857 2025-08-30 23:15:50 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 23:15:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:17:01 - pico-train - INFO - Step 30000 -- 💾 Saving Checkpoint 2025-08-30 23:19:03 - pico-train - INFO - Step 30000 -- 📊 Evaluation Results 2025-08-30 23:19:03 - pico-train - INFO - └── paloma: inf 2025-08-30 23:19:03 - pico-train - INFO - Step 30000 -- 🔄 Training Metrics 2025-08-30 23:19:03 - pico-train - INFO - ├── Loss: 4.9900 2025-08-30 23:19:03 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 23:19:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:19:03 - pico-train - INFO - Step 30000 -- 📈 Saving Learning Dynamics 2025-08-30 23:20:21 - pico-train - INFO - Step 30100 -- 🔄 Training Metrics 2025-08-30 23:20:21 - pico-train - INFO - ├── Loss: 4.9847 2025-08-30 23:20:21 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 23:20:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:21:32 - pico-train - INFO - Step 30200 -- 🔄 Training Metrics 2025-08-30 23:21:32 - pico-train - INFO - ├── Loss: 4.9702 2025-08-30 23:21:32 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 23:21:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:22:43 - pico-train - INFO - Step 30300 -- 🔄 Training Metrics 2025-08-30 23:22:43 - pico-train - INFO - ├── Loss: 4.9776 2025-08-30 23:22:43 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 23:22:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:23:54 - pico-train - INFO - Step 30400 -- 🔄 Training Metrics 2025-08-30 23:23:54 - pico-train - INFO - ├── Loss: 4.9789 2025-08-30 23:23:54 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 23:23:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:25:05 - pico-train - INFO - Step 30500 -- 🔄 Training Metrics 2025-08-30 23:25:05 - pico-train - INFO - ├── Loss: 4.9794 2025-08-30 23:25:05 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 23:25:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:26:17 - pico-train - INFO - Step 30600 -- 🔄 Training Metrics 2025-08-30 23:26:17 - pico-train - INFO - ├── Loss: 4.9955 2025-08-30 23:26:17 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 23:26:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:27:28 - pico-train - INFO - Step 30700 -- 🔄 Training Metrics 2025-08-30 23:27:28 - pico-train - INFO - ├── Loss: 4.9794 2025-08-30 23:27:28 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 23:27:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:28:39 - pico-train - INFO - Step 30800 -- 🔄 Training Metrics 2025-08-30 23:28:39 - pico-train - INFO - ├── Loss: 4.9636 2025-08-30 23:28:39 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 23:28:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:29:51 - pico-train - INFO - Step 30900 -- 🔄 Training Metrics 2025-08-30 23:29:51 - pico-train - INFO - ├── Loss: 4.9775 2025-08-30 23:29:51 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 23:29:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:31:01 - pico-train - INFO - Step 31000 -- 💾 Saving Checkpoint 2025-08-30 23:33:03 - pico-train - INFO - Step 31000 -- 📊 Evaluation Results 2025-08-30 23:33:03 - pico-train - INFO - └── paloma: inf 2025-08-30 23:33:04 - pico-train - INFO - Step 31000 -- 🔄 Training Metrics 2025-08-30 23:33:04 - pico-train - INFO - ├── Loss: 4.9882 2025-08-30 23:33:04 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 23:33:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:33:04 - pico-train - INFO - Step 31000 -- 📈 Saving Learning Dynamics 2025-08-30 23:34:18 - pico-train - INFO - Step 31100 -- 🔄 Training Metrics 2025-08-30 23:34:18 - pico-train - INFO - ├── Loss: 4.9492 2025-08-30 23:34:18 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 23:34:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:35:29 - pico-train - INFO - Step 31200 -- 🔄 Training Metrics 2025-08-30 23:35:29 - pico-train - INFO - ├── Loss: 4.9782 2025-08-30 23:35:29 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 23:35:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:36:40 - pico-train - INFO - Step 31300 -- 🔄 Training Metrics 2025-08-30 23:36:40 - pico-train - INFO - ├── Loss: 4.9733 2025-08-30 23:36:40 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 23:36:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:37:51 - pico-train - INFO - Step 31400 -- 🔄 Training Metrics 2025-08-30 23:37:51 - pico-train - INFO - ├── Loss: 4.9639 2025-08-30 23:37:51 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 23:37:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:39:03 - pico-train - INFO - Step 31500 -- 🔄 Training Metrics 2025-08-30 23:39:03 - pico-train - INFO - ├── Loss: 4.9706 2025-08-30 23:39:03 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 23:39:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:40:14 - pico-train - INFO - Step 31600 -- 🔄 Training Metrics 2025-08-30 23:40:14 - pico-train - INFO - ├── Loss: 4.9917 2025-08-30 23:40:14 - pico-train - INFO - ├── Learning Rate: 1.58e-04 2025-08-30 23:40:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:41:25 - pico-train - INFO - Step 31700 -- 🔄 Training Metrics 2025-08-30 23:41:25 - pico-train - INFO - ├── Loss: 4.9708 2025-08-30 23:41:25 - pico-train - INFO - ├── Learning Rate: 1.58e-04 2025-08-30 23:41:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:42:36 - pico-train - INFO - Step 31800 -- 🔄 Training Metrics 2025-08-30 23:42:36 - pico-train - INFO - ├── Loss: 4.9446 2025-08-30 23:42:36 - pico-train - INFO - ├── Learning Rate: 1.58e-04 2025-08-30 23:42:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:43:48 - pico-train - INFO - Step 31900 -- 🔄 Training Metrics 2025-08-30 23:43:48 - pico-train - INFO - ├── Loss: 4.9893 2025-08-30 23:43:48 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 23:43:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:44:58 - pico-train - INFO - Step 32000 -- 💾 Saving Checkpoint 2025-08-30 23:47:00 - pico-train - INFO - Step 32000 -- 📊 Evaluation Results 2025-08-30 23:47:00 - pico-train - INFO - └── paloma: inf 2025-08-30 23:47:01 - pico-train - INFO - Step 32000 -- 🔄 Training Metrics 2025-08-30 23:47:01 - pico-train - INFO - ├── Loss: 4.9584 2025-08-30 23:47:01 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 23:47:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:47:01 - pico-train - INFO - Step 32000 -- 📈 Saving Learning Dynamics 2025-08-30 23:48:14 - pico-train - INFO - Step 32100 -- 🔄 Training Metrics 2025-08-30 23:48:14 - pico-train - INFO - ├── Loss: 4.9840 2025-08-30 23:48:14 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 23:48:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:49:26 - pico-train - INFO - Step 32200 -- 🔄 Training Metrics 2025-08-30 23:49:26 - pico-train - INFO - ├── Loss: 4.9499 2025-08-30 23:49:26 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 23:49:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:50:37 - pico-train - INFO - Step 32300 -- 🔄 Training Metrics 2025-08-30 23:50:37 - pico-train - INFO - ├── Loss: 4.9514 2025-08-30 23:50:37 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 23:50:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:51:48 - pico-train - INFO - Step 32400 -- 🔄 Training Metrics 2025-08-30 23:51:48 - pico-train - INFO - ├── Loss: 4.9563 2025-08-30 23:51:48 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 23:51:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:52:59 - pico-train - INFO - Step 32500 -- 🔄 Training Metrics 2025-08-30 23:52:59 - pico-train - INFO - ├── Loss: 4.9438 2025-08-30 23:52:59 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 23:52:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:54:10 - pico-train - INFO - Step 32600 -- 🔄 Training Metrics 2025-08-30 23:54:10 - pico-train - INFO - ├── Loss: 4.9769 2025-08-30 23:54:10 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 23:54:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:55:21 - pico-train - INFO - Step 32700 -- 🔄 Training Metrics 2025-08-30 23:55:21 - pico-train - INFO - ├── Loss: 4.9642 2025-08-30 23:55:21 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-30 23:55:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:56:32 - pico-train - INFO - Step 32800 -- 🔄 Training Metrics 2025-08-30 23:56:32 - pico-train - INFO - ├── Loss: 4.9569 2025-08-30 23:56:32 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-30 23:56:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:57:43 - pico-train - INFO - Step 32900 -- 🔄 Training Metrics 2025-08-30 23:57:43 - pico-train - INFO - ├── Loss: 4.9885 2025-08-30 23:57:43 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-30 23:57:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 23:58:53 - pico-train - INFO - Step 33000 -- 💾 Saving Checkpoint 2025-08-31 00:00:54 - pico-train - INFO - Step 33000 -- 📊 Evaluation Results 2025-08-31 00:00:54 - pico-train - INFO - └── paloma: inf 2025-08-31 00:00:55 - pico-train - INFO - Step 33000 -- 🔄 Training Metrics 2025-08-31 00:00:55 - pico-train - INFO - ├── Loss: 4.9527 2025-08-31 00:00:55 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-31 00:00:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:00:55 - pico-train - INFO - Step 33000 -- 📈 Saving Learning Dynamics 2025-08-31 00:02:09 - pico-train - INFO - Step 33100 -- 🔄 Training Metrics 2025-08-31 00:02:09 - pico-train - INFO - ├── Loss: 4.9572 2025-08-31 00:02:09 - pico-train - INFO - ├── Learning Rate: 1.54e-04 2025-08-31 00:02:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:03:20 - pico-train - INFO - Step 33200 -- 🔄 Training Metrics 2025-08-31 00:03:20 - pico-train - INFO - ├── Loss: 4.9849 2025-08-31 00:03:20 - pico-train - INFO - ├── Learning Rate: 1.54e-04 2025-08-31 00:03:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:04:32 - pico-train - INFO - Step 33300 -- 🔄 Training Metrics 2025-08-31 00:04:32 - pico-train - INFO - ├── Loss: 4.9590 2025-08-31 00:04:32 - pico-train - INFO - ├── Learning Rate: 1.54e-04 2025-08-31 00:04:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:05:42 - pico-train - INFO - Step 33400 -- 🔄 Training Metrics 2025-08-31 00:05:42 - pico-train - INFO - ├── Loss: 4.9521 2025-08-31 00:05:42 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-31 00:05:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:06:54 - pico-train - INFO - Step 33500 -- 🔄 Training Metrics 2025-08-31 00:06:54 - pico-train - INFO - ├── Loss: 4.9655 2025-08-31 00:06:54 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-31 00:06:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:08:05 - pico-train - INFO - Step 33600 -- 🔄 Training Metrics 2025-08-31 00:08:05 - pico-train - INFO - ├── Loss: 4.9481 2025-08-31 00:08:05 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-31 00:08:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:09:16 - pico-train - INFO - Step 33700 -- 🔄 Training Metrics 2025-08-31 00:09:16 - pico-train - INFO - ├── Loss: 4.9613 2025-08-31 00:09:16 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-31 00:09:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:10:29 - pico-train - INFO - Step 33800 -- 🔄 Training Metrics 2025-08-31 00:10:29 - pico-train - INFO - ├── Loss: 4.9348 2025-08-31 00:10:29 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-31 00:10:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:11:39 - pico-train - INFO - Step 33900 -- 🔄 Training Metrics 2025-08-31 00:11:39 - pico-train - INFO - ├── Loss: 4.9517 2025-08-31 00:11:39 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-31 00:11:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:12:50 - pico-train - INFO - Step 34000 -- 💾 Saving Checkpoint 2025-08-31 00:14:51 - pico-train - INFO - Step 34000 -- 📊 Evaluation Results 2025-08-31 00:14:51 - pico-train - INFO - └── paloma: inf 2025-08-31 00:14:52 - pico-train - INFO - Step 34000 -- 🔄 Training Metrics 2025-08-31 00:14:52 - pico-train - INFO - ├── Loss: 4.9518 2025-08-31 00:14:52 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-31 00:14:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:14:52 - pico-train - INFO - Step 34000 -- 📈 Saving Learning Dynamics 2025-08-31 00:16:06 - pico-train - INFO - Step 34100 -- 🔄 Training Metrics 2025-08-31 00:16:06 - pico-train - INFO - ├── Loss: 4.9583 2025-08-31 00:16:06 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-31 00:16:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:17:17 - pico-train - INFO - Step 34200 -- 🔄 Training Metrics 2025-08-31 00:17:17 - pico-train - INFO - ├── Loss: 4.9762 2025-08-31 00:17:17 - pico-train - INFO - ├── Learning Rate: 1.51e-04 2025-08-31 00:17:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:18:29 - pico-train - INFO - Step 34300 -- 🔄 Training Metrics 2025-08-31 00:18:29 - pico-train - INFO - ├── Loss: 4.9672 2025-08-31 00:18:29 - pico-train - INFO - ├── Learning Rate: 1.51e-04 2025-08-31 00:18:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:19:40 - pico-train - INFO - Step 34400 -- 🔄 Training Metrics 2025-08-31 00:19:40 - pico-train - INFO - ├── Loss: 4.9656 2025-08-31 00:19:40 - pico-train - INFO - ├── Learning Rate: 1.51e-04 2025-08-31 00:19:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:20:51 - pico-train - INFO - Step 34500 -- 🔄 Training Metrics 2025-08-31 00:20:51 - pico-train - INFO - ├── Loss: 4.9669 2025-08-31 00:20:51 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-31 00:20:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:22:03 - pico-train - INFO - Step 34600 -- 🔄 Training Metrics 2025-08-31 00:22:03 - pico-train - INFO - ├── Loss: 4.9462 2025-08-31 00:22:03 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-31 00:22:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:23:14 - pico-train - INFO - Step 34700 -- 🔄 Training Metrics 2025-08-31 00:23:14 - pico-train - INFO - ├── Loss: 4.9413 2025-08-31 00:23:14 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-31 00:23:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:24:25 - pico-train - INFO - Step 34800 -- 🔄 Training Metrics 2025-08-31 00:24:25 - pico-train - INFO - ├── Loss: 4.9357 2025-08-31 00:24:25 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-31 00:24:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:25:36 - pico-train - INFO - Step 34900 -- 🔄 Training Metrics 2025-08-31 00:25:36 - pico-train - INFO - ├── Loss: 4.9346 2025-08-31 00:25:36 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-31 00:25:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:26:47 - pico-train - INFO - Step 35000 -- 💾 Saving Checkpoint 2025-08-31 00:28:48 - pico-train - INFO - Step 35000 -- 📊 Evaluation Results 2025-08-31 00:28:48 - pico-train - INFO - └── paloma: inf 2025-08-31 00:28:49 - pico-train - INFO - Step 35000 -- 🔄 Training Metrics 2025-08-31 00:28:49 - pico-train - INFO - ├── Loss: 4.9402 2025-08-31 00:28:49 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-31 00:28:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:28:49 - pico-train - INFO - Step 35000 -- 📈 Saving Learning Dynamics 2025-08-31 00:30:03 - pico-train - INFO - Step 35100 -- 🔄 Training Metrics 2025-08-31 00:30:03 - pico-train - INFO - ├── Loss: 4.9421 2025-08-31 00:30:03 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-31 00:30:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:31:14 - pico-train - INFO - Step 35200 -- 🔄 Training Metrics 2025-08-31 00:31:14 - pico-train - INFO - ├── Loss: 4.9274 2025-08-31 00:31:14 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-31 00:31:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:32:25 - pico-train - INFO - Step 35300 -- 🔄 Training Metrics 2025-08-31 00:32:25 - pico-train - INFO - ├── Loss: 4.9681 2025-08-31 00:32:25 - pico-train - INFO - ├── Learning Rate: 1.48e-04 2025-08-31 00:32:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:33:37 - pico-train - INFO - Step 35400 -- 🔄 Training Metrics 2025-08-31 00:33:37 - pico-train - INFO - ├── Loss: 4.9664 2025-08-31 00:33:37 - pico-train - INFO - ├── Learning Rate: 1.48e-04 2025-08-31 00:33:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:34:48 - pico-train - INFO - Step 35500 -- 🔄 Training Metrics 2025-08-31 00:34:48 - pico-train - INFO - ├── Loss: 4.9410 2025-08-31 00:34:48 - pico-train - INFO - ├── Learning Rate: 1.48e-04 2025-08-31 00:34:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:35:59 - pico-train - INFO - Step 35600 -- 🔄 Training Metrics 2025-08-31 00:35:59 - pico-train - INFO - ├── Loss: 4.9500 2025-08-31 00:35:59 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-31 00:35:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:37:11 - pico-train - INFO - Step 35700 -- 🔄 Training Metrics 2025-08-31 00:37:11 - pico-train - INFO - ├── Loss: 4.9276 2025-08-31 00:37:11 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-31 00:37:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:38:22 - pico-train - INFO - Step 35800 -- 🔄 Training Metrics 2025-08-31 00:38:22 - pico-train - INFO - ├── Loss: 4.9672 2025-08-31 00:38:22 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-31 00:38:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:39:34 - pico-train - INFO - Step 35900 -- 🔄 Training Metrics 2025-08-31 00:39:34 - pico-train - INFO - ├── Loss: 4.9397 2025-08-31 00:39:34 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-31 00:39:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:40:45 - pico-train - INFO - Step 36000 -- 💾 Saving Checkpoint 2025-08-31 00:42:47 - pico-train - INFO - Step 36000 -- 📊 Evaluation Results 2025-08-31 00:42:47 - pico-train - INFO - └── paloma: inf 2025-08-31 00:42:48 - pico-train - INFO - Step 36000 -- 🔄 Training Metrics 2025-08-31 00:42:48 - pico-train - INFO - ├── Loss: 4.9613 2025-08-31 00:42:48 - pico-train - INFO - ├── Learning Rate: 1.46e-04 2025-08-31 00:42:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:42:48 - pico-train - INFO - Step 36000 -- 📈 Saving Learning Dynamics 2025-08-31 00:44:02 - pico-train - INFO - Step 36100 -- 🔄 Training Metrics 2025-08-31 00:44:02 - pico-train - INFO - ├── Loss: 4.9351 2025-08-31 00:44:02 - pico-train - INFO - ├── Learning Rate: 1.46e-04 2025-08-31 00:44:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:45:13 - pico-train - INFO - Step 36200 -- 🔄 Training Metrics 2025-08-31 00:45:13 - pico-train - INFO - ├── Loss: 4.9432 2025-08-31 00:45:13 - pico-train - INFO - ├── Learning Rate: 1.46e-04 2025-08-31 00:45:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:46:24 - pico-train - INFO - Step 36300 -- 🔄 Training Metrics 2025-08-31 00:46:24 - pico-train - INFO - ├── Loss: 4.9407 2025-08-31 00:46:24 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-31 00:46:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:47:36 - pico-train - INFO - Step 36400 -- 🔄 Training Metrics 2025-08-31 00:47:36 - pico-train - INFO - ├── Loss: 4.9587 2025-08-31 00:47:36 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-31 00:47:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:48:48 - pico-train - INFO - Step 36500 -- 🔄 Training Metrics 2025-08-31 00:48:48 - pico-train - INFO - ├── Loss: 4.9297 2025-08-31 00:48:48 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-31 00:48:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:49:59 - pico-train - INFO - Step 36600 -- 🔄 Training Metrics 2025-08-31 00:49:59 - pico-train - INFO - ├── Loss: 4.9252 2025-08-31 00:49:59 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-31 00:49:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:51:10 - pico-train - INFO - Step 36700 -- 🔄 Training Metrics 2025-08-31 00:51:10 - pico-train - INFO - ├── Loss: 4.9334 2025-08-31 00:51:10 - pico-train - INFO - ├── Learning Rate: 1.44e-04 2025-08-31 00:51:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:52:22 - pico-train - INFO - Step 36800 -- 🔄 Training Metrics 2025-08-31 00:52:22 - pico-train - INFO - ├── Loss: 4.9394 2025-08-31 00:52:22 - pico-train - INFO - ├── Learning Rate: 1.44e-04 2025-08-31 00:52:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:53:33 - pico-train - INFO - Step 36900 -- 🔄 Training Metrics 2025-08-31 00:53:33 - pico-train - INFO - ├── Loss: 4.9518 2025-08-31 00:53:33 - pico-train - INFO - ├── Learning Rate: 1.44e-04 2025-08-31 00:53:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:54:44 - pico-train - INFO - Step 37000 -- 💾 Saving Checkpoint 2025-08-31 00:56:45 - pico-train - INFO - Step 37000 -- 📊 Evaluation Results 2025-08-31 00:56:45 - pico-train - INFO - └── paloma: inf 2025-08-31 00:56:46 - pico-train - INFO - Step 37000 -- 🔄 Training Metrics 2025-08-31 00:56:46 - pico-train - INFO - ├── Loss: 4.9360 2025-08-31 00:56:46 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-31 00:56:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:56:46 - pico-train - INFO - Step 37000 -- 📈 Saving Learning Dynamics 2025-08-31 00:58:00 - pico-train - INFO - Step 37100 -- 🔄 Training Metrics 2025-08-31 00:58:00 - pico-train - INFO - ├── Loss: 4.9355 2025-08-31 00:58:00 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-31 00:58:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 00:59:12 - pico-train - INFO - Step 37200 -- 🔄 Training Metrics 2025-08-31 00:59:12 - pico-train - INFO - ├── Loss: 4.9187 2025-08-31 00:59:12 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-31 00:59:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:00:23 - pico-train - INFO - Step 37300 -- 🔄 Training Metrics 2025-08-31 01:00:23 - pico-train - INFO - ├── Loss: 4.9427 2025-08-31 01:00:23 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-31 01:00:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:01:35 - pico-train - INFO - Step 37400 -- 🔄 Training Metrics 2025-08-31 01:01:35 - pico-train - INFO - ├── Loss: 4.9359 2025-08-31 01:01:35 - pico-train - INFO - ├── Learning Rate: 1.42e-04 2025-08-31 01:01:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:02:46 - pico-train - INFO - Step 37500 -- 🔄 Training Metrics 2025-08-31 01:02:46 - pico-train - INFO - ├── Loss: 4.9205 2025-08-31 01:02:46 - pico-train - INFO - ├── Learning Rate: 1.42e-04 2025-08-31 01:02:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:03:57 - pico-train - INFO - Step 37600 -- 🔄 Training Metrics 2025-08-31 01:03:57 - pico-train - INFO - ├── Loss: 4.9373 2025-08-31 01:03:57 - pico-train - INFO - ├── Learning Rate: 1.42e-04 2025-08-31 01:03:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:05:08 - pico-train - INFO - Step 37700 -- 🔄 Training Metrics 2025-08-31 01:05:08 - pico-train - INFO - ├── Loss: 4.9389 2025-08-31 01:05:08 - pico-train - INFO - ├── Learning Rate: 1.41e-04 2025-08-31 01:05:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:06:20 - pico-train - INFO - Step 37800 -- 🔄 Training Metrics 2025-08-31 01:06:20 - pico-train - INFO - ├── Loss: 4.9301 2025-08-31 01:06:20 - pico-train - INFO - ├── Learning Rate: 1.41e-04 2025-08-31 01:06:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:07:31 - pico-train - INFO - Step 37900 -- 🔄 Training Metrics 2025-08-31 01:07:31 - pico-train - INFO - ├── Loss: 4.9262 2025-08-31 01:07:31 - pico-train - INFO - ├── Learning Rate: 1.41e-04 2025-08-31 01:07:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:08:42 - pico-train - INFO - Step 38000 -- 💾 Saving Checkpoint 2025-08-31 01:10:43 - pico-train - INFO - Step 38000 -- 📊 Evaluation Results 2025-08-31 01:10:43 - pico-train - INFO - └── paloma: inf 2025-08-31 01:10:44 - pico-train - INFO - Step 38000 -- 🔄 Training Metrics 2025-08-31 01:10:44 - pico-train - INFO - ├── Loss: 4.9292 2025-08-31 01:10:44 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-31 01:10:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:10:44 - pico-train - INFO - Step 38000 -- 📈 Saving Learning Dynamics 2025-08-31 