2025-08-30 05:22:55 - pico-train - INFO - Step 0 -- 📊 Evaluation Results 2025-08-30 05:22:55 - pico-train - INFO - └── paloma: inf 2025-08-30 05:22:56 - pico-train - INFO - ================================================== 2025-08-30 05:22:56 - pico-train - INFO - ✨ Training Configuration 2025-08-30 05:22:56 - pico-train - INFO - ================================================== 2025-08-30 05:22:56 - pico-train - INFO - ╭─────────────────────────────────────────────────────╮ 2025-08-30 05:22:56 - pico-train - INFO - │ checkpointing: │ 2025-08-30 05:22:56 - pico-train - INFO - │ checkpoints_dir: checkpoints │ 2025-08-30 05:22:56 - pico-train - INFO - │ evaluation: │ 2025-08-30 05:22:56 - pico-train - INFO - │ eval_results_dir: eval_results │ 2025-08-30 05:22:56 - pico-train - INFO - │ fabric_checkpoint_dir: fabric_state │ 2025-08-30 05:22:56 - pico-train - INFO - │ fabric_checkpoint_filename: checkpoint.pt │ 2025-08-30 05:22:56 - pico-train - INFO - │ hf_checkpoint: │ 2025-08-30 05:22:56 - pico-train - INFO - │ collection_slug: null │ 2025-08-30 05:22:56 - pico-train - INFO - │ repo_id: ThomasTheMaker/pico-decoder-tiny │ 2025-08-30 05:22:56 - pico-train - INFO - │ learning_dynamics: │ 2025-08-30 05:22:56 - pico-train - INFO - │ batch_size: 1 │ 2025-08-30 05:22:56 - pico-train - INFO - │ eval_data: null │ 2025-08-30 05:22:56 - pico-train - INFO - │ layer_suffixes: │ 2025-08-30 05:22:56 - pico-train - INFO - │ - attention.v_proj │ 2025-08-30 05:22:56 - pico-train - INFO - │ - attention.o_proj │ 2025-08-30 05:22:56 - pico-train - INFO - │ - swiglu.w_2 │ 2025-08-30 05:22:56 - pico-train - INFO - │ sequence_idx: -1 │ 2025-08-30 05:22:56 - pico-train - INFO - │ learning_dynamics_dir: learning_dynamics │ 2025-08-30 05:22:56 - pico-train - INFO - │ logs_dir: logs │ 2025-08-30 05:22:56 - pico-train - INFO - │ run_name: pico-decoder-tiny-dolma10M-v1 │ 2025-08-30 05:22:56 - pico-train - INFO - │ runs_dir: runs │ 2025-08-30 05:22:56 - pico-train - INFO - │ save_every_n_steps: 2000 │ 2025-08-30 05:22:56 - pico-train - INFO - │ save_to_hf: true │ 2025-08-30 05:22:56 - pico-train - INFO - │ training: │ 2025-08-30 05:22:56 - pico-train - INFO - │ auto_resume: true │ 2025-08-30 05:22:56 - pico-train - INFO - │ data: │ 2025-08-30 05:22:56 - pico-train - INFO - │ dataloader: │ 2025-08-30 05:22:56 - pico-train - INFO - │ batch_size: 16 │ 2025-08-30 05:22:56 - pico-train - INFO - │ dataset: │ 2025-08-30 05:22:56 - pico-train - INFO - │ name: ThomasTheMaker/pretokenized-dolma-10M │ 2025-08-30 05:22:56 - pico-train - INFO - │ tokenizer: │ 2025-08-30 05:22:56 - pico-train - INFO - │ name: allenai/OLMo-7B-0724-hf │ 2025-08-30 05:22:56 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-30 05:22:56 - pico-train - INFO - │ evaluation: │ 2025-08-30 05:22:56 - pico-train - INFO - │ metrics: │ 2025-08-30 05:22:56 - pico-train - INFO - │ - paloma │ 2025-08-30 05:22:56 - pico-train - INFO - │ paloma: │ 2025-08-30 05:22:56 - pico-train - INFO - │ batch_size: 1 │ 2025-08-30 05:22:56 - pico-train - INFO - │ dataset_name: pico-lm/pretokenized-paloma-tinsy │ 2025-08-30 05:22:56 - pico-train - INFO - │ dataset_split: val │ 2025-08-30 05:22:56 - pico-train - INFO - │ max_length: 2048 │ 2025-08-30 05:22:56 - pico-train - INFO - │ model: │ 2025-08-30 05:22:56 - pico-train - INFO - │ activation_hidden_dim: 384 │ 2025-08-30 05:22:56 - pico-train - INFO - │ attention_n_heads: 12 │ 2025-08-30 05:22:56 - pico-train - INFO - │ attention_n_kv_heads: 4 │ 2025-08-30 05:22:56 - pico-train - INFO - │ batch_size: 1024 │ 2025-08-30 05:22:56 - pico-train - INFO - │ d_model: 96 │ 2025-08-30 05:22:56 - pico-train - INFO - │ max_seq_len: 2048 │ 2025-08-30 05:22:56 - pico-train - INFO - │ model_type: pico_decoder │ 2025-08-30 05:22:56 - pico-train - INFO - │ n_layers: 12 │ 2025-08-30 05:22:56 - pico-train - INFO - │ norm_eps: 1.0e-06 │ 2025-08-30 05:22:56 - pico-train - INFO - │ position_emb_theta: 10000.0 │ 2025-08-30 05:22:56 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-30 05:22:56 - pico-train - INFO - │ monitoring: │ 2025-08-30 05:22:56 - pico-train - INFO - │ logging: │ 2025-08-30 05:22:56 - pico-train - INFO - │ log_every_n_steps: 100 │ 2025-08-30 05:22:56 - pico-train - INFO - │ log_level: INFO │ 2025-08-30 05:22:56 - pico-train - INFO - │ save_to_wandb: false │ 2025-08-30 05:22:56 - pico-train - INFO - │ wandb: │ 2025-08-30 05:22:56 - pico-train - INFO - │ entity: boymyc │ 2025-08-30 05:22:56 - pico-train - INFO - │ project: pico-decoder-tiny │ 2025-08-30 05:22:56 - pico-train - INFO - │ training: │ 2025-08-30 05:22:56 - pico-train - INFO - │ fabric: │ 2025-08-30 05:22:56 - pico-train - INFO - │ accelerator: cuda │ 2025-08-30 05:22:56 - pico-train - INFO - │ num_devices: 1 │ 2025-08-30 05:22:56 - pico-train - INFO - │ num_nodes: 1 │ 2025-08-30 05:22:56 - pico-train - INFO - │ precision: bf16-mixed │ 2025-08-30 05:22:56 - pico-train - INFO - │ max_steps: 100000 │ 2025-08-30 05:22:56 - pico-train - INFO - │ optimization: │ 2025-08-30 05:22:56 - pico-train - INFO - │ gradient_accumulation_steps: 1 │ 2025-08-30 05:22:56 - pico-train - INFO - │ lr: 0.0002 │ 2025-08-30 05:22:56 - pico-train - INFO - │ lr_scheduler: cosine │ 2025-08-30 05:22:56 - pico-train - INFO - │ lr_warmup_steps: 2000 │ 2025-08-30 05:22:56 - pico-train - INFO - │ optimizer: adamw │ 2025-08-30 05:22:56 - pico-train - INFO - │ │ 2025-08-30 05:22:56 - pico-train - INFO - ╰─────────────────────────────────────────────────────╯ 2025-08-30 05:22:56 - pico-train - INFO - ================================================== 2025-08-30 05:22:56 - pico-train - INFO - ⛭ Runtime Summary: 2025-08-30 05:22:56 - pico-train - INFO - ================================================== 2025-08-30 05:22:56 - pico-train - INFO - Starting from step: 0 2025-08-30 05:22:56 - pico-train - INFO - Model Setup: 2025-08-30 05:22:56 - pico-train - INFO - └─ Total Parameters: 11,282,784 2025-08-30 05:22:56 - pico-train - INFO - └─ Trainable Parameters: 11,282,784 2025-08-30 05:22:56 - pico-train - INFO - Distributed Setup: 2025-08-30 05:22:56 - pico-train - INFO - └─ Number of Devices: 1 2025-08-30 05:22:56 - pico-train - INFO - └─ Device Type: NVIDIA H100 80GB HBM3 2025-08-30 05:22:56 - pico-train - INFO - └─ Available Memory: 85.03 GB 2025-08-30 05:22:56 - pico-train - INFO - Software Setup: 2025-08-30 05:22:56 - pico-train - INFO - └─ Python Version: 3.12.3 2025-08-30 05:22:56 - pico-train - INFO - └─ PyTorch Version: 2.8.0+cu128 2025-08-30 05:22:56 - pico-train - INFO - └─ CUDA Version: 12.8 2025-08-30 05:22:56 - pico-train - INFO - └─ Operating System: Linux 6.8.0-71-generic 2025-08-30 05:22:56 - pico-train - INFO - Batch Size Configuration: 2025-08-30 05:22:56 - pico-train - INFO - └─ Global Batch Size: 16 2025-08-30 05:22:56 - pico-train - INFO - └─ Per Device Batch Size: 16 2025-08-30 05:22:56 - pico-train - INFO - └─ Gradient Accumulation Steps: 1 2025-08-30 05:22:56 - pico-train - INFO - ================================================== 2025-08-30 05:22:57 - pico-train - INFO - Step 0 -- 🔄 Training Metrics 2025-08-30 05:22:57 - pico-train - INFO - ├── Loss: 10.9884 2025-08-30 05:22:57 - pico-train - INFO - ├── Learning Rate: 0.00e+00 2025-08-30 05:22:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:22:57 - pico-train - INFO - Step 0 -- 📈 Saving Learning Dynamics 2025-08-30 05:23:55 - pico-train - INFO - Step 100 -- 🔄 Training Metrics 2025-08-30 05:23:55 - pico-train - INFO - ├── Loss: 10.9746 2025-08-30 05:23:55 - pico-train - INFO - ├── Learning Rate: 1.00e-05 2025-08-30 05:23:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:24:49 - pico-train - INFO - Step 200 -- 🔄 Training Metrics 2025-08-30 05:24:49 - pico-train - INFO - ├── Loss: 10.7653 2025-08-30 05:24:49 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-30 05:24:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:25:44 - pico-train - INFO - Step 300 -- 🔄 Training Metrics 2025-08-30 05:25:44 - pico-train - INFO - ├── Loss: 10.2902 2025-08-30 05:25:44 - pico-train - INFO - ├── Learning Rate: 3.00e-05 2025-08-30 05:25:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:26:38 - pico-train - INFO - Step 400 -- 🔄 Training Metrics 2025-08-30 05:26:38 - pico-train - INFO - ├── Loss: 9.8373 2025-08-30 05:26:38 - pico-train - INFO - ├── Learning Rate: 4.00e-05 2025-08-30 05:26:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:27:31 - pico-train - INFO - Step 500 -- 🔄 Training Metrics 2025-08-30 05:27:31 - pico-train - INFO - ├── Loss: 9.3629 2025-08-30 05:27:31 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-30 05:27:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:28:24 - pico-train - INFO - Step 600 -- 🔄 Training Metrics 2025-08-30 05:28:24 - pico-train - INFO - ├── Loss: 8.8887 2025-08-30 05:28:24 - pico-train - INFO - ├── Learning Rate: 6.00e-05 2025-08-30 05:28:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:29:19 - pico-train - INFO - Step 700 -- 🔄 Training Metrics 2025-08-30 05:29:19 - pico-train - INFO - ├── Loss: 8.4408 2025-08-30 05:29:19 - pico-train - INFO - ├── Learning Rate: 7.00e-05 2025-08-30 05:29:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:30:13 - pico-train - INFO - Step 800 -- 🔄 Training Metrics 2025-08-30 05:30:13 - pico-train - INFO - ├── Loss: 8.0906 2025-08-30 05:30:13 - pico-train - INFO - ├── Learning Rate: 8.00e-05 2025-08-30 