01:11:58 - pico-train - INFO - Step 38100 -- 🔄 Training Metrics 2025-08-31 01:11:58 - pico-train - INFO - ├── Loss: 4.9439 2025-08-31 01:11:58 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-31 01:11:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:13:09 - pico-train - INFO - Step 38200 -- 🔄 Training Metrics 2025-08-31 01:13:09 - pico-train - INFO - ├── Loss: 4.9389 2025-08-31 01:13:09 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-31 01:13:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:14:20 - pico-train - INFO - Step 38300 -- 🔄 Training Metrics 2025-08-31 01:14:20 - pico-train - INFO - ├── Loss: 4.9439 2025-08-31 01:14:20 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-31 01:14:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:15:33 - pico-train - INFO - Step 38400 -- 🔄 Training Metrics 2025-08-31 01:15:33 - pico-train - INFO - ├── Loss: 4.9466 2025-08-31 01:15:33 - pico-train - INFO - ├── Learning Rate: 1.39e-04 2025-08-31 01:15:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:16:43 - pico-train - INFO - Step 38500 -- 🔄 Training Metrics 2025-08-31 01:16:43 - pico-train - INFO - ├── Loss: 4.9536 2025-08-31 01:16:43 - pico-train - INFO - ├── Learning Rate: 1.39e-04 2025-08-31 01:16:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:17:55 - pico-train - INFO - Step 38600 -- 🔄 Training Metrics 2025-08-31 01:17:55 - pico-train - INFO - ├── Loss: 4.9061 2025-08-31 01:17:55 - pico-train - INFO - ├── Learning Rate: 1.39e-04 2025-08-31 01:17:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:19:07 - pico-train - INFO - Step 38700 -- 🔄 Training Metrics 2025-08-31 01:19:07 - pico-train - INFO - ├── Loss: 4.9307 2025-08-31 01:19:07 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-31 01:19:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:20:18 - pico-train - INFO - Step 38800 -- 🔄 Training Metrics 2025-08-31 01:20:18 - pico-train - INFO - ├── Loss: 4.9027 2025-08-31 01:20:18 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-31 01:20:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:21:30 - pico-train - INFO - Step 38900 -- 🔄 Training Metrics 2025-08-31 01:21:30 - pico-train - INFO - ├── Loss: 4.9224 2025-08-31 01:21:30 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-31 01:21:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:22:40 - pico-train - INFO - Step 39000 -- 💾 Saving Checkpoint 2025-08-31 01:24:41 - pico-train - INFO - Step 39000 -- 📊 Evaluation Results 2025-08-31 01:24:41 - pico-train - INFO - └── paloma: inf 2025-08-31 01:24:42 - pico-train - INFO - Step 39000 -- 🔄 Training Metrics 2025-08-31 01:24:42 - pico-train - INFO - ├── Loss: 4.9213 2025-08-31 01:24:42 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-31 01:24:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:24:42 - pico-train - INFO - Step 39000 -- 📈 Saving Learning Dynamics 2025-08-31 01:25:56 - pico-train - INFO - Step 39100 -- 🔄 Training Metrics 2025-08-31 01:25:56 - pico-train - INFO - ├── Loss: 4.9162 2025-08-31 01:25:56 - pico-train - INFO - ├── Learning Rate: 1.37e-04 2025-08-31 01:25:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:27:08 - pico-train - INFO - Step 39200 -- 🔄 Training Metrics 2025-08-31 01:27:08 - pico-train - INFO - ├── Loss: 4.9188 2025-08-31 01:27:08 - pico-train - INFO - ├── Learning Rate: 1.37e-04 2025-08-31 01:27:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:28:19 - pico-train - INFO - Step 39300 -- 🔄 Training Metrics 2025-08-31 01:28:19 - pico-train - INFO - ├── Loss: 4.9239 2025-08-31 01:28:19 - pico-train - INFO - ├── Learning Rate: 1.37e-04 2025-08-31 01:28:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:29:31 - pico-train - INFO - Step 39400 -- 🔄 Training Metrics 2025-08-31 01:29:31 - pico-train - INFO - ├── Loss: 4.9180 2025-08-31 01:29:31 - pico-train - INFO - ├── Learning Rate: 1.36e-04 2025-08-31 01:29:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:30:42 - pico-train - INFO - Step 39500 -- 🔄 Training Metrics 2025-08-31 01:30:42 - pico-train - INFO - ├── Loss: 4.9127 2025-08-31 01:30:42 - pico-train - INFO - ├── Learning Rate: 1.36e-04 2025-08-31 01:30:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:31:53 - pico-train - INFO - Step 39600 -- 🔄 Training Metrics 2025-08-31 01:31:53 - pico-train - INFO - ├── Loss: 4.9226 2025-08-31 01:31:53 - pico-train - INFO - ├── Learning Rate: 1.36e-04 2025-08-31 01:31:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:33:05 - pico-train - INFO - Step 39700 -- 🔄 Training Metrics 2025-08-31 01:33:05 - pico-train - INFO - ├── Loss: 4.9442 2025-08-31 01:33:05 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-31 01:33:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:34:16 - pico-train - INFO - Step 39800 -- 🔄 Training Metrics 2025-08-31 01:34:16 - pico-train - INFO - ├── Loss: 4.9228 2025-08-31 01:34:16 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-31 01:34:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:35:27 - pico-train - INFO - Step 39900 -- 🔄 Training Metrics 2025-08-31 01:35:27 - pico-train - INFO - ├── Loss: 4.9176 2025-08-31 01:35:27 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-31 01:35:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:36:38 - pico-train - INFO - Step 40000 -- 💾 Saving Checkpoint 2025-08-31 01:38:39 - pico-train - INFO - Step 40000 -- 📊 Evaluation Results 2025-08-31 01:38:39 - pico-train - INFO - └── paloma: inf 2025-08-31 01:38:40 - pico-train - INFO - Step 40000 -- 🔄 Training Metrics 2025-08-31 01:38:40 - pico-train - INFO - ├── Loss: 4.9145 2025-08-31 01:38:40 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-31 01:38:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:38:40 - pico-train - INFO - Step 40000 -- 📈 Saving Learning Dynamics 2025-08-31 01:39:54 - pico-train - INFO - Step 40100 -- 🔄 Training Metrics 2025-08-31 01:39:54 - pico-train - INFO - ├── Loss: 4.9238 2025-08-31 01:39:54 - pico-train - INFO - ├── Learning Rate: 1.34e-04 2025-08-31 01:39:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:41:05 - pico-train - INFO - Step 40200 -- 🔄 Training Metrics 2025-08-31 01:41:05 - pico-train - INFO - ├── Loss: 4.9169 2025-08-31 01:41:05 - pico-train - INFO - ├── Learning Rate: 1.34e-04 2025-08-31 01:41:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:42:16 - pico-train - INFO - Step 40300 -- 🔄 Training Metrics 2025-08-31 01:42:16 - pico-train - INFO - ├── Loss: 4.9209 2025-08-31 01:42:16 - pico-train - INFO - ├── Learning Rate: 1.34e-04 2025-08-31 01:42:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:43:28 - pico-train - INFO - Step 40400 -- 🔄 Training Metrics 2025-08-31 01:43:28 - pico-train - INFO - ├── Loss: 4.9120 2025-08-31 01:43:28 - pico-train - INFO - ├── Learning Rate: 1.33e-04 2025-08-31 01:43:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:44:39 - pico-train - INFO - Step 40500 -- 🔄 Training Metrics 2025-08-31 01:44:39 - pico-train - INFO - ├── Loss: 4.9071 2025-08-31 01:44:39 - pico-train - INFO - ├── Learning Rate: 1.33e-04 2025-08-31 01:44:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:45:50 - pico-train - INFO - Step 40600 -- 🔄 Training Metrics 2025-08-31 01:45:50 - pico-train - INFO - ├── Loss: 4.9123 2025-08-31 01:45:50 - pico-train - INFO - ├── Learning Rate: 1.33e-04 2025-08-31 01:45:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:47:02 - pico-train - INFO - Step 40700 -- 🔄 Training Metrics 2025-08-31 01:47:02 - pico-train - INFO - ├── Loss: 4.9219 2025-08-31 01:47:02 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-31 01:47:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:48:13 - pico-train - INFO - Step 40800 -- 🔄 Training Metrics 2025-08-31 01:48:13 - pico-train - INFO - ├── Loss: 4.8844 2025-08-31 01:48:13 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-31 01:48:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:49:24 - pico-train - INFO - Step 40900 -- 🔄 Training Metrics 2025-08-31 01:49:24 - pico-train - INFO - ├── Loss: 4.9326 2025-08-31 01:49:24 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-31 01:49:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:50:35 - pico-train - INFO - Step 41000 -- 💾 Saving Checkpoint 2025-08-31 01:52:37 - pico-train - INFO - Step 41000 -- 📊 Evaluation Results 2025-08-31 01:52:37 - pico-train - INFO - └── paloma: inf 2025-08-31 01:52:38 - pico-train - INFO - Step 41000 -- 🔄 Training Metrics 2025-08-31 01:52:38 - pico-train - INFO - ├── Loss: 4.8746 2025-08-31 01:52:38 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-31 01:52:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:52:38 - pico-train - INFO - Step 41000 -- 📈 Saving Learning Dynamics 2025-08-31 01:53:52 - pico-train - INFO - Step 41100 -- 🔄 Training Metrics 2025-08-31 01:53:52 - pico-train - INFO - ├── Loss: 4.9076 2025-08-31 01:53:52 - pico-train - INFO - ├── Learning Rate: 1.31e-04 2025-08-31 01:53:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:55:02 - pico-train - INFO - Step 41200 -- 🔄 Training Metrics 2025-08-31 01:55:02 - pico-train - INFO - ├── Loss: 4.9188 2025-08-31 01:55:02 - pico-train - INFO - ├── Learning Rate: 1.31e-04 2025-08-31 01:55:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:56:14 - pico-train - INFO - Step 41300 -- 🔄 Training Metrics 2025-08-31 01:56:14 - pico-train - INFO - ├── Loss: 4.9055 2025-08-31 01:56:14 - pico-train - INFO - ├── Learning Rate: 1.31e-04 2025-08-31 01:56:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:57:25 - pico-train - INFO - Step 41400 -- 🔄 Training Metrics 2025-08-31 01:57:25 - pico-train - INFO - ├── Loss: 4.8996 2025-08-31 01:57:25 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-31 01:57:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:58:36 - pico-train - INFO - Step 41500 -- 🔄 Training Metrics 2025-08-31 01:58:36 - pico-train - INFO - ├── Loss: 4.9231 2025-08-31 01:58:36 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-31 01:58:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 01:59:48 - pico-train - INFO - Step 41600 -- 🔄 Training Metrics 2025-08-31 01:59:48 - pico-train - INFO - ├── Loss: 4.9032 2025-08-31 01:59:48 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-31 01:59:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:00:58 - pico-train - INFO - Step 41700 -- 🔄 Training Metrics 2025-08-31 02:00:58 - pico-train - INFO - ├── Loss: 4.9137 2025-08-31 02:00:58 - pico-train - INFO - ├── Learning Rate: 1.29e-04 2025-08-31 02:00:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:02:10 - pico-train - INFO - Step 41800 -- 🔄 Training Metrics 2025-08-31 02:02:10 - pico-train - INFO - ├── Loss: 4.9201 2025-08-31 02:02:10 - pico-train - INFO - ├── Learning Rate: 1.29e-04 2025-08-31 02:02:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:03:21 - pico-train - INFO - Step 41900 -- 🔄 Training Metrics 2025-08-31 02:03:21 - pico-train - INFO - ├── Loss: 4.8982 2025-08-31 02:03:21 - pico-train - INFO - ├── Learning Rate: 1.29e-04 2025-08-31 02:03:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:04:32 - pico-train - INFO - Step 42000 -- 💾 Saving Checkpoint 2025-08-31 02:06:33 - pico-train - INFO - Step 42000 -- 📊 Evaluation Results 2025-08-31 02:06:33 - pico-train - INFO - └── paloma: inf 2025-08-31 02:06:34 - pico-train - INFO - Step 42000 -- 🔄 Training Metrics 2025-08-31 02:06:34 - pico-train - INFO - ├── Loss: 4.8823 2025-08-31 02:06:34 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-31 02:06:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:06:34 - pico-train - INFO - Step 42000 -- 📈 Saving Learning Dynamics 2025-08-31 02:07:48 - pico-train - INFO - Step 42100 -- 🔄 Training Metrics 2025-08-31 02:07:48 - pico-train - INFO - ├── Loss: 4.8966 2025-08-31 02:07:48 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-31 02:07:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:08:59 - pico-train - INFO - Step 42200 -- 🔄 Training Metrics 2025-08-31 02:08:59 - pico-train - INFO - ├── Loss: 4.8974 2025-08-31 02:08:59 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-31 02:08:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:10:12 - pico-train - INFO - Step 42300 -- 🔄 Training Metrics 2025-08-31 02:10:12 - pico-train - INFO - ├── Loss: 4.9273 2025-08-31 02:10:12 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-31 02:10:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:11:23 - pico-train - INFO - Step 42400 -- 🔄 Training Metrics 2025-08-31 02:11:23 - pico-train - INFO - ├── Loss: 4.9047 2025-08-31 02:11:23 - pico-train - INFO - ├── Learning Rate: 1.27e-04 2025-08-31 02:11:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:12:34 - pico-train - INFO - Step 42500 -- 🔄 Training Metrics 2025-08-31 02:12:34 - pico-train - INFO - ├── Loss: 4.9010 2025-08-31 02:12:34 - pico-train - INFO - ├── Learning Rate: 1.27e-04 2025-08-31 02:12:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:13:45 - pico-train - INFO - Step 42600 -- 🔄 Training Metrics 2025-08-31 02:13:45 - pico-train - INFO - ├── Loss: 4.9314 2025-08-31 02:13:45 - pico-train - INFO - ├── Learning Rate: 1.27e-04 2025-08-31 02:13:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:14:57 - pico-train - INFO - Step 42700 -- 🔄 Training Metrics 2025-08-31 02:14:57 - pico-train - INFO - ├── Loss: 4.8923 2025-08-31 02:14:57 - pico-train - INFO - ├── Learning Rate: 1.26e-04 2025-08-31 02:14:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:16:08 - pico-train - INFO - Step 42800 -- 🔄 Training Metrics 2025-08-31 02:16:08 - pico-train - INFO - ├── Loss: 4.9007 2025-08-31 02:16:08 - pico-train - INFO - ├── Learning Rate: 1.26e-04 2025-08-31 02:16:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:17:19 - pico-train - INFO - Step 42900 -- 🔄 Training Metrics 2025-08-31 02:17:19 - pico-train - INFO - ├── Loss: 4.8903 2025-08-31 02:17:19 - pico-train - INFO - ├── Learning Rate: 1.26e-04 2025-08-31 02:17:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:18:30 - pico-train - INFO - Step 43000 -- 💾 Saving Checkpoint 2025-08-31 02:20:32 - pico-train - INFO - Step 43000 -- 📊 Evaluation Results 2025-08-31 02:20:32 - pico-train - INFO - └── paloma: inf 2025-08-31 02:20:33 - pico-train - INFO - Step 43000 -- 🔄 Training Metrics 2025-08-31 02:20:33 - pico-train - INFO - ├── Loss: 4.9252 2025-08-31 02:20:33 - pico-train - INFO - ├── Learning Rate: 1.25e-04 2025-08-31 02:20:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:20:33 - pico-train - INFO - Step 43000 -- 📈 Saving Learning Dynamics 2025-08-31 02:21:46 - pico-train - INFO - Step 43100 -- 🔄 Training Metrics 2025-08-31 02:21:46 - pico-train - INFO - ├── Loss: 4.8925 2025-08-31 02:21:46 - pico-train - INFO - ├── Learning Rate: 1.25e-04 2025-08-31 02:21:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:22:57 - pico-train - INFO - Step 43200 -- 🔄 Training Metrics 2025-08-31 02:22:57 - pico-train - INFO - ├── Loss: 4.8954 2025-08-31 02:22:57 - pico-train - INFO - ├── Learning Rate: 1.25e-04 2025-08-31 02:22:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:24:09 - pico-train - INFO - Step 43300 -- 🔄 Training Metrics 2025-08-31 02:24:09 - pico-train - INFO - ├── Loss: 4.8650 2025-08-31 02:24:09 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-31 02:24:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:25:21 - pico-train - INFO - Step 43400 -- 🔄 Training Metrics 2025-08-31 02:25:21 - pico-train - INFO - ├── Loss: 4.9019 2025-08-31 02:25:21 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-31 02:25:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:26:32 - pico-train - INFO - Step 43500 -- 🔄 Training Metrics 2025-08-31 02:26:32 - pico-train - INFO - ├── Loss: 4.9002 2025-08-31 02:26:32 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-31 02:26:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:27:44 - pico-train - INFO - Step 43600 -- 🔄 Training Metrics 2025-08-31 02:27:44 - pico-train - INFO - ├── Loss: 4.8981 2025-08-31 02:27:44 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-31 02:27:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:28:55 - pico-train - INFO - Step 43700 -- 🔄 Training Metrics 2025-08-31 02:28:55 - pico-train - INFO - ├── Loss: 4.9206 2025-08-31 02:28:55 - pico-train - INFO - ├── Learning Rate: 1.23e-04 2025-08-31 02:28:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:30:06 - pico-train - INFO - Step 43800 -- 🔄 Training Metrics 2025-08-31 02:30:06 - pico-train - INFO - ├── Loss: 4.8934 2025-08-31 02:30:06 - pico-train - INFO - ├── Learning Rate: 1.23e-04 2025-08-31 02:30:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:31:18 - pico-train - INFO - Step 43900 -- 🔄 Training Metrics 2025-08-31 02:31:18 - pico-train - INFO - ├── Loss: 4.8906 2025-08-31 02:31:18 - pico-train - INFO - ├── Learning Rate: 1.23e-04 2025-08-31 02:31:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:32:28 - pico-train - INFO - Step 44000 -- 💾 Saving Checkpoint 2025-08-31 02:34:29 - pico-train - INFO - Step 44000 -- 📊 Evaluation Results 2025-08-31 02:34:29 - pico-train - INFO - └── paloma: inf 2025-08-31 02:34:30 - pico-train - INFO - Step 44000 -- 🔄 Training Metrics 2025-08-31 02:34:30 - pico-train - INFO - ├── Loss: 4.9013 2025-08-31 02:34:30 - pico-train - INFO - ├── Learning Rate: 1.22e-04 2025-08-31 02:34:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:34:30 - pico-train - INFO - Step 44000 -- 📈 Saving Learning Dynamics 2025-08-31 02:35:44 - pico-train - INFO - Step 44100 -- 🔄 Training Metrics 2025-08-31 02:35:44 - pico-train - INFO - ├── Loss: 4.8915 2025-08-31 02:35:44 - pico-train - INFO - ├── Learning Rate: 1.22e-04 2025-08-31 02:35:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:36:55 - pico-train - INFO - Step 44200 -- 🔄 Training Metrics 2025-08-31 02:36:55 - pico-train - INFO - ├── Loss: 4.8804 2025-08-31 02:36:55 - pico-train - INFO - ├── Learning Rate: 1.22e-04 2025-08-31 02:36:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:38:06 - pico-train - INFO - Step 44300 -- 🔄 Training Metrics 2025-08-31 02:38:06 - pico-train - INFO - ├── Loss: 4.8928 2025-08-31 02:38:06 - pico-train - INFO - ├── Learning Rate: 1.21e-04 2025-08-31 02:38:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:39:18 - pico-train - INFO - Step 44400 -- 🔄 Training Metrics 2025-08-31 02:39:18 - pico-train - INFO - ├── Loss: 4.8801 2025-08-31 02:39:18 - pico-train - INFO - ├── Learning Rate: 1.21e-04 2025-08-31 02:39:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:40:29 - pico-train - INFO - Step 44500 -- 🔄 Training Metrics 2025-08-31 02:40:29 - pico-train - INFO - ├── Loss: 4.9167 2025-08-31 02:40:29 - pico-train - INFO - ├── Learning Rate: 1.21e-04 2025-08-31 02:40:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:41:40 - pico-train - INFO - Step 44600 -- 🔄 Training Metrics 2025-08-31 02:41:40 - pico-train - INFO - ├── Loss: 4.8424 2025-08-31 02:41:40 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-31 02:41:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:42:51 - pico-train - INFO - Step 44700 -- 🔄 Training Metrics 2025-08-31 02:42:51 - pico-train - INFO - ├── Loss: 4.8779 2025-08-31 02:42:51 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-31 02:42:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:44:04 - pico-train - INFO - Step 44800 -- 🔄 Training Metrics 2025-08-31 02:44:04 - pico-train - INFO - ├── Loss: 4.9086 2025-08-31 02:44:04 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-31 02:44:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:45:14 - pico-train - INFO - Step 44900 -- 🔄 Training Metrics 2025-08-31 02:45:14 - pico-train - INFO - ├── Loss: 4.9030 2025-08-31 02:45:14 - pico-train - INFO - ├── Learning Rate: 1.19e-04 2025-08-31 02:45:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:46:25 - pico-train - INFO - Step 45000 -- 💾 Saving Checkpoint 2025-08-31 02:48:27 - pico-train - INFO - Step 45000 -- 📊 Evaluation Results 2025-08-31 02:48:27 - pico-train - INFO - └── paloma: inf 2025-08-31 02:48:27 - pico-train - INFO - Step 45000 -- 🔄 Training Metrics 2025-08-31 02:48:27 - pico-train - INFO - ├── Loss: 4.8994 2025-08-31 02:48:27 - pico-train - INFO - ├── Learning Rate: 1.19e-04 2025-08-31 02:48:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:48:27 - pico-train - INFO - Step 45000 -- 📈 Saving Learning Dynamics 2025-08-31 02:49:41 - pico-train - INFO - Step 45100 -- 🔄 Training Metrics 2025-08-31 02:49:41 - pico-train - INFO - ├── Loss: 4.8970 2025-08-31 02:49:41 - pico-train - INFO - ├── Learning Rate: 1.19e-04 2025-08-31 02:49:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:50:53 - pico-train - INFO - Step 45200 -- 🔄 Training Metrics 2025-08-31 02:50:53 - pico-train - INFO - ├── Loss: 4.8832 2025-08-31 02:50:53 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-31 02:50:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:52:05 - pico-train - INFO - Step 45300 -- 🔄 Training Metrics 2025-08-31 02:52:05 - pico-train - INFO - ├── Loss: 4.8729 2025-08-31 02:52:05 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-31 02:52:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:53:16 - pico-train - INFO - Step 45400 -- 🔄 Training Metrics 2025-08-31 02:53:16 - pico-train - INFO - ├── Loss: 4.8860 2025-08-31 02:53:16 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-31 02:53:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:54:27 - pico-train - INFO - Step 45500 -- 🔄 Training Metrics 2025-08-31 02:54:27 - pico-train - INFO - ├── Loss: 4.9128 2025-08-31 02:54:27 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-31 02:54:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:55:38 - pico-train - INFO - Step 45600 -- 🔄 Training Metrics 2025-08-31 02:55:38 - pico-train - INFO - ├── Loss: 4.8549 2025-08-31 02:55:38 - pico-train - INFO - ├── Learning Rate: 1.17e-04 2025-08-31 02:55:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:56:50 - pico-train - INFO - Step 45700 -- 🔄 Training Metrics 2025-08-31 02:56:50 - pico-train - INFO - ├── Loss: 4.8901 2025-08-31 02:56:50 - pico-train - INFO - ├── Learning Rate: 1.17e-04 2025-08-31 02:56:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:58:02 - pico-train - INFO - Step 45800 -- 🔄 Training Metrics 2025-08-31 02:58:02 - pico-train - INFO - ├── Loss: 4.8899 2025-08-31 02:58:02 - pico-train - INFO - ├── Learning Rate: 1.17e-04 2025-08-31 02:58:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 02:59:12 - pico-train - INFO - Step 45900 -- 🔄 Training Metrics 2025-08-31 02:59:12 - pico-train - INFO - ├── Loss: 4.8725 2025-08-31 02:59:12 - pico-train - INFO - ├── Learning Rate: 1.16e-04 2025-08-31 02:59:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:00:23 - pico-train - INFO - Step 46000 -- 💾 Saving Checkpoint 2025-08-31 03:02:25 - pico-train - INFO - Step 46000 -- 📊 Evaluation Results 2025-08-31 03:02:25 - pico-train - INFO - └── paloma: inf 2025-08-31 03:02:26 - pico-train - INFO - Step 46000 -- 🔄 Training Metrics 2025-08-31 03:02:26 - pico-train - INFO - ├── Loss: 4.8771 2025-08-31 03:02:26 - pico-train - INFO - ├── Learning Rate: 1.16e-04 2025-08-31 03:02:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:02:26 - pico-train - INFO - Step 46000 -- 📈 Saving Learning Dynamics 2025-08-31 03:03:41 - pico-train - INFO - Step 46100 -- 🔄 Training Metrics 2025-08-31 03:03:41 - pico-train - INFO - ├── Loss: 4.8648 2025-08-31 03:03:41 - pico-train - INFO - ├── Learning Rate: 1.16e-04 2025-08-31 03:03:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:04:52 - pico-train - INFO - Step 46200 -- 🔄 Training Metrics 2025-08-31 03:04:52 - pico-train - INFO - ├── Loss: 4.8980 2025-08-31 03:04:52 - pico-train - INFO - ├── Learning Rate: 1.15e-04 2025-08-31 03:04:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:06:03 - pico-train - INFO - Step 46300 -- 🔄 Training Metrics 2025-08-31 03:06:03 - pico-train - INFO - ├── Loss: 4.8868 2025-08-31 03:06:03 - pico-train - INFO - ├── Learning Rate: 1.15e-04 2025-08-31 03:06:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:07:15 - pico-train - INFO - Step 46400 -- 🔄 Training Metrics 2025-08-31 03:07:15 - pico-train - INFO - ├── Loss: 4.8807 2025-08-31 03:07:15 - pico-train - INFO - ├── Learning Rate: 1.15e-04 2025-08-31 03:07:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:08:27 - pico-train - INFO - Step 46500 -- 🔄 Training Metrics 2025-08-31 03:08:27 - pico-train - INFO - ├── Loss: 4.8779 2025-08-31 03:08:27 - pico-train - INFO - ├── Learning Rate: 1.14e-04 2025-08-31 03:08:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:09:38 - pico-train - INFO - Step 46600 -- 🔄 Training Metrics 2025-08-31 03:09:38 - pico-train - INFO - ├── Loss: 4.8909 2025-08-31 03:09:38 - pico-train - INFO - ├── Learning Rate: 1.14e-04 2025-08-31 03:09:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:10:49 - pico-train - INFO - Step 46700 -- 🔄 Training Metrics 2025-08-31 03:10:49 - pico-train - INFO - ├── Loss: 4.8883 2025-08-31 03:10:49 - pico-train - INFO - ├── Learning Rate: 1.14e-04 2025-08-31 03:10:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:12:01 - pico-train - INFO - Step 46800 -- 🔄 Training Metrics 2025-08-31 03:12:01 - pico-train - INFO - ├── Loss: 4.8876 2025-08-31 03:12:01 - pico-train - INFO - ├── Learning Rate: 1.13e-04 2025-08-31 03:12:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:13:12 - pico-train - INFO - Step 46900 -- 🔄 Training Metrics 2025-08-31 03:13:12 - pico-train - INFO - ├── Loss: 4.8686 2025-08-31 03:13:12 - pico-train - INFO - ├── Learning Rate: 1.13e-04 2025-08-31 03:13:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:14:23 - pico-train - INFO - Step 47000 -- 💾 Saving Checkpoint 2025-08-31 03:16:24 - pico-train - INFO - Step 47000 -- 📊 Evaluation Results 2025-08-31 03:16:24 - pico-train - INFO - └── paloma: inf 2025-08-31 03:16:25 - pico-train - INFO - Step 47000 -- 🔄 Training Metrics 2025-08-31 03:16:25 - pico-train - INFO - ├── Loss: 4.8700 2025-08-31 03:16:25 - pico-train - INFO - ├── Learning Rate: 1.13e-04 2025-08-31 03:16:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:16:25 - pico-train - INFO - Step 47000 -- 📈 Saving Learning Dynamics 2025-08-31 03:17:39 - pico-train - INFO - Step 47100 -- 🔄 Training Metrics 2025-08-31 03:17:39 - pico-train - INFO - ├── Loss: 4.8670 2025-08-31 03:17:39 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-31 03:17:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:18:49 - pico-train - INFO - Step 47200 -- 🔄 Training Metrics 2025-08-31 03:18:49 - pico-train - INFO - ├── Loss: 4.8849 2025-08-31 03:18:49 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-31 03:18:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:20:00 - pico-train - INFO - Step 47300 -- 🔄 Training Metrics 2025-08-31 03:20:00 - pico-train - INFO - ├── Loss: 4.8666 2025-08-31 03:20:00 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-31 03:20:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:21:12 - pico-train - INFO - Step 47400 -- 🔄 Training Metrics 2025-08-31 03:21:12 - pico-train - INFO - ├── Loss: 4.8596 2025-08-31 03:21:12 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-31 03:21:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:22:23 - pico-train - INFO - Step 47500 -- 🔄 Training Metrics 2025-08-31 03:22:23 - pico-train - INFO - ├── Loss: 4.8679 2025-08-31 03:22:23 - pico-train - INFO - ├── Learning Rate: 1.11e-04 2025-08-31 03:22:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:23:34 - pico-train - INFO - Step 47600 -- 🔄 Training Metrics 2025-08-31 03:23:34 - pico-train - INFO - ├── Loss: 4.8866 2025-08-31 03:23:34 - pico-train - INFO - ├── Learning Rate: 1.11e-04 2025-08-31 03:23:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:24:45 - pico-train - INFO - Step 47700 -- 🔄 Training Metrics 2025-08-31 03:24:45 - pico-train - INFO - ├── Loss: 4.8761 2025-08-31 03:24:45 - pico-train - INFO - ├── Learning Rate: 1.11e-04 2025-08-31 03:24:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:25:56 - pico-train - INFO - Step 47800 -- 🔄 Training Metrics 2025-08-31 03:25:56 - pico-train - INFO - ├── Loss: 4.8965 2025-08-31 03:25:56 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-31 03:25:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:27:07 - pico-train - INFO - Step 47900 -- 🔄 Training Metrics 2025-08-31 03:27:07 - pico-train - INFO - ├── Loss: 4.8890 2025-08-31 03:27:07 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-31 03:27:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:28:18 - pico-train - INFO - Step 48000 -- 💾 Saving Checkpoint 2025-08-31 03:30:19 - pico-train - INFO - Step 48000 -- 📊 Evaluation Results 2025-08-31 03:30:19 - pico-train - INFO - └── paloma: inf 2025-08-31 03:30:20 - pico-train - INFO - Step 48000 -- 🔄 Training Metrics 2025-08-31 03:30:20 - pico-train - INFO - ├── Loss: 4.8801 2025-08-31 03:30:20 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-31 03:30:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:30:20 - pico-train - INFO - Step 48000 -- 📈 Saving Learning Dynamics 2025-08-31 03:31:33 - pico-train - INFO - Step 48100 -- 🔄 Training Metrics 2025-08-31 03:31:33 - pico-train - INFO - ├── Loss: 4.8751 2025-08-31 03:31:33 - pico-train - INFO - ├── Learning Rate: 1.09e-04 2025-08-31 03:31:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:32:45 - pico-train - INFO - Step 48200 -- 🔄 Training Metrics 2025-08-31 03:32:45 - pico-train - INFO - ├── Loss: 4.8702 2025-08-31 03:32:45 - pico-train - INFO - ├── Learning Rate: 1.09e-04 2025-08-31 03:32:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:33:56 - pico-train - INFO - Step 48300 -- 🔄 Training Metrics 2025-08-31 03:33:56 - pico-train - INFO - ├── Loss: 4.8748 2025-08-31 03:33:56 - pico-train - INFO - ├── Learning Rate: 1.09e-04 2025-08-31 03:33:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:35:07 - pico-train - INFO - Step 48400 -- 🔄 Training Metrics 2025-08-31 03:35:07 - pico-train - INFO - ├── Loss: 4.8780 2025-08-31 03:35:07 - pico-train - INFO - ├── Learning Rate: 1.08e-04 2025-08-31 03:35:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:36:19 - pico-train - INFO - Step 48500 -- 🔄 Training Metrics 2025-08-31 03:36:19 - pico-train - INFO - ├── Loss: 4.8676 2025-08-31 03:36:19 - pico-train - INFO - ├── Learning Rate: 1.08e-04 2025-08-31 03:36:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:37:29 - pico-train - INFO - Step 48600 -- 🔄 Training Metrics 2025-08-31 03:37:29 - pico-train - INFO - ├── Loss: 4.8609 2025-08-31 03:37:29 - pico-train - INFO - ├── Learning Rate: 1.08e-04 2025-08-31 03:37:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:38:41 - pico-train - INFO - Step 48700 -- 🔄 Training Metrics 2025-08-31 03:38:41 - pico-train - INFO - ├── Loss: 4.8671 2025-08-31 03:38:41 - pico-train - INFO - ├── Learning Rate: 1.07e-04 2025-08-31 03:38:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:39:52 - pico-train - INFO - Step 48800 -- 🔄 Training Metrics 2025-08-31 03:39:52 - pico-train - INFO - ├── Loss: 4.8771 2025-08-31 03:39:52 - pico-train - INFO - ├── Learning Rate: 1.07e-04 2025-08-31 03:39:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:41:03 - pico-train - INFO - Step 48900 -- 🔄 Training Metrics 2025-08-31 03:41:03 - pico-train - INFO - ├── Loss: 4.8739 2025-08-31 03:41:03 - pico-train - INFO - ├── Learning Rate: 1.07e-04 2025-08-31 03:41:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:42:13 - pico-train - INFO - Step 49000 -- 💾 Saving Checkpoint 2025-08-31 03:44:16 - pico-train - INFO - Step 49000 -- 📊 Evaluation Results 2025-08-31 03:44:16 - pico-train - INFO - └── paloma: inf 2025-08-31 03:44:17 - pico-train - INFO - Step 49000 -- 🔄 Training Metrics 2025-08-31 03:44:17 - pico-train - INFO - ├── Loss: 4.8755 2025-08-31 03:44:17 - pico-train - INFO - ├── Learning Rate: 1.06e-04 2025-08-31 03:44:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:44:17 - pico-train - INFO - Step 49000 -- 📈 Saving Learning Dynamics 2025-08-31 03:45:30 - pico-train - INFO - Step 49100 -- 🔄 Training Metrics 2025-08-31 03:45:30 - pico-train - INFO - ├── Loss: 4.8520 2025-08-31 03:45:30 - pico-train - INFO - ├── Learning Rate: 1.06e-04 2025-08-31 03:45:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:46:41 - pico-train - INFO - Step 49200 -- 🔄 Training Metrics 2025-08-31 03:46:41 - pico-train - INFO - ├── Loss: 4.8698 2025-08-31 03:46:41 - pico-train - INFO - ├── Learning Rate: 1.06e-04 2025-08-31 03:46:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:47:53 - pico-train - INFO - Step 49300 -- 🔄 Training Metrics 2025-08-31 03:47:53 - pico-train - INFO - ├── Loss: 4.8818 2025-08-31 03:47:53 - pico-train - INFO - ├── Learning Rate: 1.05e-04 2025-08-31 03:47:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:49:03 - pico-train - INFO - Step 49400 -- 🔄 Training Metrics 2025-08-31 03:49:03 - pico-train - INFO - ├── Loss: 4.8478 2025-08-31 03:49:03 - pico-train - INFO - ├── Learning Rate: 1.05e-04 2025-08-31 03:49:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:50:14 - pico-train - INFO - Step 49500 -- 🔄 Training Metrics 2025-08-31 03:50:14 - pico-train - INFO - ├── Loss: 4.8803 2025-08-31 03:50:14 - pico-train - INFO - ├── Learning Rate: 1.05e-04 2025-08-31 03:50:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:51:25 - pico-train - INFO - Step 49600 -- 🔄 Training Metrics 2025-08-31 03:51:25 - pico-train - INFO - ├── Loss: 4.8609 2025-08-31 03:51:25 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-31 03:51:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:52:36 - pico-train - INFO - Step 49700 -- 🔄 Training Metrics 2025-08-31 03:52:36 - pico-train - INFO - ├── Loss: 4.8419 2025-08-31 03:52:36 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-31 03:52:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:53:47 - pico-train - INFO - Step 49800 -- 🔄 Training Metrics 2025-08-31 03:53:47 - pico-train - INFO - ├── Loss: 4.8767 2025-08-31 03:53:47 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-31 03:53:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:54:58 - pico-train - INFO - Step 49900 -- 🔄 Training Metrics 2025-08-31 03:54:58 - pico-train - INFO - ├── Loss: 4.8595 2025-08-31 03:54:58 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-31 03:54:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:56:09 - pico-train - INFO - Step 50000 -- 💾 Saving Checkpoint 2025-08-31 03:58:10 - pico-train - INFO - Step 50000 -- 📊 Evaluation Results 2025-08-31 03:58:10 - pico-train - INFO - └── paloma: inf 2025-08-31 03:58:11 - pico-train - INFO - Step 50000 -- 🔄 Training Metrics 2025-08-31 03:58:11 - pico-train - INFO - ├── Loss: 4.8787 2025-08-31 03:58:11 - pico-train - INFO - ├── Learning Rate: 1.03e-04 2025-08-31 03:58:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 03:58:11 - pico-train - INFO - Step 50000 -- 📈 Saving Learning Dynamics 2025-08-31 03:59:25 - pico-train - INFO - Step 50100 -- 🔄 Training Metrics 2025-08-31 03:59:25 - pico-train - INFO - ├── Loss: 4.8819 2025-08-31 03:59:25 - pico-train - INFO - ├── Learning Rate: 1.03e-04 2025-08-31 03:59:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:00:36 - pico-train - INFO - Step 50200 -- 🔄 Training Metrics 2025-08-31 04:00:36 - pico-train - INFO - ├── Loss: 4.8675 2025-08-31 04:00:36 - pico-train - INFO - ├── Learning Rate: 1.03e-04 2025-08-31 04:00:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:01:47 - pico-train - INFO - Step 50300 -- 🔄 Training Metrics 2025-08-31 04:01:47 - pico-train - INFO - ├── Loss: 4.8522 2025-08-31 04:01:47 - pico-train - INFO - ├── Learning Rate: 1.02e-04 2025-08-31 04:01:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:02:58 - pico-train - INFO - Step 50400 -- 🔄 Training Metrics 2025-08-31 04:02:58 - pico-train - INFO - ├── Loss: 4.8488 2025-08-31 04:02:58 - pico-train - INFO - ├── Learning Rate: 1.02e-04 2025-08-31 04:02:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:04:09 - pico-train - INFO - Step 50500 -- 🔄 Training Metrics 2025-08-31 04:04:09 - pico-train - INFO - ├── Loss: 4.8620 2025-08-31 04:04:09 - pico-train - INFO - ├── Learning Rate: 1.02e-04 2025-08-31 04:04:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:05:20 - pico-train - INFO - Step 50600 -- 🔄 Training Metrics 2025-08-31 04:05:20 - pico-train - INFO - ├── Loss: 4.8662 2025-08-31 04:05:20 - pico-train - INFO - ├── Learning Rate: 1.01e-04 2025-08-31 04:05:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:06:31 - pico-train - INFO - Step 50700 -- 🔄 Training Metrics 2025-08-31 04:06:31 - pico-train - INFO - ├── Loss: 4.8596 2025-08-31 04:06:31 - pico-train - INFO - ├── Learning Rate: 1.01e-04 2025-08-31 04:06:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:07:42 - pico-train - INFO - Step 50800 -- 🔄 Training Metrics 2025-08-31 04:07:42 - pico-train - INFO - ├── Loss: 4.8543 2025-08-31 04:07:42 - pico-train - INFO - ├── Learning Rate: 1.01e-04 2025-08-31 04:07:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:08:53 - pico-train - INFO - Step 50900 -- 🔄 Training Metrics 2025-08-31 04:08:53 - pico-train - INFO - ├── Loss: 4.8712 2025-08-31 04:08:53 - pico-train - INFO - ├── Learning Rate: 1.00e-04 2025-08-31 04:08:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:10:03 - pico-train - INFO - Step 51000 -- 💾 Saving Checkpoint 2025-08-31 04:12:05 - pico-train - INFO - Step 51000 -- 📊 Evaluation Results 2025-08-31 04:12:05 - pico-train - INFO - └── paloma: inf 2025-08-31 04:12:05 - pico-train - INFO - Step 51000 -- 🔄 Training Metrics 2025-08-31 04:12:05 - pico-train - INFO - ├── Loss: 4.8637 2025-08-31 04:12:05 - pico-train - INFO - ├── Learning Rate: 1.00e-04 2025-08-31 04:12:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:12:05 - pico-train - INFO - Step 51000 -- 📈 Saving Learning Dynamics 2025-08-31 04:13:20 - pico-train - INFO - Step 51100 -- 🔄 Training Metrics 2025-08-31 04:13:20 - pico-train - INFO - ├── Loss: 4.8526 2025-08-31 04:13:20 - pico-train - INFO - ├── Learning Rate: 9.97e-05 2025-08-31 04:13:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:14:31 - pico-train - INFO - Step 51200 -- 🔄 Training Metrics 2025-08-31 04:14:31 - pico-train - INFO - ├── Loss: 4.8603 2025-08-31 04:14:31 - pico-train - INFO - ├── Learning Rate: 9.94e-05 2025-08-31 04:14:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:15:42 - pico-train - INFO - Step 51300 -- 🔄 Training Metrics 2025-08-31 04:15:42 - pico-train - INFO - ├── Loss: 4.8577 2025-08-31 04:15:42 - pico-train - INFO - ├── Learning Rate: 9.90e-05 2025-08-31 04:15:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:16:53 - pico-train - INFO - Step 51400 -- 🔄 Training Metrics 2025-08-31 04:16:53 - pico-train - INFO - ├── Loss: 4.8589 2025-08-31 04:16:53 - pico-train - INFO - ├── Learning Rate: 9.87e-05 2025-08-31 04:16:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:18:05 - pico-train - INFO - Step 51500 -- 🔄 Training Metrics 2025-08-31 04:18:05 - pico-train - INFO - ├── Loss: 4.8715 2025-08-31 04:18:05 - pico-train - INFO - ├── Learning Rate: 9.84e-05 2025-08-31 04:18:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:19:16 - pico-train - INFO - Step 51600 -- 🔄 Training Metrics 2025-08-31 04:19:16 - pico-train - INFO - ├── Loss: 4.8822 2025-08-31 04:19:16 - pico-train - INFO - ├── Learning Rate: 9.81e-05 2025-08-31 04:19:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:20:27 - pico-train - INFO - Step 51700 -- 🔄 Training Metrics 2025-08-31 04:20:27 - pico-train - INFO - ├── Loss: 4.8642 2025-08-31 04:20:27 - pico-train - INFO - ├── Learning Rate: 9.78e-05 2025-08-31 04:20:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:21:37 - pico-train - INFO - Step 51800 -- 🔄 Training Metrics 2025-08-31 04:21:37 - pico-train - INFO - ├── Loss: 4.8631 2025-08-31 04:21:37 - pico-train - INFO - ├── Learning Rate: 9.74e-05 2025-08-31 04:21:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:22:48 - pico-train - INFO - Step 51900 -- 🔄 Training Metrics 2025-08-31 04:22:48 - pico-train - INFO - ├── Loss: 4.8383 2025-08-31 04:22:48 - pico-train - INFO - ├── Learning Rate: 9.71e-05 2025-08-31 04:22:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:23:59 - pico-train - INFO - Step 52000 -- 💾 Saving Checkpoint 2025-08-31 04:26:01 - pico-train - INFO - Step 52000 -- 📊 Evaluation Results 2025-08-31 04:26:01 - pico-train - INFO - └── paloma: inf 2025-08-31 04:26:01 - pico-train - INFO - Step 52000 -- 🔄 Training Metrics 2025-08-31 04:26:01 - pico-train - INFO - ├── Loss: 4.8495 2025-08-31 04:26:01 - pico-train - INFO - ├── Learning Rate: 9.68e-05 2025-08-31 04:26:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:26:01 - pico-train - INFO - Step 52000 -- 📈 Saving Learning Dynamics 2025-08-31 04:27:15 - pico-train - INFO - Step 52100 -- 🔄 Training Metrics 2025-08-31 04:27:15 - pico-train - INFO - ├── Loss: 4.8515 2025-08-31 04:27:15 - pico-train - INFO - ├── Learning Rate: 9.65e-05 2025-08-31 04:27:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:28:27 - pico-train - INFO - Step 52200 -- 🔄 Training Metrics 2025-08-31 04:28:27 - pico-train - INFO - ├── Loss: 4.8600 2025-08-31 04:28:27 - pico-train - INFO - ├── Learning Rate: 9.62e-05 2025-08-31 04:28:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:29:37 - pico-train - INFO - Step 52300 -- 🔄 Training Metrics 2025-08-31 04:29:37 - pico-train - INFO - ├── Loss: 4.8696 2025-08-31 04:29:37 - pico-train - INFO - ├── Learning Rate: 9.58e-05 2025-08-31 04:29:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:30:48 - pico-train - INFO - Step 52400 -- 🔄 Training Metrics 2025-08-31 04:30:48 - pico-train - INFO - ├── Loss: 4.8359 2025-08-31 04:30:48 - pico-train - INFO - ├── Learning Rate: 9.55e-05 2025-08-31 04:30:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:32:00 - pico-train - INFO - Step 52500 -- 🔄 Training Metrics 2025-08-31 04:32:00 - pico-train - INFO - ├── Loss: 4.8445 2025-08-31 04:32:00 - pico-train - INFO - ├── Learning Rate: 9.52e-05 2025-08-31 04:32:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:33:11 - pico-train - INFO - Step 52600 -- 🔄 Training Metrics 2025-08-31 04:33:11 - pico-train - INFO - ├── Loss: 4.8626 2025-08-31 04:33:11 - pico-train - INFO - ├── Learning Rate: 9.49e-05 2025-08-31 04:33:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:34:22 - pico-train - INFO - Step 52700 -- 🔄 Training Metrics 2025-08-31 04:34:22 - pico-train - INFO - ├── Loss: 4.8556 2025-08-31 04:34:22 - pico-train - INFO - ├── Learning Rate: 9.46e-05 2025-08-31 04:34:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:35:33 - pico-train - INFO - Step 52800 -- 🔄 Training Metrics 2025-08-31 04:35:33 - pico-train - INFO - ├── Loss: 4.8360 2025-08-31 04:35:33 - pico-train - INFO - ├── Learning Rate: 9.42e-05 2025-08-31 04:35:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:36:44 - pico-train - INFO - Step 52900 -- 🔄 Training Metrics 2025-08-31 04:36:44 - pico-train - INFO - ├── Loss: 4.8517 2025-08-31 04:36:44 - pico-train - INFO - ├── Learning Rate: 9.39e-05 2025-08-31 04:36:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:37:55 - pico-train - INFO - Step 53000 -- 💾 Saving Checkpoint 2025-08-31 04:39:57 - pico-train - INFO - Step 53000 -- 📊 Evaluation Results 2025-08-31 04:39:57 - pico-train - INFO - └── paloma: inf 2025-08-31 04:39:58 - pico-train - INFO - Step 53000 -- 🔄 Training Metrics 2025-08-31 04:39:58 - pico-train - INFO - ├── Loss: 4.8507 2025-08-31 04:39:58 - pico-train - INFO - ├── Learning Rate: 9.36e-05 2025-08-31 04:39:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:39:58 - pico-train - INFO - Step 53000 -- 📈 Saving Learning Dynamics 2025-08-31 04:41:11 - pico-train - INFO - Step 53100 -- 🔄 Training Metrics 2025-08-31 04:41:11 - pico-train - INFO - ├── Loss: 4.8585 2025-08-31 04:41:11 - pico-train - INFO - ├── Learning Rate: 9.33e-05 2025-08-31 04:41:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:42:22 - pico-train - INFO - Step 53200 -- 🔄 Training Metrics 2025-08-31 04:42:22 - pico-train - INFO - ├── Loss: 4.8520 2025-08-31 04:42:22 - pico-train - INFO - ├── Learning Rate: 9.30e-05 2025-08-31 04:42:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:43:33 - pico-train - INFO - Step 53300 -- 🔄 Training Metrics 2025-08-31 04:43:33 - pico-train - INFO - ├── Loss: 4.8463 2025-08-31 04:43:33 - pico-train - INFO - ├── Learning Rate: 9.26e-05 2025-08-31 04:43:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:44:45 - pico-train - INFO - Step 53400 -- 🔄 Training Metrics 2025-08-31 04:44:45 - pico-train - INFO - ├── Loss: 4.8443 2025-08-31 04:44:45 - pico-train - INFO - ├── Learning Rate: 9.23e-05 2025-08-31 04:44:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:45:56 - pico-train - INFO - Step 53500 -- 🔄 Training Metrics 2025-08-31 04:45:56 - pico-train - INFO - ├── Loss: 4.8567 2025-08-31 04:45:56 - pico-train - INFO - ├── Learning Rate: 9.20e-05 2025-08-31 04:45:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:47:07 - pico-train - INFO - Step 53600 -- 🔄 Training Metrics 2025-08-31 04:47:07 - pico-train - INFO - ├── Loss: 4.8257 2025-08-31 04:47:07 - pico-train - INFO - ├── Learning Rate: 9.17e-05 2025-08-31 04:47:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:48:18 - pico-train - INFO - Step 53700 -- 🔄 Training Metrics 2025-08-31 04:48:18 - pico-train - INFO - ├── Loss: 4.8236 2025-08-31 04:48:18 - pico-train - INFO - ├── Learning Rate: 9.14e-05 2025-08-31 04:48:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:49:30 - pico-train - INFO - Step 53800 -- 🔄 Training Metrics 2025-08-31 04:49:30 - pico-train - INFO - ├── Loss: 4.8331 2025-08-31 04:49:30 - pico-train - INFO - ├── Learning Rate: 9.10e-05 2025-08-31 04:49:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:50:41 - pico-train - INFO - Step 53900 -- 🔄 Training Metrics 2025-08-31 04:50:41 - pico-train - INFO - ├── Loss: 4.8663 2025-08-31 04:50:41 - pico-train - INFO - ├── Learning Rate: 9.07e-05 2025-08-31 04:50:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:51:51 - pico-train - INFO - Step 54000 -- 💾 Saving Checkpoint 2025-08-31 04:53:52 - pico-train - INFO - Step 54000 -- 📊 Evaluation Results 2025-08-31 04:53:52 - pico-train - INFO - └── paloma: inf 2025-08-31 04:53:53 - pico-train - INFO - Step 54000 -- 🔄 Training Metrics 2025-08-31 04:53:53 - pico-train - INFO - ├── Loss: 4.8621 2025-08-31 04:53:53 - pico-train - INFO - ├── Learning Rate: 9.04e-05 2025-08-31 04:53:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:53:53 - pico-train - INFO - Step 54000 -- 📈 Saving Learning Dynamics 2025-08-31 04:55:07 - pico-train - INFO - Step 54100 -- 🔄 Training Metrics 2025-08-31 04:55:07 - pico-train - INFO - ├── Loss: 4.8374 2025-08-31 04:55:07 - pico-train - INFO - ├── Learning Rate: 9.01e-05 2025-08-31 04:55:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:56:18 - pico-train - INFO - Step 54200 -- 🔄 Training Metrics 2025-08-31 04:56:18 - pico-train - INFO - ├── Loss: 4.8493 2025-08-31 04:56:18 - pico-train - INFO - ├── Learning Rate: 8.98e-05 2025-08-31 04:56:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:57:29 - pico-train - INFO - Step 54300 -- 🔄 Training Metrics 2025-08-31 04:57:29 - pico-train - INFO - ├── Loss: 4.8266 2025-08-31 04:57:29 - pico-train - INFO - ├── Learning Rate: 8.94e-05 2025-08-31 04:57:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:58:40 - pico-train - INFO - Step 54400 -- 🔄 Training Metrics 2025-08-31 04:58:40 - pico-train - INFO - ├── Loss: 4.8625 2025-08-31 04:58:40 - pico-train - INFO - ├── Learning Rate: 8.91e-05 2025-08-31 04:58:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 04:59:51 - pico-train - INFO - Step 54500 -- 🔄 Training Metrics 2025-08-31 04:59:51 - pico-train - INFO - ├── Loss: 4.8460 2025-08-31 04:59:51 - pico-train - INFO - ├── Learning Rate: 8.88e-05 2025-08-31 04:59:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:01:02 - pico-train - INFO - Step 54600 -- 🔄 Training Metrics 2025-08-31 05:01:02 - pico-train - INFO - ├── Loss: 4.8332 2025-08-31 05:01:02 - pico-train - INFO - ├── Learning Rate: 8.85e-05 2025-08-31 05:01:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:02:13 - pico-train - INFO - Step 54700 -- 🔄 Training Metrics 2025-08-31 05:02:13 - pico-train - INFO - ├── Loss: 4.8508 2025-08-31 05:02:13 - pico-train - INFO - ├── Learning Rate: 8.82e-05 2025-08-31 05:02:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:03:24 - pico-train - INFO - Step 54800 -- 🔄 Training Metrics 2025-08-31 05:03:24 - pico-train - INFO - ├── Loss: 4.8588 2025-08-31 05:03:24 - pico-train - INFO - ├── Learning Rate: 8.78e-05 2025-08-31 05:03:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:04:36 - pico-train - INFO - Step 54900 -- 🔄 Training Metrics 2025-08-31 05:04:36 - pico-train - INFO - ├── Loss: 4.8781 2025-08-31 05:04:36 - pico-train - INFO - ├── Learning Rate: 8.75e-05 2025-08-31 05:04:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:05:45 - pico-train - INFO - Step 55000 -- 💾 Saving Checkpoint 2025-08-31 05:07:47 - pico-train - INFO - Step 55000 -- 📊 Evaluation Results 2025-08-31 05:07:47 - pico-train - INFO - └── paloma: inf 2025-08-31 05:07:48 - pico-train - INFO - Step 55000 -- 🔄 Training Metrics 2025-08-31 05:07:48 - pico-train - INFO - ├── Loss: 4.8366 2025-08-31 05:07:48 - pico-train - INFO - ├── Learning Rate: 8.72e-05 2025-08-31 05:07:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:07:48 - pico-train - INFO - Step 55000 -- 📈 Saving Learning Dynamics 2025-08-31 05:09:02 - pico-train - INFO - Step 55100 -- 🔄 Training Metrics 2025-08-31 05:09:02 - pico-train - INFO - ├── Loss: 4.8395 2025-08-31 05:09:02 - pico-train - INFO - ├── Learning Rate: 8.69e-05 2025-08-31 05:09:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:10:13 - pico-train - INFO - Step 55200 -- 🔄 Training Metrics 2025-08-31 05:10:13 - pico-train - INFO - ├── Loss: 4.8307 2025-08-31 05:10:13 - pico-train - INFO - ├── Learning Rate: 8.66e-05 2025-08-31 05:10:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:11:24 - pico-train - INFO - Step 55300 -- 🔄 Training Metrics 2025-08-31 05:11:24 - pico-train - INFO - ├── Loss: 4.8421 2025-08-31 05:11:24 - pico-train - INFO - ├── Learning Rate: 8.63e-05 2025-08-31 05:11:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:12:35 - pico-train - INFO - Step 55400 -- 🔄 Training Metrics 2025-08-31 05:12:35 - pico-train - INFO - ├── Loss: 4.8537 2025-08-31 05:12:35 - pico-train - INFO - ├── Learning Rate: 8.59e-05 2025-08-31 05:12:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:13:46 - pico-train - INFO - Step 55500 -- 🔄 Training Metrics 2025-08-31 05:13:46 - pico-train - INFO - ├── Loss: 4.8316 2025-08-31 05:13:46 - pico-train - INFO - ├── Learning Rate: 8.56e-05 2025-08-31 05:13:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:14:57 - pico-train - INFO - Step 55600 -- 🔄 Training Metrics 2025-08-31 05:14:57 - pico-train - INFO - ├── Loss: 4.8330 2025-08-31 05:14:57 - pico-train - INFO - ├── Learning Rate: 8.53e-05 2025-08-31 05:14:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:16:08 - pico-train - INFO - Step 55700 -- 🔄 Training Metrics 2025-08-31 05:16:08 - pico-train - INFO - ├── Loss: 4.8138 2025-08-31 05:16:08 - pico-train - INFO - ├── Learning Rate: 8.50e-05 2025-08-31 05:16:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:17:19 - pico-train - INFO - Step 55800 -- 🔄 Training Metrics 2025-08-31 05:17:19 - pico-train - INFO - ├── Loss: 4.8473 2025-08-31 05:17:19 - pico-train - INFO - ├── Learning Rate: 8.47e-05 2025-08-31 05:17:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:18:29 - pico-train - INFO - Step 55900 -- 🔄 Training Metrics 2025-08-31 05:18:29 - pico-train - INFO - ├── Loss: 4.8470 2025-08-31 05:18:29 - pico-train - INFO - ├── Learning Rate: 8.44e-05 2025-08-31 05:18:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:19:40 - pico-train - INFO - Step 56000 -- 💾 Saving Checkpoint 2025-08-31 05:21:41 - pico-train - INFO - Step 56000 -- 📊 Evaluation Results 2025-08-31 05:21:41 - pico-train - INFO - └── paloma: inf 2025-08-31 05:21:42 - pico-train - INFO - Step 56000 -- 🔄 Training Metrics 2025-08-31 05:21:42 - pico-train - INFO - ├── Loss: 4.8561 2025-08-31 05:21:42 - pico-train - INFO - ├── Learning Rate: 8.40e-05 2025-08-31 05:21:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:21:42 - pico-train - INFO - Step 56000 -- 📈 Saving Learning Dynamics 2025-08-31 05:22:56 - pico-train - INFO - Step 56100 -- 🔄 Training Metrics 2025-08-31 05:22:56 - pico-train - INFO - ├── Loss: 4.8491 2025-08-31 05:22:56 - pico-train - INFO - ├── Learning Rate: 8.37e-05 2025-08-31 05:22:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:24:07 - pico-train - INFO - Step 56200 -- 🔄 Training Metrics 2025-08-31 05:24:07 - pico-train - INFO - ├── Loss: 4.8458 2025-08-31 05:24:07 - pico-train - INFO - ├── Learning Rate: 8.34e-05 2025-08-31 05:24:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:25:18 - pico-train - INFO - Step 56300 -- 🔄 Training Metrics 2025-08-31 05:25:18 - pico-train - INFO - ├── Loss: 4.8346 2025-08-31 05:25:18 - pico-train - INFO - ├── Learning Rate: 8.31e-05 2025-08-31 05:25:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:26:30 - pico-train - INFO - Step 56400 -- 🔄 Training Metrics 2025-08-31 05:26:30 - pico-train - INFO - ├── Loss: 4.8510 2025-08-31 05:26:30 - pico-train - INFO - ├── Learning Rate: 8.28e-05 2025-08-31 05:26:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:27:41 - pico-train - INFO - Step 56500 -- 🔄 Training Metrics 2025-08-31 05:27:41 - pico-train - INFO - ├── Loss: 4.8172 2025-08-31 05:27:41 - pico-train - INFO - ├── Learning Rate: 8.25e-05 2025-08-31 05:27:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:28:52 - pico-train - INFO - Step 56600 -- 🔄 Training Metrics 2025-08-31 05:28:52 - pico-train - INFO - ├── Loss: 4.8297 2025-08-31 05:28:52 - pico-train - INFO - ├── Learning Rate: 8.21e-05 2025-08-31 05:28:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:30:03 - pico-train - INFO - Step 56700 -- 🔄 Training Metrics 2025-08-31 05:30:03 - pico-train - INFO - ├── Loss: 4.8400 2025-08-31 05:30:03 - pico-train - INFO - ├── Learning Rate: 8.18e-05 2025-08-31 05:30:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:31:14 - pico-train - INFO - Step 56800 -- 🔄 Training Metrics 2025-08-31 05:31:14 - pico-train - INFO - ├── Loss: 4.8370 2025-08-31 05:31:14 - pico-train - INFO - ├── Learning Rate: 8.15e-05 2025-08-31 05:31:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:32:25 - pico-train - INFO - Step 56900 -- 🔄 Training Metrics 2025-08-31 05:32:25 - pico-train - INFO - ├── Loss: 4.8458 2025-08-31 05:32:25 - pico-train - INFO - ├── Learning Rate: 8.12e-05 2025-08-31 05:32:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:33:35 - pico-train - INFO - Step 57000 -- 💾 Saving Checkpoint 2025-08-31 05:35:36 - pico-train - INFO - Step 57000 -- 📊 Evaluation Results 2025-08-31 05:35:36 - pico-train - INFO - └── paloma: inf 2025-08-31 05:35:37 - pico-train - INFO - Step 57000 -- 🔄 Training Metrics 2025-08-31 05:35:37 - pico-train - INFO - ├── Loss: 4.8467 2025-08-31 05:35:37 - pico-train - INFO - ├── Learning Rate: 8.09e-05 2025-08-31 05:35:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:35:37 - pico-train - INFO - Step 57000 -- 📈 Saving Learning Dynamics 2025-08-31 05:36:51 - pico-train - INFO - Step 57100 -- 🔄 Training Metrics 2025-08-31 05:36:51 - pico-train - INFO - ├── Loss: 4.8173 2025-08-31 05:36:51 - pico-train - INFO - ├── Learning Rate: 8.06e-05 2025-08-31 05:36:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:38:02 - pico-train - INFO - Step 57200 -- 🔄 Training Metrics 2025-08-31 05:38:02 - pico-train - INFO - ├── Loss: 4.8302 2025-08-31 05:38:02 - pico-train - INFO - ├── Learning Rate: 8.03e-05 2025-08-31 05:38:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:39:12 - pico-train - INFO - Step 57300 -- 🔄 Training Metrics 2025-08-31 05:39:12 - pico-train - INFO - ├── Loss: 4.8261 2025-08-31 05:39:12 - pico-train - INFO - ├── Learning Rate: 7.99e-05 2025-08-31 05:39:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:40:23 - pico-train - INFO - Step 57400 -- 🔄 Training Metrics 2025-08-31 05:40:23 - pico-train - INFO - ├── Loss: 4.8266 2025-08-31 05:40:23 - pico-train - INFO - ├── Learning Rate: 7.96e-05 2025-08-31 05:40:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:41:34 - pico-train - INFO - Step 57500 -- 🔄 Training Metrics 2025-08-31 05:41:34 - pico-train - INFO - ├── Loss: 4.8414 2025-08-31 05:41:34 - pico-train - INFO - ├── Learning Rate: 7.93e-05 2025-08-31 05:41:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:42:46 - pico-train - INFO - Step 57600 -- 🔄 Training Metrics 2025-08-31 05:42:46 - pico-train - INFO - ├── Loss: 4.8351 2025-08-31 05:42:46 - pico-train - INFO - ├── Learning Rate: 7.90e-05 2025-08-31 05:42:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:43:57 - pico-train - INFO - Step 57700 -- 🔄 Training Metrics 2025-08-31 05:43:57 - pico-train - INFO - ├── Loss: 4.8598 2025-08-31 05:43:57 - pico-train - INFO - ├── Learning Rate: 7.87e-05 2025-08-31 05:43:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:45:08 - pico-train - INFO - Step 57800 -- 🔄 Training Metrics 2025-08-31 05:45:08 - pico-train - INFO - ├── Loss: 4.8310 2025-08-31 05:45:08 - pico-train - INFO - ├── Learning Rate: 7.84e-05 2025-08-31 05:45:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:46:19 - pico-train - INFO - Step 57900 -- 🔄 Training Metrics 2025-08-31 05:46:19 - pico-train - INFO - ├── Loss: 4.8333 2025-08-31 05:46:19 - pico-train - INFO - ├── Learning Rate: 7.81e-05 2025-08-31 05:46:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:47:29 - pico-train - INFO - Step 58000 -- 💾 Saving Checkpoint 2025-08-31 05:49:31 - pico-train - INFO - Step 58000 -- 📊 Evaluation Results 2025-08-31 05:49:31 - pico-train - INFO - └── paloma: inf 2025-08-31 05:49:31 - pico-train - INFO - Step 58000 -- 🔄 Training Metrics 2025-08-31 05:49:31 - pico-train - INFO - ├── Loss: 4.8291 2025-08-31 05:49:31 - pico-train - INFO - ├── Learning Rate: 7.77e-05 2025-08-31 05:49:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:49:31 - pico-train - INFO - Step 58000 -- 📈 Saving Learning Dynamics 2025-08-31 05:50:45 - pico-train - INFO - Step 58100 -- 🔄 Training Metrics 2025-08-31 05:50:45 - pico-train - INFO - ├── Loss: 4.8302 2025-08-31 05:50:45 - pico-train - INFO - ├── Learning Rate: 7.74e-05 2025-08-31 05:50:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:51:56 - pico-train - INFO - Step 58200 -- 🔄 Training Metrics 2025-08-31 05:51:56 - pico-train - INFO - ├── Loss: 4.8194 2025-08-31 05:51:56 - pico-train - INFO - ├── Learning Rate: 7.71e-05 2025-08-31 05:51:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:53:07 - pico-train - INFO - Step 58300 -- 🔄 Training Metrics 2025-08-31 05:53:07 - pico-train - INFO - ├── Loss: 4.8363 2025-08-31 05:53:07 - pico-train - INFO - ├── Learning Rate: 7.68e-05 2025-08-31 05:53:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:54:18 - pico-train - INFO - Step 58400 -- 🔄 Training Metrics 2025-08-31 05:54:18 - pico-train - INFO - ├── Loss: 4.8375 2025-08-31 05:54:18 - pico-train - INFO - ├── Learning Rate: 7.65e-05 2025-08-31 05:54:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:55:29 - pico-train - INFO - Step 58500 -- 🔄 Training Metrics 2025-08-31 05:55:29 - pico-train - INFO - ├── Loss: 4.8184 2025-08-31 05:55:29 - pico-train - INFO - ├── Learning Rate: 7.62e-05 2025-08-31 05:55:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:56:40 - pico-train - INFO - Step 58600 -- 🔄 Training Metrics 2025-08-31 05:56:40 - pico-train - INFO - ├── Loss: 4.8258 2025-08-31 05:56:40 - pico-train - INFO - ├── Learning Rate: 7.59e-05 2025-08-31 05:56:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:57:51 - pico-train - INFO - Step 58700 -- 🔄 Training Metrics 2025-08-31 05:57:51 - pico-train - INFO - ├── Loss: 4.8396 2025-08-31 05:57:51 - pico-train - INFO - ├── Learning Rate: 7.56e-05 2025-08-31 05:57:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 05:59:02 - pico-train - INFO - Step 58800 -- 🔄 Training Metrics 2025-08-31 05:59:02 - pico-train - INFO - ├── Loss: 4.8104 2025-08-31 05:59:02 - pico-train - INFO - ├── Learning Rate: 7.53e-05 2025-08-31 05:59:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:00:13 - pico-train - INFO - Step 58900 -- 🔄 Training Metrics 2025-08-31 06:00:13 - pico-train - INFO - ├── Loss: 4.8457 2025-08-31 06:00:13 - pico-train - INFO - ├── Learning Rate: 7.49e-05 2025-08-31 06:00:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:01:23 - pico-train - INFO - Step 59000 -- 💾 Saving Checkpoint 2025-08-31 06:03:25 - pico-train - INFO - Step 59000 -- 📊 Evaluation Results 2025-08-31 06:03:25 - pico-train - INFO - └── paloma: inf 2025-08-31 06:03:26 - pico-train - INFO - Step 59000 -- 🔄 Training Metrics 2025-08-31 06:03:26 - pico-train - INFO - ├── Loss: 4.8381 2025-08-31 06:03:26 - pico-train - INFO - ├── Learning Rate: 7.46e-05 2025-08-31 06:03:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:03:26 - pico-train - INFO - Step 59000 -- 📈 Saving Learning Dynamics 2025-08-31 06:04:40 - pico-train - INFO - Step 59100 -- 🔄 Training Metrics 2025-08-31 06:04:40 - pico-train - INFO - ├── Loss: 4.8267 2025-08-31 06:04:40 - pico-train - INFO - ├── Learning Rate: 7.43e-05 2025-08-31 06:04:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:05:50 - pico-train - INFO - Step 59200 -- 🔄 Training Metrics 2025-08-31 06:05:50 - pico-train - INFO - ├── Loss: 4.8410 2025-08-31 06:05:50 - pico-train - INFO - ├── Learning Rate: 7.40e-05 2025-08-31 06:05:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:07:01 - pico-train - INFO - Step 59300 -- 🔄 Training Metrics 2025-08-31 06:07:01 - pico-train - INFO - ├── Loss: 4.8489 2025-08-31 06:07:01 - pico-train - INFO - ├── Learning Rate: 7.37e-05 2025-08-31 06:07:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:08:13 - pico-train - INFO - Step 59400 -- 🔄 Training Metrics 2025-08-31 06:08:13 - pico-train - INFO - ├── Loss: 4.8226 2025-08-31 06:08:13 - pico-train - INFO - ├── Learning Rate: 7.34e-05 2025-08-31 06:08:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:09:23 - pico-train - INFO - Step 59500 -- 🔄 Training Metrics 2025-08-31 06:09:23 - pico-train - INFO - ├── Loss: 4.8042 2025-08-31 06:09:23 - pico-train - INFO - ├── Learning Rate: 7.31e-05 2025-08-31 06:09:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:10:35 - pico-train - INFO - Step 59600 -- 🔄 Training Metrics 2025-08-31 06:10:35 - pico-train - INFO - ├── Loss: 4.8441 2025-08-31 06:10:35 - pico-train - INFO - ├── Learning Rate: 7.28e-05 2025-08-31 06:10:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:11:46 - pico-train - INFO - Step 59700 -- 🔄 Training Metrics 2025-08-31 06:11:46 - pico-train - INFO - ├── Loss: 4.8589 2025-08-31 06:11:46 - pico-train - INFO - ├── Learning Rate: 7.25e-05 2025-08-31 06:11:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:12:57 - pico-train - INFO - Step 59800 -- 🔄 Training Metrics 2025-08-31 06:12:57 - pico-train - INFO - ├── Loss: 4.8339 2025-08-31 06:12:57 - pico-train - INFO - ├── Learning Rate: 7.22e-05 2025-08-31 06:12:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:14:08 - pico-train - INFO - Step 59900 -- 🔄 Training Metrics 2025-08-31 06:14:08 - pico-train - INFO - ├── Loss: 4.8215 2025-08-31 06:14:08 - pico-train - INFO - ├── Learning Rate: 7.19e-05 2025-08-31 06:14:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:15:18 - pico-train - INFO - Step 60000 -- 💾 Saving Checkpoint 2025-08-31 06:17:20 - pico-train - INFO - Step 60000 -- 📊 Evaluation Results 2025-08-31 06:17:20 - pico-train - INFO - └── paloma: inf 2025-08-31 06:17:21 - pico-train - INFO - Step 60000 -- 🔄 Training Metrics 2025-08-31 06:17:21 - pico-train - INFO - ├── Loss: 4.8345 2025-08-31 06:17:21 - pico-train - INFO - ├── Learning Rate: 7.15e-05 2025-08-31 06:17:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:17:21 - pico-train - INFO - Step 60000 -- 📈 Saving Learning Dynamics 2025-08-31 06:18:34 - pico-train - INFO - Step 60100 -- 🔄 Training Metrics 2025-08-31 06:18:34 - pico-train - INFO - ├── Loss: 4.8207 2025-08-31 06:18:34 - pico-train - INFO - ├── Learning Rate: 7.12e-05 2025-08-31 06:18:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:19:46 - pico-train - INFO - Step 60200 -- 🔄 Training Metrics 2025-08-31 06:19:46 - pico-train - INFO - ├── Loss: 4.8181 2025-08-31 06:19:46 - pico-train - INFO - ├── Learning Rate: 7.09e-05 2025-08-31 06:19:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:20:57 - pico-train - INFO - Step 60300 -- 🔄 Training Metrics 2025-08-31 06:20:57 - pico-train - INFO - ├── Loss: 4.8059 2025-08-31 06:20:57 - pico-train - INFO - ├── Learning Rate: 7.06e-05 2025-08-31 06:20:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:22:08 - pico-train - INFO - Step 60400 -- 🔄 Training Metrics 2025-08-31 06:22:08 - pico-train - INFO - ├── Loss: 4.8367 2025-08-31 06:22:08 - pico-train - INFO - ├── Learning Rate: 7.03e-05 2025-08-31 06:22:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:23:19 - pico-train - INFO - Step 60500 -- 🔄 Training Metrics 2025-08-31 06:23:19 - pico-train - INFO - ├── Loss: 4.8237 2025-08-31 06:23:19 - pico-train - INFO - ├── Learning Rate: 7.00e-05 2025-08-31 06:23:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:24:31 - pico-train - INFO - Step 60600 -- 🔄 Training Metrics 2025-08-31 06:24:31 - pico-train - INFO - ├── Loss: 4.8291 2025-08-31 06:24:31 - pico-train - INFO - ├── Learning Rate: 6.97e-05 2025-08-31 06:24:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:25:42 - pico-train - INFO - Step 60700 -- 🔄 Training Metrics 2025-08-31 06:25:42 - pico-train - INFO - ├── Loss: 4.8317 2025-08-31 06:25:42 - pico-train - INFO - ├── Learning Rate: 6.94e-05 2025-08-31 06:25:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:26:53 - pico-train - INFO - Step 60800 -- 🔄 Training Metrics 2025-08-31 06:26:53 - pico-train - INFO - ├── Loss: 4.8204 2025-08-31 06:26:53 - pico-train - INFO - ├── Learning Rate: 6.91e-05 2025-08-31 06:26:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:28:03 - pico-train - INFO - Step 60900 -- 🔄 Training Metrics 2025-08-31 06:28:03 - pico-train - INFO - ├── Loss: 4.8455 2025-08-31 06:28:03 - pico-train - INFO - ├── Learning Rate: 6.88e-05 2025-08-31 06:28:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:29:14 - pico-train - INFO - Step 61000 -- 💾 Saving Checkpoint 2025-08-31 06:31:15 - pico-train - INFO - Step 61000 -- 📊 Evaluation Results 2025-08-31 06:31:15 - pico-train - INFO - └── paloma: inf 2025-08-31 06:31:16 - pico-train - INFO - Step 61000 -- 🔄 Training Metrics 2025-08-31 06:31:16 - pico-train - INFO - ├── Loss: 4.8133 2025-08-31 06:31:16 - pico-train - INFO - ├── Learning Rate: 6.85e-05 2025-08-31 06:31:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:31:16 - pico-train - INFO - Step 61000 -- 📈 Saving Learning Dynamics 2025-08-31 06:32:30 - pico-train - INFO - Step 61100 -- 🔄 Training Metrics 2025-08-31 06:32:30 - pico-train - INFO - ├── Loss: 4.8156 2025-08-31 06:32:30 - pico-train - INFO - ├── Learning Rate: 6.82e-05 2025-08-31 06:32:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:33:41 - pico-train - INFO - Step 61200 -- 🔄 Training Metrics 2025-08-31 06:33:41 - pico-train - INFO - ├── Loss: 4.8153 2025-08-31 06:33:41 - pico-train - INFO - ├── Learning Rate: 6.79e-05 2025-08-31 06:33:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:34:53 - pico-train - INFO - Step 61300 -- 🔄 Training Metrics 2025-08-31 06:34:53 - pico-train - INFO - ├── Loss: 4.8111 2025-08-31 06:34:53 - pico-train - INFO - ├── Learning Rate: 6.76e-05 2025-08-31 06:34:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:36:03 - pico-train - INFO - Step 61400 -- 🔄 Training Metrics 2025-08-31 06:36:03 - pico-train - INFO - ├── Loss: 4.8220 2025-08-31 06:36:03 - pico-train - INFO - ├── Learning Rate: 6.73e-05 2025-08-31 06:36:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:37:15 - pico-train - INFO - Step 61500 -- 🔄 Training Metrics 2025-08-31 06:37:15 - pico-train - INFO - ├── Loss: 4.8183 2025-08-31 06:37:15 - pico-train - INFO - ├── Learning Rate: 6.70e-05 2025-08-31 06:37:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:38:26 - pico-train - INFO - Step 61600 -- 🔄 Training Metrics 2025-08-31 06:38:26 - pico-train - INFO - ├── Loss: 4.8133 2025-08-31 06:38:26 - pico-train - INFO - ├── Learning Rate: 6.67e-05 2025-08-31 06:38:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:39:37 - pico-train - INFO - Step 61700 -- 🔄 Training Metrics 2025-08-31 06:39:37 - pico-train - INFO - ├── Loss: 4.8243 2025-08-31 06:39:37 - pico-train - INFO - ├── Learning Rate: 6.64e-05 2025-08-31 06:39:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:40:48 - pico-train - INFO - Step 61800 -- 🔄 Training Metrics 2025-08-31 06:40:48 - pico-train - INFO - ├── Loss: 4.8117 2025-08-31 06:40:48 - pico-train - INFO - ├── Learning Rate: 6.61e-05 2025-08-31 06:40:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:41:58 - pico-train - INFO - Step 61900 -- 🔄 Training Metrics 2025-08-31 06:41:58 - pico-train - INFO - ├── Loss: 4.8329 2025-08-31 06:41:58 - pico-train - INFO - ├── Learning Rate: 6.58e-05 2025-08-31 06:41:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:43:09 - pico-train - INFO - Step 62000 -- 💾 Saving Checkpoint 2025-08-31 06:45:10 - pico-train - INFO - Step 62000 -- 📊 Evaluation Results 2025-08-31 06:45:10 - pico-train - INFO - └── paloma: inf 2025-08-31 06:45:11 - pico-train - INFO - Step 62000 -- 🔄 Training Metrics 2025-08-31 06:45:11 - pico-train - INFO - ├── Loss: 4.8042 2025-08-31 06:45:11 - pico-train - INFO - ├── Learning Rate: 6.55e-05 2025-08-31 06:45:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:45:11 - pico-train - INFO - Step 62000 -- 📈 Saving Learning Dynamics 2025-08-31 06:46:26 - pico-train - INFO - Step 62100 -- 🔄 Training Metrics 2025-08-31 06:46:26 - pico-train - INFO - ├── Loss: 4.8256 2025-08-31 06:46:26 - pico-train - INFO - ├── Learning Rate: 6.52e-05 2025-08-31 06:46:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:47:37 - pico-train - INFO - Step 62200 -- 🔄 Training Metrics 2025-08-31 06:47:37 - pico-train - INFO - ├── Loss: 4.8248 2025-08-31 06:47:37 - pico-train - INFO - ├── Learning Rate: 6.49e-05 2025-08-31 06:47:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:48:47 - pico-train - INFO - Step 62300 -- 🔄 Training Metrics 2025-08-31 06:48:47 - pico-train - INFO - ├── Loss: 4.8133 2025-08-31 06:48:47 - pico-train - INFO - ├── Learning Rate: 6.46e-05 2025-08-31 06:48:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:49:58 - pico-train - INFO - Step 62400 -- 🔄 Training Metrics 2025-08-31 06:49:58 - pico-train - INFO - ├── Loss: 4.8239 2025-08-31 06:49:58 - pico-train - INFO - ├── Learning Rate: 6.43e-05 2025-08-31 06:49:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:51:09 - pico-train - INFO - Step 62500 -- 🔄 Training Metrics 2025-08-31 06:51:09 - pico-train - INFO - ├── Loss: 4.8295 2025-08-31 06:51:09 - pico-train - INFO - ├── Learning Rate: 6.40e-05 2025-08-31 06:51:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:52:20 - pico-train - INFO - Step 62600 -- 🔄 Training