05:30:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:31:07 - pico-train - INFO - Step 900 -- 🔄 Training Metrics 2025-08-30 05:31:07 - pico-train - INFO - ├── Loss: 7.8459 2025-08-30 05:31:07 - pico-train - INFO - ├── Learning Rate: 9.00e-05 2025-08-30 05:31:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:32:02 - pico-train - INFO - Step 1000 -- 🔄 Training Metrics 2025-08-30 05:32:02 - pico-train - INFO - ├── Loss: 7.6972 2025-08-30 05:32:02 - pico-train - INFO - ├── Learning Rate: 1.00e-04 2025-08-30 05:32:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:32:55 - pico-train - INFO - Step 1100 -- 🔄 Training Metrics 2025-08-30 05:32:55 - pico-train - INFO - ├── Loss: 7.5570 2025-08-30 05:32:55 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-30 05:32:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:33:48 - pico-train - INFO - Step 1200 -- 🔄 Training Metrics 2025-08-30 05:33:48 - pico-train - INFO - ├── Loss: 7.4823 2025-08-30 05:33:48 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-30 05:33:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:34:42 - pico-train - INFO - Step 1300 -- 🔄 Training Metrics 2025-08-30 05:34:42 - pico-train - INFO - ├── Loss: 7.3624 2025-08-30 05:34:42 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-30 05:34:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:35:33 - pico-train - INFO - Step 1400 -- 🔄 Training Metrics 2025-08-30 05:35:33 - pico-train - INFO - ├── Loss: 7.2538 2025-08-30 05:35:33 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-30 05:35:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:36:26 - pico-train - INFO - Step 1500 -- 🔄 Training Metrics 2025-08-30 05:36:26 - pico-train - INFO - ├── Loss: 7.1582 2025-08-30 05:36:26 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-30 05:36:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:37:18 - pico-train - INFO - Step 1600 -- 🔄 Training Metrics 2025-08-30 05:37:18 - pico-train - INFO - ├── Loss: 7.0462 2025-08-30 05:37:18 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 05:37:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:38:11 - pico-train - INFO - Step 1700 -- 🔄 Training Metrics 2025-08-30 05:38:11 - pico-train - INFO - ├── Loss: 6.9729 2025-08-30 05:38:11 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 05:38:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:39:04 - pico-train - INFO - Step 1800 -- 🔄 Training Metrics 2025-08-30 05:39:04 - pico-train - INFO - ├── Loss: 6.8825 2025-08-30 05:39:04 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 05:39:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:39:56 - pico-train - INFO - Step 1900 -- 🔄 Training Metrics 2025-08-30 05:39:56 - pico-train - INFO - ├── Loss: 6.8003 2025-08-30 05:39:56 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 05:39:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:40:48 - pico-train - INFO - Step 2000 -- 💾 Saving Checkpoint 2025-08-30 05:42:56 - pico-train - INFO - Step 2000 -- 📊 Evaluation Results 2025-08-30 05:42:56 - pico-train - INFO - └── paloma: 9.921214391079047e+20 2025-08-30 05:42:57 - pico-train - INFO - Step 2000 -- 🔄 Training Metrics 2025-08-30 05:42:57 - pico-train - INFO - ├── Loss: 6.7360 2025-08-30 05:42:57 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:42:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:42:57 - pico-train - INFO - Step 2000 -- 📈 Saving Learning Dynamics 2025-08-30 05:43:54 - pico-train - INFO - Step 2100 -- 🔄 Training Metrics 2025-08-30 05:43:54 - pico-train - INFO - ├── Loss: 6.6658 2025-08-30 05:43:54 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:43:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:44:47 - pico-train - INFO - Step 2200 -- 🔄 Training Metrics 2025-08-30 05:44:47 - pico-train - INFO - ├── Loss: 6.6040 2025-08-30 05:44:47 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:44:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:45:39 - pico-train - INFO - Step 2300 -- 🔄 Training Metrics 2025-08-30 05:45:39 - pico-train - INFO - ├── Loss: 6.5360 2025-08-30 05:45:39 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:45:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:46:31 - pico-train - INFO - Step 2400 -- 🔄 Training Metrics 2025-08-30 05:46:31 - pico-train - INFO - ├── Loss: 6.5011 2025-08-30 05:46:31 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:46:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:47:24 - pico-train - INFO - Step 2500 -- 🔄 Training Metrics 2025-08-30 05:47:24 - pico-train - INFO - ├── Loss: 6.4541 2025-08-30 05:47:24 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:47:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:48:17 - pico-train - INFO - Step 2600 -- 🔄 Training Metrics 2025-08-30 05:48:17 - pico-train - INFO - ├── Loss: 6.4299 2025-08-30 05:48:17 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:48:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:49:10 - pico-train - INFO - Step 2700 -- 🔄 Training Metrics 2025-08-30 05:49:10 - pico-train - INFO - ├── Loss: 6.3677 2025-08-30 05:49:10 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:49:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:50:02 - pico-train - INFO - Step 2800 -- 🔄 Training Metrics 2025-08-30 05:50:02 - pico-train - INFO - ├── Loss: 6.3537 2025-08-30 05:50:02 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:50:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:50:54 - pico-train - INFO - Step 2900 -- 🔄 Training Metrics 2025-08-30 05:50:54 - pico-train - INFO - ├── Loss: 6.3225 2025-08-30 05:50:54 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:50:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:51:47 - pico-train - INFO - Step 3000 -- 🔄 Training Metrics 2025-08-30 05:51:47 - pico-train - INFO - ├── Loss: 6.2806 2025-08-30 05:51:47 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:51:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:52:39 - pico-train - INFO - Step 3100 -- 🔄 Training Metrics 2025-08-30 05:52:39 - pico-train - INFO - ├── Loss: 6.2626 2025-08-30 05:52:39 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:52:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:53:32 - pico-train - INFO - Step 3200 -- 🔄 Training Metrics 2025-08-30 05:53:32 - pico-train - INFO - ├── Loss: 6.2206 2025-08-30 05:53:32 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:53:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:54:24 - pico-train - INFO - Step 3300 -- 🔄 Training Metrics 2025-08-30 05:54:24 - pico-train - INFO - ├── Loss: 6.2140 2025-08-30 05:54:24 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:54:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:55:17 - pico-train - INFO - Step 3400 -- 🔄 Training Metrics 2025-08-30 05:55:17 - pico-train - INFO - ├── Loss: 6.1525 2025-08-30 05:55:17 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:55:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:56:11 - pico-train - INFO - Step 3500 -- 🔄 Training Metrics 2025-08-30 05:56:11 - pico-train - INFO - ├── Loss: 6.1104 2025-08-30 05:56:11 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:56:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:57:05 - pico-train - INFO - Step 3600 -- 🔄 Training Metrics 2025-08-30 05:57:05 - pico-train - INFO - ├── Loss: 6.1327 2025-08-30 05:57:05 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:57:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:57:58 - pico-train - INFO - Step 3700 -- 🔄 Training Metrics 2025-08-30 05:57:58 - pico-train - INFO - ├── Loss: 6.1046 2025-08-30 05:57:58 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:57:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:58:51 - pico-train - INFO - Step 3800 -- 🔄 Training Metrics 2025-08-30 05:58:51 - pico-train - INFO - ├── Loss: 6.0910 2025-08-30 05:58:51 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:58:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 05:59:44 - pico-train - INFO - Step 3900 -- 🔄 Training Metrics 2025-08-30 05:59:44 - pico-train - INFO - ├── Loss: 6.0369 2025-08-30 05:59:44 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 05:59:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:00:36 - pico-train - INFO - Step 4000 -- 💾 Saving Checkpoint 2025-08-30 06:02:50 - pico-train - INFO - Step 4000 -- 📊 Evaluation Results 2025-08-30 06:02:50 - pico-train - INFO - └── paloma: 3.516233710165711e+23 2025-08-30 06:02:51 - pico-train - INFO - Step 4000 -- 🔄 Training Metrics 2025-08-30 06:02:51 - pico-train - INFO - ├── Loss: 6.0450 2025-08-30 06:02:51 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:02:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:02:51 - pico-train - INFO - Step 4000 -- 📈 Saving Learning Dynamics 2025-08-30 06:03:48 - pico-train - INFO - Step 4100 -- 🔄 Training Metrics 2025-08-30 06:03:48 - pico-train - INFO - ├── Loss: 6.0120 2025-08-30 06:03:48 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:03:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:04:39 - pico-train - INFO - Step 4200 -- 🔄 Training Metrics 2025-08-30 06:04:39 - pico-train - INFO - ├── Loss: 5.9897 2025-08-30 06:04:39 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:04:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:05:33 - pico-train - INFO - Step 4300 -- 🔄 Training Metrics 2025-08-30 06:05:33 - pico-train - INFO - ├── Loss: 5.9636 2025-08-30 06:05:33 