Metrics 2025-08-31 06:52:20 - pico-train - INFO - ├── Loss: 4.8202 2025-08-31 06:52:20 - pico-train - INFO - ├── Learning Rate: 6.37e-05 2025-08-31 06:52:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:53:32 - pico-train - INFO - Step 62700 -- 🔄 Training Metrics 2025-08-31 06:53:32 - pico-train - INFO - ├── Loss: 4.7956 2025-08-31 06:53:32 - pico-train - INFO - ├── Learning Rate: 6.34e-05 2025-08-31 06:53:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:54:43 - pico-train - INFO - Step 62800 -- 🔄 Training Metrics 2025-08-31 06:54:43 - pico-train - INFO - ├── Loss: 4.8361 2025-08-31 06:54:43 - pico-train - INFO - ├── Learning Rate: 6.31e-05 2025-08-31 06:54:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:55:54 - pico-train - INFO - Step 62900 -- 🔄 Training Metrics 2025-08-31 06:55:54 - pico-train - INFO - ├── Loss: 4.8381 2025-08-31 06:55:54 - pico-train - INFO - ├── Learning Rate: 6.28e-05 2025-08-31 06:55:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:57:05 - pico-train - INFO - Step 63000 -- 💾 Saving Checkpoint 2025-08-31 06:59:06 - pico-train - INFO - Step 63000 -- 📊 Evaluation Results 2025-08-31 06:59:06 - pico-train - INFO - └── paloma: inf 2025-08-31 06:59:07 - pico-train - INFO - Step 63000 -- 🔄 Training Metrics 2025-08-31 06:59:07 - pico-train - INFO - ├── Loss: 4.8256 2025-08-31 06:59:07 - pico-train - INFO - ├── Learning Rate: 6.25e-05 2025-08-31 06:59:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 06:59:07 - pico-train - INFO - Step 63000 -- 📈 Saving Learning Dynamics 2025-08-31 07:00:20 - pico-train - INFO - Step 63100 -- 🔄 Training Metrics 2025-08-31 07:00:20 - pico-train - INFO - ├── Loss: 4.8417 2025-08-31 07:00:20 - pico-train - INFO - ├── Learning Rate: 6.22e-05 2025-08-31 07:00:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:01:31 - pico-train - INFO - Step 63200 -- 🔄 Training Metrics 2025-08-31 07:01:31 - pico-train - INFO - ├── Loss: 4.8099 2025-08-31 07:01:31 - pico-train - INFO - ├── Learning Rate: 6.19e-05 2025-08-31 07:01:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:02:42 - pico-train - INFO - Step 63300 -- 🔄 Training Metrics 2025-08-31 07:02:42 - pico-train - INFO - ├── Loss: 4.8293 2025-08-31 07:02:42 - pico-train - INFO - ├── Learning Rate: 6.16e-05 2025-08-31 07:02:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:03:53 - pico-train - INFO - Step 63400 -- 🔄 Training Metrics 2025-08-31 07:03:53 - pico-train - INFO - ├── Loss: 4.8126 2025-08-31 07:03:53 - pico-train - INFO - ├── Learning Rate: 6.13e-05 2025-08-31 07:03:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:05:04 - pico-train - INFO - Step 63500 -- 🔄 Training Metrics 2025-08-31 07:05:04 - pico-train - INFO - ├── Loss: 4.8183 2025-08-31 07:05:04 - pico-train - INFO - ├── Learning Rate: 6.10e-05 2025-08-31 07:05:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:06:15 - pico-train - INFO - Step 63600 -- 🔄 Training Metrics 2025-08-31 07:06:15 - pico-train - INFO - ├── Loss: 4.8345 2025-08-31 07:06:15 - pico-train - INFO - ├── Learning Rate: 6.07e-05 2025-08-31 07:06:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:07:26 - pico-train - INFO - Step 63700 -- 🔄 Training Metrics 2025-08-31 07:07:26 - pico-train - INFO - ├── Loss: 4.8124 2025-08-31 07:07:26 - pico-train - INFO - ├── Learning Rate: 6.04e-05 2025-08-31 07:07:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:08:39 - pico-train - INFO - Step 63800 -- 🔄 Training Metrics 2025-08-31 07:08:39 - pico-train - INFO - ├── Loss: 4.8222 2025-08-31 07:08:39 - pico-train - INFO - ├── Learning Rate: 6.01e-05 2025-08-31 07:08:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:09:50 - pico-train - INFO - Step 63900 -- 🔄 Training Metrics 2025-08-31 07:09:50 - pico-train - INFO - ├── Loss: 4.8265 2025-08-31 07:09:50 - pico-train - INFO - ├── Learning Rate: 5.98e-05 2025-08-31 07:09:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:11:00 - pico-train - INFO - Step 64000 -- 💾 Saving Checkpoint 2025-08-31 07:13:02 - pico-train - INFO - Step 64000 -- 📊 Evaluation Results 2025-08-31 07:13:02 - pico-train - INFO - └── paloma: inf 2025-08-31 07:13:04 - pico-train - INFO - Step 64000 -- 🔄 Training Metrics 2025-08-31 07:13:04 - pico-train - INFO - ├── Loss: 4.7990 2025-08-31 07:13:04 - pico-train - INFO - ├── Learning Rate: 5.95e-05 2025-08-31 07:13:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:13:04 - pico-train - INFO - Step 64000 -- 📈 Saving Learning Dynamics 2025-08-31 07:14:17 - pico-train - INFO - Step 64100 -- 🔄 Training Metrics 2025-08-31 07:14:17 - pico-train - INFO - ├── Loss: 4.8111 2025-08-31 07:14:17 - pico-train - INFO - ├── Learning Rate: 5.92e-05 2025-08-31 07:14:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:15:28 - pico-train - INFO - Step 64200 -- 🔄 Training Metrics 2025-08-31 07:15:28 - pico-train - INFO - ├── Loss: 4.7969 2025-08-31 07:15:28 - pico-train - INFO - ├── Learning Rate: 5.89e-05 2025-08-31 07:15:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:16:39 - pico-train - INFO - Step 64300 -- 🔄 Training Metrics 2025-08-31 07:16:39 - pico-train - INFO - ├── Loss: 4.8199 2025-08-31 07:16:39 - pico-train - INFO - ├── Learning Rate: 5.86e-05 2025-08-31 07:16:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:17:50 - pico-train - INFO - Step 64400 -- 🔄 Training Metrics 2025-08-31 07:17:50 - pico-train - INFO - ├── Loss: 4.8352 2025-08-31 07:17:50 - pico-train - INFO - ├── Learning Rate: 5.84e-05 2025-08-31 07:17:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:19:01 - pico-train - INFO - Step 64500 -- 🔄 Training Metrics 2025-08-31 07:19:01 - pico-train - INFO - ├── Loss: 4.8160 2025-08-31 07:19:01 - pico-train - INFO - ├── Learning Rate: 5.81e-05 2025-08-31 07:19:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:20:12 - pico-train - INFO - Step 64600 -- 🔄 Training Metrics 2025-08-31 07:20:12 - pico-train - INFO - ├── Loss: 4.8396 2025-08-31 07:20:12 - pico-train - INFO - ├── Learning Rate: 5.78e-05 2025-08-31 07:20:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:21:23 - pico-train - INFO - Step 64700 -- 🔄 Training Metrics 2025-08-31 07:21:23 - pico-train - INFO - ├── Loss: 4.8071 2025-08-31 07:21:23 - pico-train - INFO - ├── Learning Rate: 5.75e-05 2025-08-31 07:21:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:22:34 - pico-train - INFO - Step 64800 -- 🔄 Training Metrics 2025-08-31 07:22:34 - pico-train - INFO - ├── Loss: 4.8250 2025-08-31 07:22:34 - pico-train - INFO - ├── Learning Rate: 5.72e-05 2025-08-31 07:22:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:23:45 - pico-train - INFO - Step 64900 -- 🔄 Training Metrics 2025-08-31 07:23:45 - pico-train - INFO - ├── Loss: 4.8292 2025-08-31 07:23:45 - pico-train - INFO - ├── Learning Rate: 5.69e-05 2025-08-31 07:23:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:24:55 - pico-train - INFO - Step 65000 -- 💾 Saving Checkpoint 2025-08-31 07:26:57 - pico-train - INFO - Step 65000 -- 📊 Evaluation Results 2025-08-31 07:26:57 - pico-train - INFO - └── paloma: inf 2025-08-31 07:26:58 - pico-train - INFO - Step 65000 -- 🔄 Training Metrics 2025-08-31 07:26:58 - pico-train - INFO - ├── Loss: 4.8135 2025-08-31 07:26:58 - pico-train - INFO - ├── Learning Rate: 5.66e-05 2025-08-31 07:26:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:26:58 - pico-train - INFO - Step 65000 -- 📈 Saving Learning Dynamics 2025-08-31 07:28:12 - pico-train - INFO - Step 65100 -- 🔄 Training Metrics 2025-08-31 07:28:12 - pico-train - INFO - ├── Loss: 4.7973 2025-08-31 07:28:12 - pico-train - INFO - ├── Learning Rate: 5.63e-05 2025-08-31 07:28:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:29:23 - pico-train - INFO - Step 65200 -- 🔄 Training Metrics 2025-08-31 07:29:23 - pico-train - INFO - ├── Loss: 4.7910 2025-08-31 07:29:23 - pico-train - INFO - ├── Learning Rate: 5.60e-05 2025-08-31 07:29:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:30:35 - pico-train - INFO - Step 65300 -- 🔄 Training Metrics 2025-08-31 07:30:35 - pico-train - INFO - ├── Loss: 4.8193 2025-08-31 07:30:35 - pico-train - INFO - ├── Learning Rate: 5.57e-05 2025-08-31 07:30:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:31:45 - pico-train - INFO - Step 65400 -- 🔄 Training Metrics 2025-08-31 07:31:45 - pico-train - INFO - ├── Loss: 4.8241 2025-08-31 07:31:45 - pico-train - INFO - ├── Learning Rate: 5.55e-05 2025-08-31 07:31:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:32:57 - pico-train - INFO - Step 65500 -- 🔄 Training Metrics 2025-08-31 07:32:57 - pico-train - INFO - ├── Loss: 4.8292 2025-08-31 07:32:57 - pico-train - INFO - ├── Learning Rate: 5.52e-05 2025-08-31 07:32:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:34:08 - pico-train - INFO - Step 65600 -- 🔄 Training Metrics 2025-08-31 07:34:08 - pico-train - INFO - ├── Loss: 4.8186 2025-08-31 07:34:08 - pico-train - INFO - ├── Learning Rate: 5.49e-05 2025-08-31 07:34:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:35:19 - pico-train - INFO - Step 65700 -- 🔄 Training Metrics 2025-08-31 07:35:19 - pico-train - INFO - ├── Loss: 4.8085 2025-08-31 07:35:19 - pico-train - INFO - ├── Learning Rate: 5.46e-05 2025-08-31 07:35:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:36:30 - pico-train - INFO - Step 65800 -- 🔄 Training Metrics 2025-08-31 07:36:30 - pico-train - INFO - ├── Loss: 4.8058 2025-08-31 07:36:30 - pico-train - INFO - ├── Learning Rate: 5.43e-05 2025-08-31 07:36:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:37:41 - pico-train - INFO - Step 65900 -- 🔄 Training Metrics 2025-08-31 07:37:41 - pico-train - INFO - ├── Loss: 4.7922 2025-08-31 07:37:41 - pico-train - INFO - ├── Learning Rate: 5.40e-05 2025-08-31 07:37:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:38:51 - pico-train - INFO - Step 66000 -- 💾 Saving Checkpoint 2025-08-31 07:40:53 - pico-train - INFO - Step 66000 -- 📊 Evaluation Results 2025-08-31 07:40:53 - pico-train - INFO - └── paloma: inf 2025-08-31 07:40:53 - pico-train - INFO - Step 66000 -- 🔄 Training Metrics 2025-08-31 07:40:53 - pico-train - INFO - ├── Loss: 4.8014 2025-08-31 07:40:53 - pico-train - INFO - ├── Learning Rate: 5.37e-05 2025-08-31 07:40:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:40:53 - pico-train - INFO - Step 66000 -- 📈 Saving Learning Dynamics 2025-08-31 07:42:07 - pico-train - INFO - Step 66100 -- 🔄 Training Metrics 2025-08-31 07:42:07 - pico-train - INFO - ├── Loss: 4.8063 2025-08-31 07:42:07 - pico-train - INFO - ├── Learning Rate: 5.35e-05 2025-08-31 07:42:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:43:18 - pico-train - INFO - Step 66200 -- 🔄 Training Metrics 2025-08-31 07:43:18 - pico-train - INFO - ├── Loss: 4.8139 2025-08-31 07:43:18 - pico-train - INFO - ├── Learning Rate: 5.32e-05 2025-08-31 07:43:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:44:30 - pico-train - INFO - Step 66300 -- 🔄 Training Metrics 2025-08-31 07:44:30 - pico-train - INFO - ├── Loss: 4.8191 2025-08-31 07:44:30 - pico-train - INFO - ├── Learning Rate: 5.29e-05 2025-08-31 07:44:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:45:40 - pico-train - INFO - Step 66400 -- 🔄 Training Metrics 2025-08-31 07:45:40 - pico-train - INFO - ├── Loss: 4.7988 2025-08-31 07:45:40 - pico-train - INFO - ├── Learning Rate: 5.26e-05 2025-08-31 07:45:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:46:52 - pico-train - INFO - Step 66500 -- 🔄 Training Metrics 2025-08-31 07:46:52 - pico-train - INFO - ├── Loss: 4.7927 2025-08-31 07:46:52 - pico-train - INFO - ├── Learning Rate: 5.23e-05 2025-08-31 07:46:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:48:04 - pico-train - INFO - Step 66600 -- 🔄 Training Metrics 2025-08-31 07:48:04 - pico-train - INFO - ├── Loss: 4.8113 2025-08-31 07:48:04 - pico-train - INFO - ├── Learning Rate: 5.20e-05 2025-08-31 07:48:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:49:15 - pico-train - INFO - Step 66700 -- 🔄 Training Metrics 2025-08-31 07:49:15 - pico-train - INFO - ├── Loss: 4.7948 2025-08-31 07:49:15 - pico-train - INFO - ├── Learning Rate: 5.18e-05 2025-08-31 07:49:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:50:25 - pico-train - INFO - Step 66800 -- 🔄 Training Metrics 2025-08-31 07:50:25 - pico-train - INFO - ├── Loss: 4.8223 2025-08-31 07:50:25 - pico-train - INFO - ├── Learning Rate: 5.15e-05 2025-08-31 07:50:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:51:37 - pico-train - INFO - Step 66900 -- 🔄 Training Metrics 2025-08-31 07:51:37 - pico-train - INFO - ├── Loss: 4.7917 2025-08-31 07:51:37 - pico-train - INFO - ├── Learning Rate: 5.12e-05 2025-08-31 07:51:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:52:47 - pico-train - INFO - Step 67000 -- 💾 Saving Checkpoint 2025-08-31 07:54:49 - pico-train - INFO - Step 67000 -- 📊 Evaluation Results 2025-08-31 07:54:49 - pico-train - INFO - └── paloma: inf 2025-08-31 07:54:50 - pico-train - INFO - Step 67000 -- 🔄 Training Metrics 2025-08-31 07:54:50 - pico-train - INFO - ├── Loss: 4.8179 2025-08-31 07:54:50 - pico-train - INFO - ├── Learning Rate: 5.09e-05 2025-08-31 07:54:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:54:50 - pico-train - INFO - Step 67000 -- 📈 Saving Learning Dynamics 2025-08-31 07:56:03 - pico-train - INFO - Step 67100 -- 🔄 Training Metrics 2025-08-31 07:56:03 - pico-train - INFO - ├── Loss: 4.8136 2025-08-31 07:56:03 - pico-train - INFO - ├── Learning Rate: 5.06e-05 2025-08-31 07:56:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:57:14 - pico-train - INFO - Step 67200 -- 🔄 Training Metrics 2025-08-31 07:57:14 - pico-train - INFO - ├── Loss: 4.7937 2025-08-31 07:57:14 - pico-train - INFO - ├── Learning Rate: 5.04e-05 2025-08-31 07:57:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:58:25 - pico-train - INFO - Step 67300 -- 🔄 Training Metrics 2025-08-31 07:58:25 - pico-train - INFO - ├── Loss: 4.7952 2025-08-31 07:58:25 - pico-train - INFO - ├── Learning Rate: 5.01e-05 2025-08-31 07:58:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 07:59:36 - pico-train - INFO - Step 67400 -- 🔄 Training Metrics 2025-08-31 07:59:36 - pico-train - INFO - ├── Loss: 4.7929 2025-08-31 07:59:36 - pico-train - INFO - ├── Learning Rate: 4.98e-05 2025-08-31 07:59:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:00:47 - pico-train - INFO - Step 67500 -- 🔄 Training Metrics 2025-08-31 08:00:47 - pico-train - INFO - ├── Loss: 4.8137 2025-08-31 08:00:47 - pico-train - INFO - ├── Learning Rate: 4.95e-05 2025-08-31 08:00:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:01:58 - pico-train - INFO - Step 67600 -- 🔄 Training Metrics 2025-08-31 08:01:58 - pico-train - INFO - ├── Loss: 4.7972 2025-08-31 08:01:58 - pico-train - INFO - ├── Learning Rate: 4.93e-05 2025-08-31 08:01:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:03:10 - pico-train - INFO - Step 67700 -- 🔄 Training Metrics 2025-08-31 08:03:10 - pico-train - INFO - ├── Loss: 4.8047 2025-08-31 08:03:10 - pico-train - INFO - ├── Learning Rate: 4.90e-05 2025-08-31 08:03:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:04:20 - pico-train - INFO - Step 67800 -- 🔄 Training Metrics 2025-08-31 08:04:20 - pico-train - INFO - ├── Loss: 4.8156 2025-08-31 08:04:20 - pico-train - INFO - ├── Learning Rate: 4.87e-05 2025-08-31 08:04:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:05:32 - pico-train - INFO - Step 67900 -- 🔄 Training Metrics 2025-08-31 08:05:32 - pico-train - INFO - ├── Loss: 4.7833 2025-08-31 08:05:32 - pico-train - INFO - ├── Learning Rate: 4.84e-05 2025-08-31 08:05:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:06:43 - pico-train - INFO - Step 68000 -- 💾 Saving Checkpoint 2025-08-31 08:08:45 - pico-train - INFO - Step 68000 -- 📊 Evaluation Results 2025-08-31 08:08:45 - pico-train - INFO - └── paloma: inf 2025-08-31 08:08:45 - pico-train - INFO - Step 68000 -- 🔄 Training Metrics 2025-08-31 08:08:45 - pico-train - INFO - ├── Loss: 4.8150 2025-08-31 08:08:45 - pico-train - INFO - ├── Learning Rate: 4.82e-05 2025-08-31 08:08:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:08:45 - pico-train - INFO - Step 68000 -- 📈 Saving Learning Dynamics 2025-08-31 08:09:59 - pico-train - INFO - Step 68100 -- 🔄 Training Metrics 2025-08-31 08:09:59 - pico-train - INFO - ├── Loss: 4.8111 2025-08-31 08:09:59 - pico-train - INFO - ├── Learning Rate: 4.79e-05 2025-08-31 08:09:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:11:10 - pico-train - INFO - Step 68200 -- 🔄 Training Metrics 2025-08-31 08:11:10 - pico-train - INFO - ├── Loss: 4.8168 2025-08-31 08:11:10 - pico-train - INFO - ├── Learning Rate: 4.76e-05 2025-08-31 08:11:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:12:21 - pico-train - INFO - Step 68300 -- 🔄 Training Metrics 2025-08-31 08:12:21 - pico-train - INFO - ├── Loss: 4.8166 2025-08-31 08:12:21 - pico-train - INFO - ├── Learning Rate: 4.73e-05 2025-08-31 08:12:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:13:32 - pico-train - INFO - Step 68400 -- 🔄 Training Metrics 2025-08-31 08:13:32 - pico-train - INFO - ├── Loss: 4.8310 2025-08-31 08:13:32 - pico-train - INFO - ├── Learning Rate: 4.71e-05 2025-08-31 08:13:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:14:44 - pico-train - INFO - Step 68500 -- 🔄 Training Metrics 2025-08-31 08:14:44 - pico-train - INFO - ├── Loss: 4.8159 2025-08-31 08:14:44 - pico-train - INFO - ├── Learning Rate: 4.68e-05 2025-08-31 08:14:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:15:55 - pico-train - INFO - Step 68600 -- 🔄 Training Metrics 2025-08-31 08:15:55 - pico-train - INFO - ├── Loss: 4.7912 2025-08-31 08:15:55 - pico-train - INFO - ├── Learning Rate: 4.65e-05 2025-08-31 08:15:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:17:05 - pico-train - INFO - Step 68700 -- 🔄 Training Metrics 2025-08-31 08:17:05 - pico-train - INFO - ├── Loss: 4.7638 2025-08-31 08:17:05 - pico-train - INFO - ├── Learning Rate: 4.63e-05 2025-08-31 08:17:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:18:17 - pico-train - INFO - Step 68800 -- 🔄 Training Metrics 2025-08-31 08:18:17 - pico-train - INFO - ├── Loss: 4.8171 2025-08-31 08:18:17 - pico-train - INFO - ├── Learning Rate: 4.60e-05 2025-08-31 08:18:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:19:28 - pico-train - INFO - Step 68900 -- 🔄 Training Metrics 2025-08-31 08:19:28 - pico-train - INFO - ├── Loss: 4.7935 2025-08-31 08:19:28 - pico-train - INFO - ├── Learning Rate: 4.57e-05 2025-08-31 08:19:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:20:39 - pico-train - INFO - Step 69000 -- 💾 Saving Checkpoint 2025-08-31 08:22:40 - pico-train - INFO - Step 69000 -- 📊 Evaluation Results 2025-08-31 08:22:40 - pico-train - INFO - └── paloma: inf 2025-08-31 08:22:41 - pico-train - INFO - Step 69000 -- 🔄 Training Metrics 2025-08-31 08:22:41 - pico-train - INFO - ├── Loss: 4.8098 2025-08-31 08:22:41 - pico-train - INFO - ├── Learning Rate: 4.54e-05 2025-08-31 08:22:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:22:41 - pico-train - INFO - Step 69000 -- 📈 Saving Learning Dynamics 2025-08-31 08:23:55 - pico-train - INFO - Step 69100 -- 🔄 Training Metrics 2025-08-31 08:23:55 - pico-train - INFO - ├── Loss: 4.8127 2025-08-31 08:23:55 - pico-train - INFO - ├── Learning Rate: 4.52e-05 2025-08-31 08:23:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:25:06 - pico-train - INFO - Step 69200 -- 🔄 Training Metrics 2025-08-31 08:25:06 - pico-train - INFO - ├── Loss: 4.8256 2025-08-31 08:25:06 - pico-train - INFO - ├── Learning Rate: 4.49e-05 2025-08-31 08:25:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:26:17 - pico-train - INFO - Step 69300 -- 🔄 Training Metrics 2025-08-31 08:26:17 - pico-train - INFO - ├── Loss: 4.8021 2025-08-31 08:26:17 - pico-train - INFO - ├── Learning Rate: 4.46e-05 2025-08-31 08:26:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:27:28 - pico-train - INFO - Step 69400 -- 🔄 Training Metrics 2025-08-31 08:27:28 - pico-train - INFO - ├── Loss: 4.8068 2025-08-31 08:27:28 - pico-train - INFO - ├── Learning Rate: 4.44e-05 2025-08-31 08:27:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:28:40 - pico-train - INFO - Step 69500 -- 🔄 Training Metrics 2025-08-31 08:28:40 - pico-train - INFO - ├── Loss: 4.7974 2025-08-31 08:28:40 - pico-train - INFO - ├── Learning Rate: 4.41e-05 2025-08-31 08:28:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:29:50 - pico-train - INFO - Step 69600 -- 🔄 Training Metrics 2025-08-31 08:29:50 - pico-train - INFO - ├── Loss: 4.8162 2025-08-31 08:29:50 - pico-train - INFO - ├── Learning Rate: 4.38e-05 2025-08-31 08:29:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:31:02 - pico-train - INFO - Step 69700 -- 🔄 Training Metrics 2025-08-31 08:31:02 - pico-train - INFO - ├── Loss: 4.8043 2025-08-31 08:31:02 - pico-train - INFO - ├── Learning Rate: 4.36e-05 2025-08-31 08:31:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:32:13 - pico-train - INFO - Step 69800 -- 🔄 Training Metrics 2025-08-31 08:32:13 - pico-train - INFO - ├── Loss: 4.7863 2025-08-31 08:32:13 - pico-train - INFO - ├── Learning Rate: 4.33e-05 2025-08-31 08:32:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:33:24 - pico-train - INFO - Step 69900 -- 🔄 Training Metrics 2025-08-31 08:33:24 - pico-train - INFO - ├── Loss: 4.8059 2025-08-31 08:33:24 - pico-train - INFO - ├── Learning Rate: 4.31e-05 2025-08-31 08:33:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:34:34 - pico-train - INFO - Step 70000 -- 💾 Saving Checkpoint 2025-08-31 08:36:36 - pico-train - INFO - Step 70000 -- 📊 Evaluation Results 2025-08-31 08:36:36 - pico-train - INFO - └── paloma: inf 2025-08-31 08:36:37 - pico-train - INFO - Step 70000 -- 🔄 Training Metrics 2025-08-31 08:36:37 - pico-train - INFO - ├── Loss: 4.7928 2025-08-31 08:36:37 - pico-train - INFO - ├── Learning Rate: 4.28e-05 2025-08-31 08:36:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:36:37 - pico-train - INFO - Step 70000 -- 📈 Saving Learning Dynamics 2025-08-31 08:37:50 - pico-train - INFO - Step 70100 -- 🔄 Training Metrics 2025-08-31 08:37:50 - pico-train - INFO - ├── Loss: 4.8159 2025-08-31 08:37:50 - pico-train - INFO - ├── Learning Rate: 4.25e-05 2025-08-31 08:37:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:39:01 - pico-train - INFO - Step 70200 -- 🔄 Training Metrics 2025-08-31 08:39:01 - pico-train - INFO - ├── Loss: 4.8087 2025-08-31 08:39:01 - pico-train - INFO - ├── Learning Rate: 4.23e-05 2025-08-31 08:39:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:40:13 - pico-train - INFO - Step 70300 -- 🔄 Training Metrics 2025-08-31 08:40:13 - pico-train - INFO - ├── Loss: 4.8081 2025-08-31 08:40:13 - pico-train - INFO - ├── Learning Rate: 4.20e-05 2025-08-31 08:40:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:41:24 - pico-train - INFO - Step 70400 -- 🔄 Training Metrics 2025-08-31 08:41:24 - pico-train - INFO - ├── Loss: 4.7848 2025-08-31 08:41:24 - pico-train - INFO - ├── Learning Rate: 4.17e-05 2025-08-31 08:41:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:42:35 - pico-train - INFO - Step 70500 -- 🔄 Training Metrics 2025-08-31 08:42:35 - pico-train - INFO - ├── Loss: 4.7941 2025-08-31 08:42:35 - pico-train - INFO - ├── Learning Rate: 4.15e-05 2025-08-31 08:42:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:43:46 - pico-train - INFO - Step 70600 -- 🔄 Training Metrics 2025-08-31 08:43:46 - pico-train - INFO - ├── Loss: 4.7965 2025-08-31 08:43:46 - pico-train - INFO - ├── Learning Rate: 4.12e-05 2025-08-31 08:43:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:44:57 - pico-train - INFO - Step 70700 -- 🔄 Training Metrics 2025-08-31 08:44:57 - pico-train - INFO - ├── Loss: 4.7734 2025-08-31 08:44:57 - pico-train - INFO - ├── Learning Rate: 4.10e-05 2025-08-31 08:44:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:46:08 - pico-train - INFO - Step 70800 -- 🔄 Training Metrics 2025-08-31 08:46:08 - pico-train - INFO - ├── Loss: 4.8101 2025-08-31 08:46:08 - pico-train - INFO - ├── Learning Rate: 4.07e-05 2025-08-31 08:46:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:47:19 - pico-train - INFO - Step 70900 -- 🔄 Training Metrics 2025-08-31 08:47:19 - pico-train - INFO - ├── Loss: 4.8094 2025-08-31 08:47:19 - pico-train - INFO - ├── Learning Rate: 4.04e-05 2025-08-31 08:47:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:48:29 - pico-train - INFO - Step 71000 -- 💾 Saving Checkpoint 2025-08-31 08:50:31 - pico-train - INFO - Step 71000 -- 📊 Evaluation Results 2025-08-31 08:50:31 - pico-train - INFO - └── paloma: inf 2025-08-31 08:50:32 - pico-train - INFO - Step 71000 -- 🔄 Training Metrics 2025-08-31 08:50:32 - pico-train - INFO - ├── Loss: 4.8045 2025-08-31 08:50:32 - pico-train - INFO - ├── Learning Rate: 4.02e-05 2025-08-31 08:50:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:50:32 - pico-train - INFO - Step 71000 -- 📈 Saving Learning Dynamics 2025-08-31 08:51:46 - pico-train - INFO - Step 71100 -- 🔄 Training Metrics 2025-08-31 08:51:46 - pico-train - INFO - ├── Loss: 4.7922 2025-08-31 08:51:46 - pico-train - INFO - ├── Learning Rate: 3.99e-05 2025-08-31 08:51:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:52:57 - pico-train - INFO - Step 71200 -- 🔄 Training Metrics 2025-08-31 08:52:57 - pico-train - INFO - ├── Loss: 4.8090 2025-08-31 08:52:57 - pico-train - INFO - ├── Learning Rate: 3.97e-05 2025-08-31 08:52:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:54:08 - pico-train - INFO - Step 71300 -- 🔄 Training Metrics 2025-08-31 08:54:08 - pico-train - INFO - ├── Loss: 4.8051 2025-08-31 08:54:08 - pico-train - INFO - ├── Learning Rate: 3.94e-05 2025-08-31 08:54:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:55:19 - pico-train - INFO - Step 71400 -- 🔄 Training Metrics 2025-08-31 08:55:19 - pico-train - INFO - ├── Loss: 4.7895 2025-08-31 08:55:19 - pico-train - INFO - ├── Learning Rate: 3.92e-05 2025-08-31 08:55:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:56:30 - pico-train - INFO - Step 71500 -- 🔄 Training Metrics 2025-08-31 08:56:30 - pico-train - INFO - ├── Loss: 4.8153 2025-08-31 08:56:30 - pico-train - INFO - ├── Learning Rate: 3.89e-05 2025-08-31 08:56:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:57:41 - pico-train - INFO - Step 71600 -- 🔄 Training Metrics 2025-08-31 08:57:41 - pico-train - INFO - ├── Loss: 4.8103 2025-08-31 08:57:41 - pico-train - INFO - ├── Learning Rate: 3.87e-05 2025-08-31 08:57:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 08:58:53 - pico-train - INFO - Step 71700 -- 🔄 Training Metrics 2025-08-31 08:58:53 - pico-train - INFO - ├── Loss: 4.7847 2025-08-31 08:58:53 - pico-train - INFO - ├── Learning Rate: 3.84e-05 2025-08-31 08:58:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:00:04 - pico-train - INFO - Step 71800 -- 🔄 Training Metrics 2025-08-31 09:00:04 - pico-train - INFO - ├── Loss: 4.7882 2025-08-31 09:00:04 - pico-train - INFO - ├── Learning Rate: 3.82e-05 2025-08-31 09:00:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:01:15 - pico-train - INFO - Step 71900 -- 🔄 Training Metrics 2025-08-31 09:01:15 - pico-train - INFO - ├── Loss: 4.8031 2025-08-31 09:01:15 - pico-train - INFO - ├── Learning Rate: 3.79e-05 2025-08-31 09:01:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:02:25 - pico-train - INFO - Step 72000 -- 💾 Saving Checkpoint 2025-08-31 09:04:27 - pico-train - INFO - Step 72000 -- 📊 Evaluation Results 2025-08-31 09:04:27 - pico-train - INFO - └── paloma: inf 2025-08-31 09:04:27 - pico-train - INFO - Step 72000 -- 🔄 Training Metrics 2025-08-31 09:04:27 - pico-train - INFO - ├── Loss: 4.8049 2025-08-31 09:04:27 - pico-train - INFO - ├── Learning Rate: 3.77e-05 2025-08-31 09:04:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:04:27 - pico-train - INFO - Step 72000 -- 📈 Saving Learning Dynamics 2025-08-31 09:05:41 - pico-train - INFO - Step 72100 -- 🔄 Training Metrics 2025-08-31 09:05:41 - pico-train - INFO - ├── Loss: 4.7998 2025-08-31 09:05:41 - pico-train - INFO - ├── Learning Rate: 3.74e-05 2025-08-31 09:05:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:06:52 - pico-train - INFO - Step 72200 -- 🔄 Training Metrics 2025-08-31 09:06:52 - pico-train - INFO - ├── Loss: 4.8082 2025-08-31 09:06:52 - pico-train - INFO - ├── Learning Rate: 3.72e-05 2025-08-31 09:06:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:08:03 - pico-train - INFO - Step 72300 -- 🔄 Training Metrics 2025-08-31 09:08:03 - pico-train - INFO - ├── Loss: 4.8191 2025-08-31 09:08:03 - pico-train - INFO - ├── Learning Rate: 3.69e-05 2025-08-31 09:08:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:09:14 - pico-train - INFO - Step 72400 -- 🔄 Training Metrics 2025-08-31 09:09:14 - pico-train - INFO - ├── Loss: 4.7900 2025-08-31 09:09:14 - pico-train - INFO - ├── Learning Rate: 3.67e-05 2025-08-31 09:09:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:10:25 - pico-train - INFO - Step 72500 -- 🔄 Training Metrics 2025-08-31 09:10:25 - pico-train - INFO - ├── Loss: 4.7962 2025-08-31 09:10:25 - pico-train - INFO - ├── Learning Rate: 3.64e-05 2025-08-31 09:10:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:11:37 - pico-train - INFO - Step 72600 -- 🔄 Training Metrics 2025-08-31 09:11:37 - pico-train - INFO - ├── Loss: 4.8325 2025-08-31 09:11:37 - pico-train - INFO - ├── Learning Rate: 3.62e-05 2025-08-31 09:11:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:12:48 - pico-train - INFO - Step 72700 -- 🔄 Training Metrics 2025-08-31 09:12:48 - pico-train - INFO - ├── Loss: 4.7872 2025-08-31 09:12:48 - pico-train - INFO - ├── Learning Rate: 3.59e-05 2025-08-31 09:12:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:13:59 - pico-train - INFO - Step 72800 -- 🔄 Training Metrics 2025-08-31 09:13:59 - pico-train - INFO - ├── Loss: 4.7991 2025-08-31 09:13:59 - pico-train - INFO - ├── Learning Rate: 3.57e-05 2025-08-31 09:13:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:15:10 - pico-train - INFO - Step 72900 -- 🔄 Training Metrics 2025-08-31 09:15:10 - pico-train - INFO - ├── Loss: 4.7826 2025-08-31 09:15:10 - pico-train - INFO - ├── Learning Rate: 3.54e-05 2025-08-31 09:15:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:16:21 - pico-train - INFO - Step 73000 -- 💾 Saving Checkpoint 2025-08-31 09:18:23 - pico-train - INFO - Step 73000 -- 📊 Evaluation Results 2025-08-31 09:18:23 - pico-train - INFO - └── paloma: inf 2025-08-31 09:18:24 - pico-train - INFO - Step 73000 -- 🔄 Training Metrics 2025-08-31 09:18:24 - pico-train - INFO - ├── Loss: 4.7869 2025-08-31 09:18:24 - pico-train - INFO - ├── Learning Rate: 3.52e-05 2025-08-31 09:18:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:18:24 - pico-train - INFO - Step 73000 -- 📈 Saving Learning Dynamics 2025-08-31 09:19:37 - pico-train - INFO - Step 73100 -- 🔄 Training Metrics 2025-08-31 09:19:37 - pico-train - INFO - ├── Loss: 4.7872 2025-08-31 09:19:37 - pico-train - INFO - ├── Learning Rate: 3.49e-05 2025-08-31 09:19:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:20:48 - pico-train - INFO - Step 73200 -- 🔄 Training Metrics 2025-08-31 09:20:48 - pico-train - INFO - ├── Loss: 4.7995 2025-08-31 09:20:48 - pico-train - INFO - ├── Learning Rate: 3.47e-05 2025-08-31 09:20:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:22:00 - pico-train - INFO - Step 73300 -- 🔄 Training Metrics 2025-08-31 09:22:00 - pico-train - INFO - ├── Loss: 4.8165 2025-08-31 09:22:00 - pico-train - INFO - ├── Learning Rate: 3.44e-05 2025-08-31 09:22:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:23:11 - pico-train - INFO - Step 73400 -- 🔄 Training Metrics 2025-08-31 09:23:11 - pico-train - INFO - ├── Loss: 4.7786 2025-08-31 09:23:11 - pico-train - INFO - ├── Learning Rate: 3.42e-05 2025-08-31 09:23:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:24:23 - pico-train - INFO - Step 73500 -- 🔄 Training Metrics 2025-08-31 09:24:23 - pico-train - INFO - ├── Loss: 4.7794 2025-08-31 09:24:23 - pico-train - INFO - ├── Learning Rate: 3.40e-05 2025-08-31 09:24:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:25:34 - pico-train - INFO - Step 73600 -- 🔄 Training Metrics 2025-08-31 09:25:34 - pico-train - INFO - ├── Loss: 4.7911 2025-08-31 09:25:34 - pico-train - INFO - ├── Learning Rate: 3.37e-05 2025-08-31 09:25:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:26:44 - pico-train - INFO - Step 73700 -- 🔄 Training Metrics 2025-08-31 09:26:44 - pico-train - INFO - ├── Loss: 4.8029 2025-08-31 09:26:44 - pico-train - INFO - ├── Learning Rate: 3.35e-05 2025-08-31 09:26:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:27:56 - pico-train - INFO - Step 73800 -- 🔄 Training Metrics 2025-08-31 09:27:56 - pico-train - INFO - ├── Loss: 4.7945 2025-08-31 09:27:56 - pico-train - INFO - ├── Learning Rate: 3.32e-05 2025-08-31 09:27:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:29:07 - pico-train - INFO - Step 73900 -- 🔄 Training Metrics 2025-08-31 09:29:07 - pico-train - INFO - ├── Loss: 4.8115 2025-08-31 09:29:07 - pico-train - INFO - ├── Learning Rate: 3.30e-05 2025-08-31 09:29:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:30:18 - pico-train - INFO - Step 74000 -- 💾 Saving Checkpoint 2025-08-31 09:32:20 - pico-train - INFO - Step 74000 -- 📊 Evaluation Results 2025-08-31 09:32:20 - pico-train - INFO - └── paloma: inf 2025-08-31 09:32:20 - pico-train - INFO - Step 74000 -- 🔄 Training Metrics 2025-08-31 09:32:20 - pico-train - INFO - ├── Loss: 4.8107 2025-08-31 09:32:20 - pico-train - INFO - ├── Learning Rate: 3.28e-05 2025-08-31 09:32:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:32:20 - pico-train - INFO - Step 74000 -- 📈 Saving Learning Dynamics 2025-08-31 09:33:34 - pico-train - INFO - Step 74100 -- 🔄 Training Metrics 2025-08-31 09:33:34 - pico-train - INFO - ├── Loss: 4.7847 2025-08-31 09:33:34 - pico-train - INFO - ├── Learning Rate: 3.25e-05 2025-08-31 09:33:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:34:45 - pico-train - INFO - Step 74200 -- 🔄 Training Metrics 2025-08-31 09:34:45 - pico-train - INFO - ├── Loss: 4.7943 2025-08-31 09:34:45 - pico-train - INFO - ├── Learning Rate: 3.23e-05 2025-08-31 09:34:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:35:57 - pico-train - INFO - Step 74300 -- 🔄 Training Metrics 2025-08-31 09:35:57 - pico-train - INFO - ├── Loss: 4.7811 2025-08-31 09:35:57 - pico-train - INFO - ├── Learning Rate: 3.21e-05 2025-08-31 09:35:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:37:08 - pico-train - INFO - Step 74400 -- 🔄 Training Metrics 2025-08-31 09:37:08 - pico-train - INFO - ├── Loss: 4.8010 2025-08-31 09:37:08 - pico-train - INFO - ├── Learning Rate: 3.18e-05 2025-08-31 09:37:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:38:19 - pico-train - INFO - Step 74500 -- 🔄 Training Metrics 2025-08-31 09:38:19 - pico-train - INFO - ├── Loss: 4.7898 2025-08-31 09:38:19 - pico-train - INFO - ├── Learning Rate: 3.16e-05 2025-08-31 09:38:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:39:30 - pico-train - INFO - Step 74600 -- 🔄 Training Metrics 2025-08-31 09:39:30 - pico-train - INFO - ├── Loss: 4.8247 2025-08-31 09:39:30 - pico-train - INFO - ├── Learning Rate: 3.14e-05 2025-08-31 09:39:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:40:41 - pico-train - INFO - Step 74700 -- 🔄 Training Metrics 2025-08-31 09:40:41 - pico-train - INFO - ├── Loss: 4.8034 2025-08-31 09:40:41 - pico-train - INFO - ├── Learning Rate: 3.11e-05 2025-08-31 09:40:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:41:52 - pico-train - INFO - Step 74800 -- 🔄 Training Metrics 2025-08-31 09:41:52 - pico-train - INFO - ├── Loss: 4.7996 2025-08-31 09:41:52 - pico-train - INFO - ├── Learning Rate: 3.09e-05 2025-08-31 09:41:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:43:03 - pico-train - INFO - Step 74900 -- 🔄 Training Metrics 2025-08-31 09:43:03 - pico-train - INFO - ├── Loss: 4.7822 2025-08-31 09:43:03 - pico-train - INFO - ├── Learning Rate: 3.07e-05 2025-08-31 09:43:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:44:14 - pico-train - INFO - Step 75000 -- 💾 Saving Checkpoint 2025-08-31 09:46:15 - pico-train - INFO - Step 75000 -- 📊 Evaluation Results 2025-08-31 09:46:15 - pico-train - INFO - └── paloma: inf 2025-08-31 09:46:16 - pico-train - INFO - Step 75000 -- 🔄 Training Metrics 2025-08-31 09:46:16 - pico-train - INFO - ├── Loss: 4.7939 2025-08-31 09:46:16 - pico-train - INFO - ├── Learning Rate: 3.04e-05 2025-08-31 09:46:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:46:16 - pico-train - INFO - Step 75000 -- 📈 Saving Learning Dynamics 2025-08-31 09:47:29 - pico-train - INFO - Step 75100 -- 🔄 Training Metrics 2025-08-31 09:47:29 - pico-train - INFO - ├── Loss: 4.7925 2025-08-31 09:47:29 - pico-train - INFO - ├── Learning Rate: 3.02e-05 2025-08-31 09:47:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:48:41 - pico-train - INFO - Step 75200 -- 🔄 Training Metrics 2025-08-31 09:48:41 - pico-train - INFO - ├── Loss: 4.7906 2025-08-31 09:48:41 - pico-train - INFO - ├── Learning Rate: 3.00e-05 2025-08-31 09:48:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:49:52 - pico-train - INFO - Step 75300 -- 🔄 Training Metrics 2025-08-31 09:49:52 - pico-train - INFO - ├── Loss: 4.8083 2025-08-31 09:49:52 - pico-train - INFO - ├── Learning Rate: 2.97e-05 2025-08-31 09:49:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:51:03 - pico-train - INFO - Step 75400 -- 🔄 Training Metrics 2025-08-31 09:51:03 - pico-train - INFO - ├── Loss: 4.7914 2025-08-31 09:51:03 - pico-train - INFO - ├── Learning Rate: 2.95e-05 2025-08-31 09:51:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:52:14 - pico-train - INFO - Step 75500 -- 🔄 Training Metrics 2025-08-31 09:52:14 - pico-train - INFO - ├── Loss: 4.7965 2025-08-31 09:52:14 - pico-train - INFO - ├── Learning Rate: 2.93e-05 2025-08-31 09:52:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:53:26 - pico-train - INFO - Step 75600 -- 🔄 Training Metrics 2025-08-31 09:53:26 - pico-train - INFO - ├── Loss: 4.7760 2025-08-31 09:53:26 - pico-train - INFO - ├── Learning Rate: 2.91e-05 2025-08-31 09:53:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:54:37 - pico-train - INFO - Step 75700 -- 🔄 Training Metrics 2025-08-31 09:54:37 - pico-train - INFO - ├── Loss: 4.7893 2025-08-31 09:54:37 - pico-train - INFO - ├── Learning Rate: 2.88e-05 2025-08-31 09:54:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:55:48 - pico-train - INFO - Step 75800 -- 🔄 Training Metrics 2025-08-31 09:55:48 - pico-train - INFO - ├── Loss: 4.7945 2025-08-31 09:55:48 - pico-train - INFO - ├── Learning Rate: 2.86e-05 2025-08-31 09:55:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:56:59 - pico-train - INFO - Step 75900 -- 🔄 Training Metrics 2025-08-31 09:56:59 - pico-train - INFO - ├── Loss: 4.7982 2025-08-31 09:56:59 - pico-train - INFO - ├── Learning Rate: 2.84e-05 2025-08-31 09:56:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 09:58:09 - pico-train - INFO - Step 76000 -- 💾 Saving Checkpoint 2025-08-31 10:00:10 - pico-train - INFO - Step 76000 -- 📊 Evaluation Results 2025-08-31 10:00:10 - pico-train - INFO - └── paloma: inf 2025-08-31 10:00:11 - pico-train - INFO - Step 76000 -- 🔄 Training Metrics 2025-08-31 10:00:11 - pico-train - INFO - ├── Loss: 4.7743 2025-08-31 10:00:11 - pico-train - INFO - ├── Learning Rate: 2.82e-05 2025-08-31 10:00:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:00:11 - pico-train - INFO - Step 76000 -- 📈 Saving Learning Dynamics 2025-08-31 10:01:25 - pico-train - INFO - Step 76100 -- 🔄 Training Metrics 2025-08-31 10:01:25 - pico-train - INFO - ├── Loss: 4.7834 2025-08-31 10:01:25 - pico-train - INFO - ├── Learning Rate: 2.79e-05 2025-08-31 10:01:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:02:37 - pico-train - INFO - Step 76200 -- 🔄 Training Metrics 2025-08-31 10:02:37 - pico-train - INFO - ├── Loss: 4.8036 2025-08-31 10:02:37 - pico-train - INFO - ├── Learning Rate: 2.77e-05 2025-08-31 10:02:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:03:48 - pico-train - INFO - Step 76300 -- 🔄 Training Metrics 2025-08-31 10:03:48 - pico-train - INFO - ├── Loss: 4.8019 2025-08-31 10:03:48 - pico-train - INFO - ├── Learning Rate: 2.75e-05 2025-08-31 10:03:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:04:59 - pico-train - INFO - Step 76400 -- 🔄 Training Metrics 2025-08-31 10:04:59 - pico-train - INFO - ├── Loss: 4.7705 2025-08-31 10:04:59 - pico-train - INFO - ├── Learning Rate: 2.73e-05 2025-08-31 10:04:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:06:10 - pico-train - INFO - Step 76500 -- 🔄 Training Metrics 2025-08-31 10:06:10 - pico-train - INFO - ├── Loss: 4.7851 2025-08-31 10:06:10 - pico-train - INFO - ├── Learning Rate: 2.71e-05 2025-08-31 10:06:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:07:21 - pico-train - INFO - Step 76600 -- 🔄 Training Metrics 2025-08-31 10:07:21 - pico-train - INFO - ├── Loss: 4.8080 2025-08-31 10:07:21 - pico-train - INFO - ├── Learning Rate: 2.68e-05 2025-08-31 10:07:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:08:33 - pico-train - INFO - Step 76700 -- 🔄 Training Metrics 2025-08-31 10:08:33 - pico-train - INFO - ├── Loss: 4.7811 2025-08-31 10:08:33 - pico-train - INFO - ├── Learning Rate: 2.66e-05 2025-08-31 10:08:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:09:45 - pico-train - INFO - Step 76800 -- 🔄 Training Metrics 2025-08-31 10:09:45 - pico-train - INFO - ├── Loss: 4.7781 2025-08-31 10:09:45 - pico-train - INFO - ├── Learning Rate: 2.64e-05 2025-08-31 10:09:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:10:55 - pico-train - INFO - Step 76900 -- 🔄 Training Metrics 2025-08-31 10:10:55 - pico-train - INFO - ├── Loss: 4.7936 2025-08-31 10:10:55 - pico-train - INFO - ├── Learning Rate: 2.62e-05 2025-08-31 10:10:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:12:06 - pico-train - INFO - Step 77000 -- 💾 Saving Checkpoint 2025-08-31 10:14:08 - pico-train - INFO - Step 77000 -- 📊 Evaluation Results 2025-08-31 10:14:08 - pico-train - INFO - └── paloma: inf 2025-08-31 10:14:08 - pico-train - INFO - Step 77000 -- 🔄 Training Metrics 2025-08-31 10:14:08 - pico-train - INFO - ├── Loss: 4.7972 2025-08-31 10:14:08 - pico-train - INFO - ├── Learning Rate: 2.60e-05 2025-08-31 10:14:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:14:08 - pico-train - INFO - Step 77000 -- 📈 Saving Learning Dynamics 2025-08-31 10:15:22 - pico-train - INFO - Step 77100 -- 🔄 Training Metrics 2025-08-31 10:15:22 - pico-train - INFO - ├── Loss: 4.8169 2025-08-31 10:15:22 - pico-train - INFO - ├── Learning Rate: 2.58e-05 2025-08-31 10:15:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:16:33 - pico-train - INFO - Step 77200 -- 🔄 Training Metrics 2025-08-31 10:16:33 - pico-train - INFO - ├── Loss: 4.7975 2025-08-31 10:16:33 - pico-train - INFO - ├── Learning Rate: 2.55e-05 2025-08-31 10:16:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:17:44 - pico-train - INFO - Step 77300 -- 🔄 Training Metrics 2025-08-31 10:17:44 - pico-train - INFO - ├── Loss: 4.7711 2025-08-31 10:17:44 - pico-train - INFO - ├── Learning Rate: 2.53e-05 2025-08-31 10:17:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:18:55 - pico-train - INFO - Step 77400 -- 🔄 Training Metrics 2025-08-31 10:18:55 - pico-train - INFO - ├── Loss: 4.7869 2025-08-31 10:18:55 - pico-train - INFO - ├── Learning Rate: 2.51e-05 2025-08-31 10:18:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:20:06 - pico-train - INFO - Step 77500 -- 🔄 Training Metrics 2025-08-31 10:20:06 - pico-train - INFO - ├── Loss: 4.8086 2025-08-31 10:20:06 - pico-train - INFO - ├── Learning Rate: 2.49e-05 2025-08-31 10:20:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:21:18 - pico-train - INFO - Step 77600 -- 🔄 Training Metrics 2025-08-31 10:21:18 - pico-train - INFO - ├── Loss: 4.7981 2025-08-31 10:21:18 - pico-train - INFO - ├── Learning Rate: 2.47e-05 2025-08-31 10:21:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:22:29 - pico-train - INFO - Step 77700 -- 🔄 Training Metrics 2025-08-31 10:22:29 - pico-train - INFO - ├── Loss: 4.7844 2025-08-31 10:22:29 - pico-train - INFO - ├── Learning Rate: 2.45e-05 2025-08-31 10:22:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:23:40 - pico-train - INFO - Step 77800 -- 🔄 Training Metrics 2025-08-31 10:23:40 - pico-train - INFO - ├── Loss: 4.7779 2025-08-31 10:23:40 - pico-train - INFO - ├── Learning Rate: 2.43e-05 2025-08-31 10:23:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:24:51 - pico-train - INFO - Step 77900 -- 🔄 Training Metrics 2025-08-31 10:24:51 - pico-train - INFO - ├── Loss: 4.7901 2025-08-31 10:24:51 - pico-train - INFO - ├── Learning Rate: 2.41e-05 2025-08-31 10:24:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:26:01 - pico-train - INFO - Step 78000 -- 💾 Saving Checkpoint 2025-08-31 10:28:03 - pico-train - INFO - Step 78000 -- 📊 Evaluation Results 2025-08-31 10:28:03 - pico-train - INFO - └── paloma: inf 2025-08-31 10:28:04 - pico-train - INFO - Step 78000 -- 🔄 Training Metrics 2025-08-31 10:28:04 - pico-train - INFO - ├── Loss: 4.7974 2025-08-31 10:28:04 - pico-train - INFO - ├── Learning Rate: 2.39e-05 2025-08-31 10:28:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:28:04 - pico-train - INFO - Step 78000 -- 📈 Saving Learning Dynamics 2025-08-31 10:29:19 - pico-train - INFO - Step 78100 -- 🔄 Training Metrics 2025-08-31 10:29:19 - pico-train - INFO - ├── Loss: 4.7623 2025-08-31 10:29:19 - pico-train - INFO - ├── Learning Rate: 2.36e-05 2025-08-31 10:29:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:30:30 - pico-train - INFO - Step 78200 -- 🔄 Training Metrics 2025-08-31 10:30:30 - pico-train - INFO - ├── Loss: 4.8048 2025-08-31 10:30:30 - pico-train - INFO - ├── Learning Rate: 2.34e-05 2025-08-31 10:30:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:31:41 - pico-train - INFO - Step 78300 -- 🔄 Training Metrics 2025-08-31 10:31:41 - pico-train - INFO - ├── Loss: 4.7813 2025-08-31 10:31:41 - pico-train - INFO - ├── Learning Rate: 2.32e-05 2025-08-31 10:31:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:32:52 - pico-train - INFO - Step 78400 -- 🔄 Training Metrics 2025-08-31 10:32:52 - pico-train - INFO - ├── Loss: 4.8007 2025-08-31 10:32:52 - pico-train - INFO - ├── Learning Rate: 2.30e-05 2025-08-31 10:32:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:34:03 - pico-train - INFO - Step 78500 -- 🔄 Training Metrics 2025-08-31 10:34:03 - pico-train - INFO - ├── Loss: 4.8197 2025-08-31 10:34:03 - pico-train - INFO - ├── Learning Rate: 2.28e-05 2025-08-31 10:34:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:35:15 - pico-train - INFO - Step 78600 -- 🔄 Training Metrics 2025-08-31 10:35:15 - pico-train - INFO - ├── Loss: 4.7738 2025-08-31 10:35:15 - pico-train - INFO - ├── Learning Rate: 2.26e-05 2025-08-31 10:35:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:36:25 - pico-train - INFO - Step 78700 -- 🔄 Training Metrics 2025-08-31 10:36:25 - pico-train - INFO - ├── Loss: 4.7747 2025-08-31 10:36:25 - pico-train - INFO - ├── Learning Rate: 2.24e-05 2025-08-31 10:36:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:37:37 - pico-train - INFO - Step 78800 -- 🔄 Training Metrics 2025-08-31 10:37:37 - pico-train - INFO - ├── Loss: 4.7643 2025-08-31 10:37:37 - pico-train - INFO - ├── Learning Rate: 2.22e-05 2025-08-31 10:37:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:38:48 - pico-train - INFO - Step 78900 -- 🔄 Training