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:05:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:06:25 - pico-train - INFO - Step 4400 -- 🔄 Training Metrics 2025-08-30 06:06:25 - pico-train - INFO - ├── Loss: 5.9759 2025-08-30 06:06:25 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:06:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:07:18 - pico-train - INFO - Step 4500 -- 🔄 Training Metrics 2025-08-30 06:07:18 - pico-train - INFO - ├── Loss: 5.9551 2025-08-30 06:07:18 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:07:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:08:10 - pico-train - INFO - Step 4600 -- 🔄 Training Metrics 2025-08-30 06:08:10 - pico-train - INFO - ├── Loss: 5.9165 2025-08-30 06:08:10 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:08:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:09:02 - pico-train - INFO - Step 4700 -- 🔄 Training Metrics 2025-08-30 06:09:02 - pico-train - INFO - ├── Loss: 5.8939 2025-08-30 06:09:02 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:09:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:09:54 - pico-train - INFO - Step 4800 -- 🔄 Training Metrics 2025-08-30 06:09:54 - pico-train - INFO - ├── Loss: 5.8769 2025-08-30 06:09:54 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:09:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:10:47 - pico-train - INFO - Step 4900 -- 🔄 Training Metrics 2025-08-30 06:10:47 - pico-train - INFO - ├── Loss: 5.8605 2025-08-30 06:10:47 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:10:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:11:39 - pico-train - INFO - Step 5000 -- 🔄 Training Metrics 2025-08-30 06:11:39 - pico-train - INFO - ├── Loss: 5.8727 2025-08-30 06:11:39 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:11:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:12:31 - pico-train - INFO - Step 5100 -- 🔄 Training Metrics 2025-08-30 06:12:31 - pico-train - INFO - ├── Loss: 5.8446 2025-08-30 06:12:31 - pico-train - INFO - ├── Learning Rate: 2.00e-04 2025-08-30 06:12:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:13:24 - pico-train - INFO - Step 5200 -- 🔄 Training Metrics 2025-08-30 06:13:24 - pico-train - INFO - ├── Loss: 5.8289 2025-08-30 06:13:24 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:13:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:14:16 - pico-train - INFO - Step 5300 -- 🔄 Training Metrics 2025-08-30 06:14:16 - pico-train - INFO - ├── Loss: 5.8220 2025-08-30 06:14:16 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:14:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:15:09 - pico-train - INFO - Step 5400 -- 🔄 Training Metrics 2025-08-30 06:15:09 - pico-train - INFO - ├── Loss: 5.8132 2025-08-30 06:15:09 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:15:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:16:01 - pico-train - INFO - Step 5500 -- 🔄 Training Metrics 2025-08-30 06:16:01 - pico-train - INFO - ├── Loss: 5.7878 2025-08-30 06:16:01 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:16:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:16:53 - pico-train - INFO - Step 5600 -- 🔄 Training Metrics 2025-08-30 06:16:53 - pico-train - INFO - ├── Loss: 5.7639 2025-08-30 06:16:53 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:16:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:17:45 - pico-train - INFO - Step 5700 -- 🔄 Training Metrics 2025-08-30 06:17:45 - pico-train - INFO - ├── Loss: 5.7698 2025-08-30 06:17:45 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:17:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:18:38 - pico-train - INFO - Step 5800 -- 🔄 Training Metrics 2025-08-30 06:18:38 - pico-train - INFO - ├── Loss: 5.7458 2025-08-30 06:18:38 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:18:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:19:31 - pico-train - INFO - Step 5900 -- 🔄 Training Metrics 2025-08-30 06:19:31 - pico-train - INFO - ├── Loss: 5.7482 2025-08-30 06:19:31 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:19:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:20:23 - pico-train - INFO - Step 6000 -- 💾 Saving Checkpoint 2025-08-30 06:22:23 - pico-train - INFO - Step 6000 -- 📊 Evaluation Results 2025-08-30 06:22:23 - pico-train - INFO - └── paloma: 5.501352274432362e+26 2025-08-30 06:22:25 - pico-train - INFO - Step 6000 -- 🔄 Training Metrics 2025-08-30 06:22:25 - pico-train - INFO - ├── Loss: 5.7402 2025-08-30 06:22:25 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:22:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:22:25 - pico-train - INFO - Step 6000 -- 📈 Saving Learning Dynamics 2025-08-30 06:23:21 - pico-train - INFO - Step 6100 -- 🔄 Training Metrics 2025-08-30 06:23:21 - pico-train - INFO - ├── Loss: 5.7377 2025-08-30 06:23:21 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:23:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:24:13 - pico-train - INFO - Step 6200 -- 🔄 Training Metrics 2025-08-30 06:24:13 - pico-train - INFO - ├── Loss: 5.6952 2025-08-30 06:24:13 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:24:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:25:06 - pico-train - INFO - Step 6300 -- 🔄 Training Metrics 2025-08-30 06:25:06 - pico-train - INFO - ├── Loss: 5.6845 2025-08-30 06:25:06 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:25:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:26:00 - pico-train - INFO - Step 6400 -- 🔄 Training Metrics 2025-08-30 06:26:00 - pico-train - INFO - ├── Loss: 5.6903 2025-08-30 06:26:00 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:26:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:26:53 - pico-train - INFO - Step 6500 -- 🔄 Training Metrics 2025-08-30 06:26:53 - pico-train - INFO - ├── Loss: 5.6877 2025-08-30 06:26:53 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:26:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:27:47 - pico-train - INFO - Step 6600 -- 🔄 Training Metrics 2025-08-30 06:27:47 - pico-train - INFO - ├── Loss: 5.6538 2025-08-30 06:27:47 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:27:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:28:41 - pico-train - INFO - Step 6700 -- 🔄 Training Metrics 2025-08-30 06:28:41 - pico-train - INFO - ├── Loss: 5.6437 2025-08-30 06:28:41 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:28:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:29:35 - pico-train - INFO - Step 6800 -- 🔄 Training Metrics 2025-08-30 06:29:35 - pico-train - INFO - ├── Loss: 5.6444 2025-08-30 06:29:35 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:29:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:30:28 - pico-train - INFO - Step 6900 -- 🔄 Training Metrics 2025-08-30 06:30:28 - pico-train - INFO - ├── Loss: 5.6238 2025-08-30 06:30:28 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:30:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:31:21 - pico-train - INFO - Step 7000 -- 🔄 Training Metrics 2025-08-30 06:31:21 - pico-train - INFO - ├── Loss: 5.6188 2025-08-30 06:31:21 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:31:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:32:14 - pico-train - INFO - Step 7100 -- 🔄 Training Metrics 2025-08-30 06:32:14 - pico-train - INFO - ├── Loss: 5.5782 2025-08-30 06:32:14 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:32:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:33:08 - pico-train - INFO - Step 7200 -- 🔄 Training Metrics 2025-08-30 06:33:08 - pico-train - INFO - ├── Loss: 5.6112 2025-08-30 06:33:08 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:33:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:34:01 - pico-train - INFO - Step 7300 -- 🔄 Training Metrics 2025-08-30 06:34:01 - pico-train - INFO - ├── Loss: 5.5985 2025-08-30 06:34:01 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:34:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:34:55 - pico-train - INFO - Step 7400 -- 🔄 Training Metrics 2025-08-30 06:34:55 - pico-train - INFO - ├── Loss: 5.6009 2025-08-30 06:34:55 - pico-train - INFO - ├── Learning Rate: 1.99e-04 2025-08-30 06:34:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:35:48 - pico-train - INFO - Step 7500 -- 🔄 Training Metrics 2025-08-30 06:35:48 - pico-train - INFO - ├── Loss: 5.5714 2025-08-30 06:35:48 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:35:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:36:41 - pico-train - INFO - Step 7600 -- 🔄 Training Metrics 2025-08-30 06:36:41 - pico-train - INFO - ├── Loss: 5.5714 2025-08-30 06:36:41 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:36:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:37:36 - pico-train - INFO - Step 7700 -- 🔄 Training Metrics 2025-08-30 06:37:36 - pico-train - INFO - ├── Loss: 5.5653 2025-08-30 06:37:36 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:37:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:38:28 - pico-train - INFO - Step 7800 -- 🔄 Training Metrics 2025-08-30 06:38:28 - pico-train - INFO - ├── Loss: 5.5559 2025-08-30 06:38:28 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:38:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:39:22 - pico-train - INFO - Step 7900 -- 🔄 Training Metrics 2025-08-30 06:39:22 - pico-train - INFO - ├── Loss: 5.5568 2025-08-30 06:39:22 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:39:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:40:15 - pico-train - INFO - Step 8000 -- 💾 Saving Checkpoint 2025-08-30 06:42:29 - pico-train - INFO - Step 8000 -- 📊 Evaluation Results 2025-08-30 06:42:29 - pico-train - INFO - └── paloma: 2.7741731039516784e+30 2025-08-30 06:42:33 - pico-train - INFO - Step 8000 -- 🔄 Training Metrics 2025-08-30 06:42:33 - pico-train - INFO - ├── Loss: 5.5269 2025-08-30 06:42:33 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:42:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:42:33 - pico-train - INFO - Step 8000 -- 📈 Saving Learning Dynamics 2025-08-30 06:43:31 - pico-train - INFO - Step 8100 -- 🔄 Training Metrics 2025-08-30 06:43:31 - pico-train - INFO - ├── Loss: 5.5294 2025-08-30 06:43:31 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:43:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:44:24 - pico-train - INFO - Step 8200 -- 🔄 Training Metrics 2025-08-30 06:44:24 - pico-train - INFO - ├── Loss: 5.5352 2025-08-30 06:44:24 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:44:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:45:16 - pico-train - INFO - Step 8300 -- 🔄 Training Metrics 2025-08-30 06:45:16 - pico-train - INFO - ├── Loss: 5.5280 2025-08-30 06:45:16 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:45:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:46:08 - pico-train - INFO - Step 8400 -- 🔄 Training Metrics 2025-08-30 06:46:08 - pico-train - INFO - ├── Loss: 5.4997 2025-08-30 06:46:08 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:46:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:47:00 - pico-train - INFO - Step 8500 -- 🔄 Training Metrics 2025-08-30 06:47:00 - pico-train - INFO - ├── Loss: 5.4873 2025-08-30 06:47:00 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:47:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:47:53 - pico-train - INFO - Step 8600 -- 🔄 Training Metrics 2025-08-30 06:47:53 - pico-train - INFO - ├── Loss: 5.5047 2025-08-30 06:47:53 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:47:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:48:45 - pico-train - INFO - Step 8700 -- 🔄 Training Metrics 2025-08-30 06:48:45 - pico-train - INFO - ├── Loss: 5.4809 2025-08-30 06:48:45 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:48:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:49:37 - pico-train - INFO - Step 8800 -- 🔄 Training Metrics 2025-08-30 06:49:37 - pico-train - INFO - ├── Loss: 5.4859 2025-08-30 06:49:37 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:49:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:50:30 - pico-train - INFO - Step 8900 -- 🔄 Training Metrics 2025-08-30 06:50:30 - pico-train - INFO - ├── Loss: 5.4690 2025-08-30 06:50:30 - pico-train - INFO - ├── Learning Rate: 1.98e-04 2025-08-30 06:50:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:51:23 - pico-train - INFO - Step 9000 -- 🔄 Training Metrics 2025-08-30 06:51:23 - pico-train - INFO - ├── Loss: 5.4476 2025-08-30 06:51:23 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:51:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:52:16 - pico-train - INFO - Step 9100 -- 🔄 Training Metrics 2025-08-30 06:52:16 - pico-train - INFO - ├── Loss: 5.4383 2025-08-30 06:52:16 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:52:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:53:07 - pico-train - INFO - Step 9200 -- 🔄 Training Metrics 2025-08-30 06:53:07 - pico-train - INFO - ├── Loss: 5.4569 2025-08-30 06:53:07 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:53:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:53:59 - pico-train - INFO - Step 9300 -- 🔄 Training Metrics 2025-08-30 06:53:59 - pico-train - INFO - ├── Loss: 5.4367 2025-08-30 06:53:59 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:53:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:54:52 - pico-train - INFO - Step 9400 -- 🔄 Training Metrics 2025-08-30 06:54:52 - pico-train - INFO - ├── Loss: 5.4623 2025-08-30 06:54:52 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:54:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:55:45 - pico-train - INFO - Step 9500 -- 🔄 Training Metrics 2025-08-30 06:55:45 - pico-train - INFO - ├── Loss: 5.4268 2025-08-30 06:55:45 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:55:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:56:37 - pico-train - INFO - Step 9600 -- 🔄 Training Metrics 2025-08-30 06:56:37 - pico-train - INFO - ├── Loss: 5.4639 2025-08-30 06:56:37 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:56:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:57:28 - pico-train - INFO - Step 