Metrics 2025-08-31 10:38:48 - pico-train - INFO - ├── Loss: 4.7826 2025-08-31 10:38:48 - pico-train - INFO - ├── Learning Rate: 2.20e-05 2025-08-31 10:38:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:39:59 - pico-train - INFO - Step 79000 -- 💾 Saving Checkpoint 2025-08-31 10:42:00 - pico-train - INFO - Step 79000 -- 📊 Evaluation Results 2025-08-31 10:42:00 - pico-train - INFO - └── paloma: inf 2025-08-31 10:42:01 - pico-train - INFO - Step 79000 -- 🔄 Training Metrics 2025-08-31 10:42:01 - pico-train - INFO - ├── Loss: 4.7848 2025-08-31 10:42:01 - pico-train - INFO - ├── Learning Rate: 2.18e-05 2025-08-31 10:42:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:42:01 - pico-train - INFO - Step 79000 -- 📈 Saving Learning Dynamics 2025-08-31 10:43:15 - pico-train - INFO - Step 79100 -- 🔄 Training Metrics 2025-08-31 10:43:15 - pico-train - INFO - ├── Loss: 4.7719 2025-08-31 10:43:15 - pico-train - INFO - ├── Learning Rate: 2.16e-05 2025-08-31 10:43:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:44:26 - pico-train - INFO - Step 79200 -- 🔄 Training Metrics 2025-08-31 10:44:26 - pico-train - INFO - ├── Loss: 4.7832 2025-08-31 10:44:26 - pico-train - INFO - ├── Learning Rate: 2.14e-05 2025-08-31 10:44:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:45:37 - pico-train - INFO - Step 79300 -- 🔄 Training Metrics 2025-08-31 10:45:37 - pico-train - INFO - ├── Loss: 4.8105 2025-08-31 10:45:37 - pico-train - INFO - ├── Learning Rate: 2.12e-05 2025-08-31 10:45:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:46:50 - pico-train - INFO - Step 79400 -- 🔄 Training Metrics 2025-08-31 10:46:50 - pico-train - INFO - ├── Loss: 4.7942 2025-08-31 10:46:50 - pico-train - INFO - ├── Learning Rate: 2.10e-05 2025-08-31 10:46:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:48:01 - pico-train - INFO - Step 79500 -- 🔄 Training Metrics 2025-08-31 10:48:01 - pico-train - INFO - ├── Loss: 4.7787 2025-08-31 10:48:01 - pico-train - INFO - ├── Learning Rate: 2.08e-05 2025-08-31 10:48:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:49:12 - pico-train - INFO - Step 79600 -- 🔄 Training Metrics 2025-08-31 10:49:12 - pico-train - INFO - ├── Loss: 4.8027 2025-08-31 10:49:12 - pico-train - INFO - ├── Learning Rate: 2.06e-05 2025-08-31 10:49:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:50:23 - pico-train - INFO - Step 79700 -- 🔄 Training Metrics 2025-08-31 10:50:23 - pico-train - INFO - ├── Loss: 4.7814 2025-08-31 10:50:23 - pico-train - INFO - ├── Learning Rate: 2.04e-05 2025-08-31 10:50:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:51:34 - pico-train - INFO - Step 79800 -- 🔄 Training Metrics 2025-08-31 10:51:34 - pico-train - INFO - ├── Loss: 4.7827 2025-08-31 10:51:34 - pico-train - INFO - ├── Learning Rate: 2.02e-05 2025-08-31 10:51:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:52:45 - pico-train - INFO - Step 79900 -- 🔄 Training Metrics 2025-08-31 10:52:45 - pico-train - INFO - ├── Loss: 4.7776 2025-08-31 10:52:45 - pico-train - INFO - ├── Learning Rate: 2.01e-05 2025-08-31 10:52:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:53:55 - pico-train - INFO - Step 80000 -- 💾 Saving Checkpoint 2025-08-31 10:55:57 - pico-train - INFO - Step 80000 -- 📊 Evaluation Results 2025-08-31 10:55:57 - pico-train - INFO - └── paloma: inf 2025-08-31 10:55:58 - pico-train - INFO - Step 80000 -- 🔄 Training Metrics 2025-08-31 10:55:58 - pico-train - INFO - ├── Loss: 4.7796 2025-08-31 10:55:58 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 10:55:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:55:58 - pico-train - INFO - Step 80000 -- 📈 Saving Learning Dynamics 2025-08-31 10:57:11 - pico-train - INFO - Step 80100 -- 🔄 Training Metrics 2025-08-31 10:57:11 - pico-train - INFO - ├── Loss: 4.8003 2025-08-31 10:57:11 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 10:57:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:58:23 - pico-train - INFO - Step 80200 -- 🔄 Training Metrics 2025-08-31 10:58:23 - pico-train - INFO - ├── Loss: 4.8047 2025-08-31 10:58:23 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 10:58:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 10:59:34 - pico-train - INFO - Step 80300 -- 🔄 Training Metrics 2025-08-31 10:59:34 - pico-train - INFO - ├── Loss: 4.7894 2025-08-31 10:59:34 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 10:59:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:00:46 - pico-train - INFO - Step 80400 -- 🔄 Training Metrics 2025-08-31 11:00:46 - pico-train - INFO - ├── Loss: 4.7800 2025-08-31 11:00:46 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:00:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:01:57 - pico-train - INFO - Step 80500 -- 🔄 Training Metrics 2025-08-31 11:01:57 - pico-train - INFO - ├── Loss: 4.7781 2025-08-31 11:01:57 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:01:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:03:07 - pico-train - INFO - Step 80600 -- 🔄 Training Metrics 2025-08-31 11:03:07 - pico-train - INFO - ├── Loss: 4.7873 2025-08-31 11:03:07 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:03:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:04:20 - pico-train - INFO - Step 80700 -- 🔄 Training Metrics 2025-08-31 11:04:20 - pico-train - INFO - ├── Loss: 4.7820 2025-08-31 11:04:20 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:04:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:05:31 - pico-train - INFO - Step 80800 -- 🔄 Training Metrics 2025-08-31 11:05:31 - pico-train - INFO - ├── Loss: 4.7757 2025-08-31 11:05:31 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:05:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:06:42 - pico-train - INFO - Step 80900 -- 🔄 Training Metrics 2025-08-31 11:06:42 - pico-train - INFO - ├── Loss: 4.7693 2025-08-31 11:06:42 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:06:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:07:52 - pico-train - INFO - Step 81000 -- 💾 Saving Checkpoint 2025-08-31 11:09:54 - pico-train - INFO - Step 81000 -- 📊 Evaluation Results 2025-08-31 11:09:54 - pico-train - INFO - └── paloma: inf 2025-08-31 11:09:54 - pico-train - INFO - Step 81000 -- 🔄 Training Metrics 2025-08-31 11:09:54 - pico-train - INFO - ├── Loss: 4.8021 2025-08-31 11:09:54 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:09:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:09:54 - pico-train - INFO - Step 81000 -- 📈 Saving Learning Dynamics 2025-08-31 11:11:08 - pico-train - INFO - Step 81100 -- 🔄 Training Metrics 2025-08-31 11:11:08 - pico-train - INFO - ├── Loss: 4.7742 2025-08-31 11:11:08 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:11:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:12:19 - pico-train - INFO - Step 81200 -- 🔄 Training Metrics 2025-08-31 11:12:19 - pico-train - INFO - ├── Loss: 4.7801 2025-08-31 11:12:19 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:12:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:13:31 - pico-train - INFO - Step 81300 -- 🔄 Training Metrics 2025-08-31 11:13:31 - pico-train - INFO - ├── Loss: 4.7931 2025-08-31 11:13:31 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:13:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:14:42 - pico-train - INFO - Step 81400 -- 🔄 Training Metrics 2025-08-31 11:14:42 - pico-train - INFO - ├── Loss: 4.7744 2025-08-31 11:14:42 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:14:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:15:53 - pico-train - INFO - Step 81500 -- 🔄 Training Metrics 2025-08-31 11:15:53 - pico-train - INFO - ├── Loss: 4.7913 2025-08-31 11:15:53 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:15:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:17:04 - pico-train - INFO - Step 81600 -- 🔄 Training Metrics 2025-08-31 11:17:04 - pico-train - INFO - ├── Loss: 4.7748 2025-08-31 11:17:04 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:17:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:18:16 - pico-train - INFO - Step 81700 -- 🔄 Training Metrics 2025-08-31 11:18:16 - pico-train - INFO - ├── Loss: 4.7952 2025-08-31 11:18:16 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:18:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:19:27 - pico-train - INFO - Step 81800 -- 🔄 Training Metrics 2025-08-31 11:19:27 - pico-train - INFO - ├── Loss: 4.7844 2025-08-31 11:19:27 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:19:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:20:38 - pico-train - INFO - Step 81900 -- 🔄 Training Metrics 2025-08-31 11:20:38 - pico-train - INFO - ├── Loss: 4.7869 2025-08-31 11:20:38 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:20:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:21:49 - pico-train - INFO - Step 82000 -- 💾 Saving Checkpoint 2025-08-31 11:23:50 - pico-train - INFO - Step 82000 -- 📊 Evaluation Results 2025-08-31 11:23:50 - pico-train - INFO - └── paloma: inf 2025-08-31 11:23:51 - pico-train - INFO - Step 82000 -- 🔄 Training Metrics 2025-08-31 11:23:51 - pico-train - INFO - ├── Loss: 4.7823 2025-08-31 11:23:51 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:23:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:23:51 - pico-train - INFO - Step 82000 -- 📈 Saving Learning Dynamics 2025-08-31 11:25:05 - pico-train - INFO - Step 82100 -- 🔄 Training Metrics 2025-08-31 11:25:05 - pico-train - INFO - ├── Loss: 4.7911 2025-08-31 11:25:05 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:25:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:26:16 - pico-train - INFO - Step 82200 -- 🔄 Training Metrics 2025-08-31 11:26:16 - pico-train - INFO - ├── Loss: 4.7879 2025-08-31 11:26:16 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:26:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:27:27 - pico-train - INFO - Step 82300 -- 🔄 Training Metrics 2025-08-31 11:27:27 - pico-train - INFO - ├── Loss: 4.7873 2025-08-31 11:27:27 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:27:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:28:38 - pico-train - INFO - Step 82400 -- 🔄 Training Metrics 2025-08-31 11:28:38 - pico-train - INFO - ├── Loss: 4.7660 2025-08-31 11:28:38 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:28:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:29:49 - pico-train - INFO - Step 82500 -- 🔄 Training Metrics 2025-08-31 11:29:49 - pico-train - INFO - ├── Loss: 4.7860 2025-08-31 11:29:49 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:29:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:31:00 - pico-train - INFO - Step 82600 -- 🔄 Training Metrics 2025-08-31 11:31:00 - pico-train - INFO - ├── Loss: 4.8142 2025-08-31 11:31:00 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:31:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:32:11 - pico-train - INFO - Step 82700 -- 🔄 Training Metrics 2025-08-31 11:32:11 - pico-train - INFO - ├── Loss: 4.7781 2025-08-31 11:32:11 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:32:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:33:23 - pico-train - INFO - Step 82800 -- 🔄 Training Metrics 2025-08-31 11:33:23 - pico-train - INFO - ├── Loss: 4.7692 2025-08-31 11:33:23 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:33:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:34:33 - pico-train - INFO - Step 82900 -- 🔄 Training Metrics 2025-08-31 11:34:33 - pico-train - INFO - ├── Loss: 4.7853 2025-08-31 11:34:33 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:34:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:35:44 - pico-train - INFO - Step 83000 -- 💾 Saving Checkpoint 2025-08-31 11:37:45 - pico-train - INFO - Step 83000 -- 📊 Evaluation Results 2025-08-31 11:37:45 - pico-train - INFO - └── paloma: inf 2025-08-31 11:37:46 - pico-train - INFO - Step 83000 -- 🔄 Training Metrics 2025-08-31 11:37:46 - pico-train - INFO - ├── Loss: 4.7917 2025-08-31 11:37:46 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:37:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:37:46 - pico-train - INFO - Step 83000 -- 📈 Saving Learning Dynamics 2025-08-31 11:39:00 - pico-train - INFO - Step 83100 -- 🔄 Training Metrics 2025-08-31 11:39:00 - pico-train - INFO - ├── Loss: 4.7694 2025-08-31 11:39:00 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:39:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:40:12 - pico-train - INFO - Step 83200 -- 🔄 Training Metrics 2025-08-31 11:40:12 - pico-train - INFO - ├── Loss: 4.7764 2025-08-31 11:40:12 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:40:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:41:23 - pico-train - INFO - Step 83300 -- 🔄 Training Metrics 2025-08-31 11:41:23 - pico-train - INFO - ├── Loss: 4.7760 2025-08-31 11:41:23 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:41:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:42:34 - pico-train - INFO - Step 83400 -- 🔄 Training Metrics 2025-08-31 11:42:34 - pico-train - INFO - ├── Loss: 4.7765 2025-08-31 11:42:34 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:42:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:43:45 - pico-train - INFO - Step 83500 -- 🔄 Training Metrics 2025-08-31 11:43:45 - pico-train - INFO - ├── Loss: 4.7858 2025-08-31 11:43:45 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:43:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:44:56 - pico-train - INFO - Step 83600 -- 🔄 Training Metrics 2025-08-31 11:44:56 - pico-train - INFO - ├── Loss: 4.7846 2025-08-31 11:44:56 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:44:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:46:08 - pico-train - INFO - Step 83700 -- 🔄 Training Metrics 2025-08-31 11:46:08 - pico-train - INFO - ├── Loss: 4.7743 2025-08-31 11:46:08 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:46:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:47:19 - pico-train - INFO - Step 83800 -- 🔄 Training Metrics 2025-08-31 11:47:19 - pico-train - INFO - ├── Loss: 4.7898 2025-08-31 11:47:19 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:47:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:48:30 - pico-train - INFO - Step 83900 -- 🔄 Training Metrics 2025-08-31 11:48:30 - pico-train - INFO - ├── Loss: 4.7867 2025-08-31 11:48:30 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:48:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:49:40 - pico-train - INFO - Step 84000 -- 💾 Saving Checkpoint 2025-08-31 11:51:42 - pico-train - INFO - Step 84000 -- 📊 Evaluation Results 2025-08-31 11:51:42 - pico-train - INFO - └── paloma: inf 2025-08-31 11:51:43 - pico-train - INFO - Step 84000 -- 🔄 Training Metrics 2025-08-31 11:51:43 - pico-train - INFO - ├── Loss: 4.7616 2025-08-31 11:51:43 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:51:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:51:43 - pico-train - INFO - Step 84000 -- 📈 Saving Learning Dynamics 2025-08-31 11:52:56 - pico-train - INFO - Step 84100 -- 🔄 Training Metrics 2025-08-31 11:52:56 - pico-train - INFO - ├── Loss: 4.7942 2025-08-31 11:52:56 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:52:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:54:08 - pico-train - INFO - Step 84200 -- 🔄 Training Metrics 2025-08-31 11:54:08 - pico-train - INFO - ├── Loss: 4.7937 2025-08-31 11:54:08 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:54:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:55:18 - pico-train - INFO - Step 84300 -- 🔄 Training Metrics 2025-08-31 11:55:18 - pico-train - INFO - ├── Loss: 4.7635 2025-08-31 11:55:18 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:55:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:56:29 - pico-train - INFO - Step 84400 -- 🔄 Training Metrics 2025-08-31 11:56:29 - pico-train - INFO - ├── Loss: 4.7841 2025-08-31 11:56:29 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:56:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:57:41 - pico-train - INFO - Step 84500 -- 🔄 Training Metrics 2025-08-31 11:57:41 - pico-train - INFO - ├── Loss: 4.7763 2025-08-31 11:57:41 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:57:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 11:58:52 - pico-train - INFO - Step 84600 -- 🔄 Training Metrics 2025-08-31 11:58:52 - pico-train - INFO - ├── Loss: 4.7988 2025-08-31 11:58:52 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 11:58:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:00:03 - pico-train - INFO - Step 84700 -- 🔄 Training Metrics 2025-08-31 12:00:03 - pico-train - INFO - ├── Loss: 4.7889 2025-08-31 12:00:03 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:00:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:01:14 - pico-train - INFO - Step 84800 -- 🔄 Training Metrics 2025-08-31 12:01:14 - pico-train - INFO - ├── Loss: 4.7821 2025-08-31 12:01:14 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:01:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:02:26 - pico-train - INFO - Step 84900 -- 🔄 Training Metrics 2025-08-31 12:02:26 - pico-train - INFO - ├── Loss: 4.7949 2025-08-31 12:02:26 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:02:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:03:36 - pico-train - INFO - Step 85000 -- 💾 Saving Checkpoint 2025-08-31 12:05:38 - pico-train - INFO - Step 85000 -- 📊 Evaluation Results 2025-08-31 12:05:38 - pico-train - INFO - └── paloma: inf 2025-08-31 12:05:38 - pico-train - INFO - Step 85000 -- 🔄 Training Metrics 2025-08-31 12:05:38 - pico-train - INFO - ├── Loss: 4.8050 2025-08-31 12:05:38 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:05:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:05:38 - pico-train - INFO - Step 85000 -- 📈 Saving Learning Dynamics 2025-08-31 12:06:52 - pico-train - INFO - Step 85100 -- 🔄 Training Metrics 2025-08-31 12:06:52 - pico-train - INFO - ├── Loss: 4.7980 2025-08-31 12:06:52 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:06:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:08:03 - pico-train - INFO - Step 85200 -- 🔄 Training Metrics 2025-08-31 12:08:03 - pico-train - INFO - ├── Loss: 4.8045 2025-08-31 12:08:03 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:08:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:09:14 - pico-train - INFO - Step 85300 -- 🔄 Training Metrics 2025-08-31 12:09:14 - pico-train - INFO - ├── Loss: 4.7894 2025-08-31 12:09:14 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:09:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:10:26 - pico-train - INFO - Step 85400 -- 🔄 Training Metrics 2025-08-31 12:10:26 - pico-train - INFO - ├── Loss: 4.7978 2025-08-31 12:10:26 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:10:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:11:37 - pico-train - INFO - Step 85500 -- 🔄 Training Metrics 2025-08-31 12:11:37 - pico-train - INFO - ├── Loss: 4.7824 2025-08-31 12:11:37 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:11:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:12:48 - pico-train - INFO - Step 85600 -- 🔄 Training Metrics 2025-08-31 12:12:48 - pico-train - INFO - ├── Loss: 4.7912 2025-08-31 12:12:48 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:12:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:13:59 - pico-train - INFO - Step 85700 -- 🔄 Training Metrics 2025-08-31 12:13:59 - pico-train - INFO - ├── Loss: 4.7705 2025-08-31 12:13:59 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:13:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:15:10 - pico-train - INFO - Step 85800 -- 🔄 Training Metrics 2025-08-31 12:15:10 - pico-train - INFO - ├── Loss: 4.7781 2025-08-31 12:15:10 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:15:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:16:22 - pico-train - INFO - Step 85900 -- 🔄 Training Metrics 2025-08-31 12:16:22 - pico-train - INFO - ├── Loss: 4.8135 2025-08-31 12:16:22 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:16:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:17:32 - pico-train - INFO - Step 86000 -- 💾 Saving Checkpoint 2025-08-31 12:19:33 - pico-train - INFO - Step 86000 -- 📊 Evaluation Results 2025-08-31 12:19:33 - pico-train - INFO - └── paloma: inf 2025-08-31 12:19:34 - pico-train - INFO - Step 86000 -- 🔄 Training Metrics 2025-08-31 12:19:34 - pico-train - INFO - ├── Loss: 4.7768 2025-08-31 12:19:34 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:19:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:19:34 - pico-train - INFO - Step 86000 -- 📈 Saving Learning Dynamics 2025-08-31 12:20:48 - pico-train - INFO - Step 86100 -- 🔄 Training Metrics 2025-08-31 12:20:48 - pico-train - INFO - ├── Loss: 4.7966 2025-08-31 12:20:48 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:20:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:21:59 - pico-train - INFO - Step 86200 -- 🔄 Training Metrics 2025-08-31 12:21:59 - pico-train - INFO - ├── Loss: 4.7856 2025-08-31 12:21:59 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:21:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:23:10 - pico-train - INFO - Step 86300 -- 🔄 Training Metrics 2025-08-31 12:23:10 - pico-train - INFO - ├── Loss: 4.7666 2025-08-31 12:23:10 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:23:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:24:21 - pico-train - INFO - Step 86400 -- 🔄 Training Metrics 2025-08-31 12:24:21 - pico-train - INFO - ├── Loss: 4.8334 2025-08-31 12:24:21 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:24:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:25:32 - pico-train - INFO - Step 86500 -- 🔄 Training Metrics 2025-08-31 12:25:32 - pico-train - INFO - ├── Loss: 4.7574 2025-08-31 12:25:32 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:25:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:26:43 - pico-train - INFO - Step 86600 -- 🔄 Training Metrics 2025-08-31 12:26:43 - pico-train - INFO - ├── Loss: 4.7646 2025-08-31 12:26:43 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:26:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:27:54 - pico-train - INFO - Step 86700 -- 🔄 Training Metrics 2025-08-31 12:27:54 - pico-train - INFO - ├── Loss: 4.7596 2025-08-31 12:27:54 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:27:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:29:06 - pico-train - INFO - Step 86800 -- 🔄 Training Metrics 2025-08-31 12:29:06 - pico-train - INFO - ├── Loss: 4.7842 2025-08-31 12:29:06 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:29:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:30:17 - pico-train - INFO - Step 86900 -- 🔄 Training Metrics 2025-08-31 12:30:17 - pico-train - INFO - ├── Loss: 4.7731 2025-08-31 12:30:17 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:30:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:31:27 - pico-train - INFO - Step 87000 -- 💾 Saving Checkpoint 2025-08-31 12:33:28 - pico-train - INFO - Step 87000 -- 📊 Evaluation Results 2025-08-31 12:33:28 - pico-train - INFO - └── paloma: inf 2025-08-31 12:33:29 - pico-train - INFO - Step 87000 -- 🔄 Training Metrics 2025-08-31 12:33:29 - pico-train - INFO - ├── Loss: 4.7844 2025-08-31 12:33:29 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:33:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:33:29 - pico-train - INFO - Step 87000 -- 📈 Saving Learning Dynamics 2025-08-31 12:34:43 - pico-train - INFO - Step 87100 -- 🔄 Training Metrics 2025-08-31 12:34:43 - pico-train - INFO - ├── Loss: 4.7705 2025-08-31 12:34:43 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:34:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:35:54 - pico-train - INFO - Step 87200 -- 🔄 Training Metrics 2025-08-31 12:35:54 - pico-train - INFO - ├── Loss: 4.7808 2025-08-31 12:35:54 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:35:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:37:06 - pico-train - INFO - Step 87300 -- 🔄 Training Metrics 2025-08-31 12:37:06 - pico-train - INFO - ├── Loss: 4.7454 2025-08-31 12:37:06 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:37:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:38:16 - pico-train - INFO - Step 87400 -- 🔄 Training Metrics 2025-08-31 12:38:16 - pico-train - INFO - ├── Loss: 4.7594 2025-08-31 12:38:16 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:38:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:39:28 - pico-train - INFO - Step 87500 -- 🔄 Training Metrics 2025-08-31 12:39:28 - pico-train - INFO - ├── Loss: 4.7863 2025-08-31 12:39:28 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:39:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:40:39 - pico-train - INFO - Step 87600 -- 🔄 Training Metrics 2025-08-31 12:40:39 - pico-train - INFO - ├── Loss: 4.7863 2025-08-31 12:40:39 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:40:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:41:50 - pico-train - INFO - Step 87700 -- 🔄 Training Metrics 2025-08-31 12:41:50 - pico-train - INFO - ├── Loss: 4.7821 2025-08-31 12:41:50 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:41:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:43:01 - pico-train - INFO - Step 87800 -- 🔄 Training Metrics 2025-08-31 12:43:01 - pico-train - INFO - ├── Loss: 4.7758 2025-08-31 12:43:01 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:43:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:44:12 - pico-train - INFO - Step 87900 -- 🔄 Training Metrics 2025-08-31 12:44:12 - pico-train - INFO - ├── Loss: 4.7932 2025-08-31 12:44:12 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:44:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:45:22 - pico-train - INFO - Step 88000 -- 💾 Saving Checkpoint 2025-08-31 12:47:24 - pico-train - INFO - Step 88000 -- 📊 Evaluation Results 2025-08-31 12:47:24 - pico-train - INFO - └── paloma: inf 2025-08-31 12:47:24 - pico-train - INFO - Step 88000 -- 🔄 Training Metrics 2025-08-31 12:47:24 - pico-train - INFO - ├── Loss: 4.7787 2025-08-31 12:47:24 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:47:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:47:24 - pico-train - INFO - Step 88000 -- 📈 Saving Learning Dynamics 2025-08-31 12:48:38 - pico-train - INFO - Step 88100 -- 🔄 Training Metrics 2025-08-31 12:48:38 - pico-train - INFO - ├── Loss: 4.8045 2025-08-31 12:48:38 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:48:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:49:49 - pico-train - INFO - Step 88200 -- 🔄 Training Metrics 2025-08-31 12:49:49 - pico-train - INFO - ├── Loss: 4.7800 2025-08-31 12:49:49 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:49:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:51:00 - pico-train - INFO - Step 88300 -- 🔄 Training Metrics 2025-08-31 12:51:00 - pico-train - INFO - ├── Loss: 4.7828 2025-08-31 12:51:00 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:51:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:52:12 - pico-train - INFO - Step 88400 -- 🔄 Training Metrics 2025-08-31 12:52:12 - pico-train - INFO - ├── Loss: 4.7886 2025-08-31 12:52:12 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:52:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:53:23 - pico-train - INFO - Step 88500 -- 🔄 Training Metrics 2025-08-31 12:53:23 - pico-train - INFO - ├── Loss: 4.7917 2025-08-31 12:53:23 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:53:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:54:34 - pico-train - INFO - Step 88600 -- 🔄 Training Metrics 2025-08-31 12:54:34 - pico-train - INFO - ├── Loss: 4.7897 2025-08-31 12:54:34 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:54:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:55:45 - pico-train - INFO - Step 88700 -- 🔄 Training Metrics 2025-08-31 12:55:45 - pico-train - INFO - ├── Loss: 4.7861 2025-08-31 12:55:45 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:55:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:56:55 - pico-train - INFO - Step 88800 -- 🔄 Training Metrics 2025-08-31 12:56:55 - pico-train - INFO - ├── Loss: 4.7767 2025-08-31 12:56:55 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:56:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:58:07 - pico-train - INFO - Step 88900 -- 🔄 Training Metrics 2025-08-31 12:58:07 - pico-train - INFO - ├── Loss: 4.7696 2025-08-31 12:58:07 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 12:58:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 12:59:17 - pico-train - INFO - Step 89000 -- 💾 Saving Checkpoint 2025-08-31 13:01:18 - pico-train - INFO - Step 89000 -- 📊 Evaluation Results 2025-08-31 13:01:18 - pico-train - INFO - └── paloma: inf 2025-08-31 13:01:19 - pico-train - INFO - Step 89000 -- 🔄 Training Metrics 2025-08-31 13:01:19 - pico-train - INFO - ├── Loss: 4.7836 2025-08-31 13:01:19 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:01:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:01:19 - pico-train - INFO - Step 89000 -- 📈 Saving Learning Dynamics 2025-08-31 13:02:33 - pico-train - INFO - Step 89100 -- 🔄 Training Metrics 2025-08-31 13:02:33 - pico-train - INFO - ├── Loss: 4.7812 2025-08-31 13:02:33 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:02:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:03:44 - pico-train - INFO - Step 89200 -- 🔄 Training Metrics 2025-08-31 13:03:44 - pico-train - INFO - ├── Loss: 4.7896 2025-08-31 13:03:44 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:03:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:04:55 - pico-train - INFO - Step 89300 -- 🔄 Training Metrics 2025-08-31 13:04:55 - pico-train - INFO - ├── Loss: 4.7898 2025-08-31 13:04:55 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:04:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:06:06 - pico-train - INFO - Step 89400 -- 🔄 Training Metrics 2025-08-31 13:06:06 - pico-train - INFO - ├── Loss: 4.7914 2025-08-31 13:06:06 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:06:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:07:17 - pico-train - INFO - Step 89500 -- 🔄 Training Metrics 2025-08-31 13:07:17 - pico-train - INFO - ├── Loss: 4.7922 2025-08-31 13:07:17 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:07:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:08:29 - pico-train - INFO - Step 89600 -- 🔄 Training Metrics 2025-08-31 13:08:29 - pico-train - INFO - ├── Loss: 4.7673 2025-08-31 13:08:29 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:08:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:09:40 - pico-train - INFO - Step 89700 -- 🔄 Training Metrics 2025-08-31 13:09:40 - pico-train - INFO - ├── Loss: 4.7810 2025-08-31 13:09:40 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:09:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:10:51 - pico-train - INFO - Step 89800 -- 🔄 Training Metrics 2025-08-31 13:10:51 - pico-train - INFO - ├── Loss: 4.7763 2025-08-31 13:10:51 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:10:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:12:02 - pico-train - INFO - Step 89900 -- 🔄 Training Metrics 2025-08-31 13:12:02 - pico-train - INFO - ├── Loss: 4.7684 2025-08-31 13:12:02 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:12:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:13:12 - pico-train - INFO - Step 90000 -- 💾 Saving Checkpoint 2025-08-31 13:15:13 - pico-train - INFO - Step 90000 -- 📊 Evaluation Results 2025-08-31 13:15:13 - pico-train - INFO - └── paloma: inf 2025-08-31 13:15:14 - pico-train - INFO - Step 90000 -- 🔄 Training Metrics 2025-08-31 13:15:14 - pico-train - INFO - ├── Loss: 4.7821 2025-08-31 13:15:14 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:15:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:15:14 - pico-train - INFO - Step 90000 -- 📈 Saving Learning Dynamics 2025-08-31 13:16:28 - pico-train - INFO - Step 90100 -- 🔄 Training Metrics 2025-08-31 13:16:28 - pico-train - INFO - ├── Loss: 4.7878 2025-08-31 13:16:28 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:16:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:17:38 - pico-train - INFO - Step 90200 -- 🔄 Training Metrics 2025-08-31 13:17:38 - pico-train - INFO - ├── Loss: 4.7773 2025-08-31 13:17:38 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:17:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:18:49 - pico-train - INFO - Step 90300 -- 🔄 Training Metrics 2025-08-31 13:18:49 - pico-train - INFO - ├── Loss: 4.7771 2025-08-31 13:18:49 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:18:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:20:00 - pico-train - INFO - Step 90400 -- 🔄 Training Metrics 2025-08-31 13:20:00 - pico-train - INFO - ├── Loss: 4.7744 2025-08-31 13:20:00 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:20:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:21:11 - pico-train - INFO - Step 90500 -- 🔄 Training Metrics 2025-08-31 13:21:11 - pico-train - INFO - ├── Loss: 4.7964 2025-08-31 13:21:11 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:21:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:22:21 - pico-train - INFO - Step 90600 -- 🔄 Training Metrics 2025-08-31 13:22:21 - pico-train - INFO - ├── Loss: 4.7864 2025-08-31 13:22:21 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:22:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:23:32 - pico-train - INFO - Step 90700 -- 🔄 Training Metrics 2025-08-31 13:23:32 - pico-train - INFO - ├── Loss: 4.7873 2025-08-31 13:23:32 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:23:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:24:43 - pico-train - INFO - Step 90800 -- 🔄 Training Metrics 2025-08-31 13:24:43 - pico-train - INFO - ├── Loss: 4.7767 2025-08-31 13:24:43 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:24:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:25:54 - pico-train - INFO - Step 90900 -- 🔄 Training Metrics 2025-08-31 13:25:54 - pico-train - INFO - ├── Loss: 4.7846 2025-08-31 13:25:54 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:25:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:27:04 - pico-train - INFO - Step 91000 -- 💾 Saving Checkpoint 2025-08-31 13:29:06 - pico-train - INFO - Step 91000 -- 📊 Evaluation Results 2025-08-31 13:29:06 - pico-train - INFO - └── paloma: inf 2025-08-31 13:29:07 - pico-train - INFO - Step 91000 -- 🔄 Training Metrics 2025-08-31 13:29:07 - pico-train - INFO - ├── Loss: 4.7906 2025-08-31 13:29:07 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:29:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:29:07 - pico-train - INFO - Step 91000 -- 📈 Saving Learning Dynamics 2025-08-31 13:30:20 - pico-train - INFO - Step 91100 -- 🔄 Training Metrics 2025-08-31 13:30:20 - pico-train - INFO - ├── Loss: 4.7907 2025-08-31 13:30:20 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:30:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:31:31 - pico-train - INFO - Step 91200 -- 🔄 Training Metrics 2025-08-31 13:31:31 - pico-train - INFO - ├── Loss: 4.7947 2025-08-31 13:31:31 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:31:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:32:43 - pico-train - INFO - Step 91300 -- 🔄 Training Metrics 2025-08-31 13:32:43 - pico-train - INFO - ├── Loss: 4.7752 2025-08-31 13:32:43 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:32:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:33:54 - pico-train - INFO - Step 91400 -- 🔄 Training Metrics 2025-08-31 13:33:54 - pico-train - INFO - ├── Loss: 4.7782 2025-08-31 13:33:54 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:33:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:35:04 - pico-train - INFO - Step 91500 -- 🔄 Training Metrics 2025-08-31 13:35:04 - pico-train - INFO - ├── Loss: 4.7775 2025-08-31 13:35:04 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:35:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:36:15 - pico-train - INFO - Step 91600 -- 🔄 Training Metrics 2025-08-31 13:36:15 - pico-train - INFO - ├── Loss: 4.7964 2025-08-31 13:36:15 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:36:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:37:26 - pico-train - INFO - Step 91700 -- 🔄 Training Metrics 2025-08-31 13:37:26 - pico-train - INFO - ├── Loss: 4.7612 2025-08-31 13:37:26 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:37:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:38:37 - pico-train - INFO - Step 91800 -- 🔄 Training Metrics 2025-08-31 13:38:37 - pico-train - INFO - ├── Loss: 4.7855 2025-08-31 13:38:37 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:38:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:39:49 - pico-train - INFO - Step 91900 -- 🔄 Training Metrics 2025-08-31 13:39:49 - pico-train - INFO - ├── Loss: 4.7587 2025-08-31 13:39:49 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:39:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:40:59 - pico-train - INFO - Step 92000 -- 💾 Saving Checkpoint 2025-08-31 13:43:01 - pico-train - INFO - Step 92000 -- 📊 Evaluation Results 2025-08-31 13:43:01 - pico-train - INFO - └── paloma: inf 2025-08-31 13:43:01 - pico-train - INFO - Step 92000 -- 🔄 Training Metrics 2025-08-31 13:43:01 - pico-train - INFO - ├── Loss: 4.7725 2025-08-31 13:43:01 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:43:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:43:01 - pico-train - INFO - Step 92000 -- 📈 Saving Learning Dynamics 2025-08-31 13:44:15 - pico-train - INFO - Step 92100 -- 🔄 Training Metrics 2025-08-31 13:44:15 - pico-train - INFO - ├── Loss: 4.7884 2025-08-31 13:44:15 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:44:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:45:27 - pico-train - INFO - Step 92200 -- 🔄 Training Metrics 2025-08-31 13:45:27 - pico-train - INFO - ├── Loss: 4.7677 2025-08-31 13:45:27 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:45:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:46:38 - pico-train - INFO - Step 92300 -- 🔄 Training Metrics 2025-08-31 13:46:38 - pico-train - INFO - ├── Loss: 4.7904 2025-08-31 13:46:38 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:46:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:47:49 - pico-train - INFO - Step 92400 -- 🔄 Training Metrics 2025-08-31 13:47:49 - pico-train - INFO - ├── Loss: 4.7862 2025-08-31 13:47:49 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:47:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:49:00 - pico-train - INFO - Step 92500 -- 🔄 Training Metrics 2025-08-31 13:49:00 - pico-train - INFO - ├── Loss: 4.8080 2025-08-31 13:49:00 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:49:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:50:11 - pico-train - INFO - Step 92600 -- 🔄 Training Metrics 2025-08-31 13:50:11 - pico-train - INFO - ├── Loss: 4.7588 2025-08-31 13:50:11 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:50:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:51:22 - pico-train - INFO - Step 92700 -- 🔄 Training Metrics 2025-08-31 13:51:22 - pico-train - INFO - ├── Loss: 4.8001 2025-08-31 13:51:22 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:51:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:52:33 - pico-train - INFO - Step 92800 -- 🔄 Training Metrics 2025-08-31 13:52:33 - pico-train - INFO - ├── Loss: 4.8003 2025-08-31 13:52:33 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:52:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:53:44 - pico-train - INFO - Step 92900 -- 🔄 Training Metrics 2025-08-31 13:53:44 - pico-train - INFO - ├── Loss: 4.7780 2025-08-31 13:53:44 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:53:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:54:54 - pico-train - INFO - Step 93000 -- 💾 Saving Checkpoint 2025-08-31 13:56:55 - pico-train - INFO - Step 93000 -- 📊 Evaluation Results 2025-08-31 13:56:55 - pico-train - INFO - └── paloma: inf 2025-08-31 13:56:56 - pico-train - INFO - Step 93000 -- 🔄 Training Metrics 2025-08-31 13:56:56 - pico-train - INFO - ├── Loss: 4.7952 2025-08-31 13:56:56 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:56:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:56:56 - pico-train - INFO - Step 93000 -- 📈 Saving Learning Dynamics 2025-08-31 13:58:10 - pico-train - INFO - Step 93100 -- 🔄 Training Metrics 2025-08-31 13:58:10 - pico-train - INFO - ├── Loss: 4.7548 2025-08-31 13:58:10 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:58:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 13:59:22 - pico-train - INFO - Step 93200 -- 🔄 Training Metrics 2025-08-31 13:59:22 - pico-train - INFO - ├── Loss: 4.7780 2025-08-31 13:59:22 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 13:59:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:00:33 - pico-train - INFO - Step 93300 -- 🔄 Training Metrics 2025-08-31 14:00:33 - pico-train - INFO - ├── Loss: 4.7779 2025-08-31 14:00:33 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:00:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:01:43 - pico-train - INFO - Step 93400 -- 🔄 Training Metrics 2025-08-31 14:01:43 - pico-train - INFO - ├── Loss: 4.7857 2025-08-31 14:01:43 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:01:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:02:55 - pico-train - INFO - Step 93500 -- 🔄 Training Metrics 2025-08-31 14:02:55 - pico-train - INFO - ├── Loss: 4.7840 2025-08-31 14:02:55 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:02:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:04:06 - pico-train - INFO - Step 93600 -- 🔄 Training Metrics 2025-08-31 14:04:06 - pico-train - INFO - ├── Loss: 4.7887 2025-08-31 14:04:06 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:04:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:05:18 - pico-train - INFO - Step 93700 -- 🔄 Training Metrics 2025-08-31 14:05:18 - pico-train - INFO - ├── Loss: 4.7694 2025-08-31 14:05:18 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:05:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:06:28 - pico-train - INFO - Step 93800 -- 🔄 Training Metrics 2025-08-31 14:06:28 - pico-train - INFO - ├── Loss: 4.7762 2025-08-31 14:06:28 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:06:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:07:39 - pico-train - INFO - Step 93900 -- 🔄 Training Metrics 2025-08-31 14:07:39 - pico-train - INFO - ├── Loss: 4.7933 2025-08-31 14:07:39 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:07:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:08:50 - pico-train - INFO - Step 94000 -- 💾 Saving Checkpoint 2025-08-31 14:10:52 - pico-train - INFO - Step 94000 -- 📊 Evaluation Results 2025-08-31 14:10:52 - pico-train - INFO - └── paloma: inf 2025-08-31 14:10:53 - pico-train - INFO - Step 94000 -- 🔄 Training Metrics 2025-08-31 14:10:53 - pico-train - INFO - ├── Loss: 4.7827 2025-08-31 14:10:53 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:10:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:10:53 - pico-train - INFO - Step 94000 -- 📈 Saving Learning Dynamics 2025-08-31 14:12:07 - pico-train - INFO - Step 94100 -- 🔄 Training Metrics 2025-08-31 14:12:07 - pico-train - INFO - ├── Loss: 4.7810 2025-08-31 14:12:07 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:12:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:13:18 - pico-train - INFO - Step 94200 -- 🔄 Training Metrics 2025-08-31 14:13:18 - pico-train - INFO - ├── Loss: 4.7890 2025-08-31 14:13:18 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:13:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:14:28 - pico-train - INFO - Step 94300 -- 🔄 Training Metrics 2025-08-31 14:14:28 - pico-train - INFO - ├── Loss: 4.7834 2025-08-31 14:14:28 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:14:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:15:39 - pico-train - INFO - Step 94400 -- 🔄 Training Metrics 2025-08-31 14:15:39 - pico-train - INFO - ├── Loss: 4.7593 2025-08-31 14:15:39 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:15:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:16:51 - pico-train - INFO - Step 94500 -- 🔄 Training Metrics 2025-08-31 14:16:51 - pico-train - INFO - ├── Loss: 4.7865 2025-08-31 14:16:51 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:16:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:18:02 - pico-train - INFO - Step 94600 -- 🔄 Training Metrics 2025-08-31 14:18:02 - pico-train - INFO - ├── Loss: 4.7815 2025-08-31 14:18:02 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:18:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:19:13 - pico-train - INFO - Step 94700 -- 🔄 Training Metrics 2025-08-31 14:19:13 - pico-train - INFO - ├── Loss: 4.7722 2025-08-31 14:19:13 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:19:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:20:24 - pico-train - INFO - Step 94800 -- 🔄 Training Metrics 2025-08-31 14:20:24 - pico-train - INFO - ├── Loss: 4.7647 2025-08-31 14:20:24 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:20:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:21:35 - pico-train - INFO - Step 94900 -- 🔄 Training Metrics 2025-08-31 14:21:35 - pico-train - INFO - ├── Loss: 4.7664 2025-08-31 14:21:35 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:21:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:22:45 - pico-train - INFO - Step 95000 -- 💾 Saving Checkpoint 2025-08-31 14:24:47 - pico-train - INFO - Step 95000 -- 📊 Evaluation Results 2025-08-31 14:24:47 - pico-train - INFO - └── paloma: inf 2025-08-31 14:24:47 - pico-train - INFO - Step 95000 -- 🔄 Training Metrics 2025-08-31 14:24:47 - pico-train - INFO - ├── Loss: 4.7738 2025-08-31 14:24:47 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:24:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:24:47 - pico-train - INFO - Step 95000 -- 📈 Saving Learning Dynamics 2025-08-31 14:26:01 - pico-train - INFO - Step 95100 -- 🔄 Training Metrics 2025-08-31 14:26:01 - pico-train - INFO - ├── Loss: 4.7868 2025-08-31 14:26:01 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:26:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:27:12 - pico-train - INFO - Step 95200 -- 🔄 Training Metrics 2025-08-31 14:27:12 - pico-train - INFO - ├── Loss: 4.7701 2025-08-31 14:27:12 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:27:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:28:23 - pico-train - INFO - Step 95300 -- 🔄 Training Metrics 2025-08-31 14:28:23 - pico-train - INFO - ├── Loss: 4.7908 2025-08-31 14:28:23 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:28:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:29:33 - pico-train - INFO - Step 95400 -- 🔄 Training Metrics 2025-08-31 14:29:33 - pico-train - INFO - ├── Loss: 4.7643 2025-08-31 14:29:33 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:29:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:30:44 - pico-train - INFO - Step 95500 -- 🔄 Training Metrics 2025-08-31 14:30:44 - pico-train - INFO - ├── Loss: 4.8021 2025-08-31 14:30:44 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:30:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-31 14:32:19 - pico-train - INFO - Step 95600 -- 🔄 Training Metrics 2025-08-31 14:32:19 - pico-train - INFO - ├── Loss: 4.7821 2025-08-31 14:32:19 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-31 14:32:19 - pico-train - INFO - └── Inf/NaN count: 0