9700 -- 🔄 Training Metrics 2025-08-30 06:57:28 - pico-train - INFO - ├── Loss: 5.4521 2025-08-30 06:57:28 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:57:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:58:21 - pico-train - INFO - Step 9800 -- 🔄 Training Metrics 2025-08-30 06:58:21 - pico-train - INFO - ├── Loss: 5.4139 2025-08-30 06:58:21 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:58:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 06:59:13 - pico-train - INFO - Step 9900 -- 🔄 Training Metrics 2025-08-30 06:59:13 - pico-train - INFO - ├── Loss: 5.4026 2025-08-30 06:59:13 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 06:59:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:00:05 - pico-train - INFO - Step 10000 -- 💾 Saving Checkpoint 2025-08-30 07:02:19 - pico-train - INFO - Step 10000 -- 📊 Evaluation Results 2025-08-30 07:02:19 - pico-train - INFO - └── paloma: 1.0181753654885411e+35 2025-08-30 07:02:21 - pico-train - INFO - Step 10000 -- 🔄 Training Metrics 2025-08-30 07:02:21 - pico-train - INFO - ├── Loss: 5.4191 2025-08-30 07:02:21 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 07:02:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:02:21 - pico-train - INFO - Step 10000 -- 📈 Saving Learning Dynamics 2025-08-30 07:03:18 - pico-train - INFO - Step 10100 -- 🔄 Training Metrics 2025-08-30 07:03:18 - pico-train - INFO - ├── Loss: 5.3756 2025-08-30 07:03:18 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 07:03:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:04:10 - pico-train - INFO - Step 10200 -- 🔄 Training Metrics 2025-08-30 07:04:10 - pico-train - INFO - ├── Loss: 5.3976 2025-08-30 07:04:10 - pico-train - INFO - ├── Learning Rate: 1.97e-04 2025-08-30 07:04:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:05:04 - pico-train - INFO - Step 10300 -- 🔄 Training Metrics 2025-08-30 07:05:04 - pico-train - INFO - ├── Loss: 5.4049 2025-08-30 07:05:04 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:05:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:05:56 - pico-train - INFO - Step 10400 -- 🔄 Training Metrics 2025-08-30 07:05:56 - pico-train - INFO - ├── Loss: 5.3991 2025-08-30 07:05:56 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:05:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:06:48 - pico-train - INFO - Step 10500 -- 🔄 Training Metrics 2025-08-30 07:06:48 - pico-train - INFO - ├── Loss: 5.4016 2025-08-30 07:06:48 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:06:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:07:40 - pico-train - INFO - Step 10600 -- 🔄 Training Metrics 2025-08-30 07:07:40 - pico-train - INFO - ├── Loss: 5.3924 2025-08-30 07:07:40 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:07:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:08:32 - pico-train - INFO - Step 10700 -- 🔄 Training Metrics 2025-08-30 07:08:32 - pico-train - INFO - ├── Loss: 5.3781 2025-08-30 07:08:32 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:08:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:09:25 - pico-train - INFO - Step 10800 -- 🔄 Training Metrics 2025-08-30 07:09:25 - pico-train - INFO - ├── Loss: 5.3433 2025-08-30 07:09:25 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:09:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:10:17 - pico-train - INFO - Step 10900 -- 🔄 Training Metrics 2025-08-30 07:10:17 - pico-train - INFO - ├── Loss: 5.3610 2025-08-30 07:10:17 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:10:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:11:09 - pico-train - INFO - Step 11000 -- 🔄 Training Metrics 2025-08-30 07:11:09 - pico-train - INFO - ├── Loss: 5.3561 2025-08-30 07:11:09 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:11:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:12:01 - pico-train - INFO - Step 11100 -- 🔄 Training Metrics 2025-08-30 07:12:01 - pico-train - INFO - ├── Loss: 5.3818 2025-08-30 07:12:01 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:12:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:12:53 - pico-train - INFO - Step 11200 -- 🔄 Training Metrics 2025-08-30 07:12:53 - pico-train - INFO - ├── Loss: 5.3596 2025-08-30 07:12:53 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:12:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:13:46 - pico-train - INFO - Step 11300 -- 🔄 Training Metrics 2025-08-30 07:13:46 - pico-train - INFO - ├── Loss: 5.3558 2025-08-30 07:13:46 - pico-train - INFO - ├── Learning Rate: 1.96e-04 2025-08-30 07:13:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:14:38 - pico-train - INFO - Step 11400 -- 🔄 Training Metrics 2025-08-30 07:14:38 - pico-train - INFO - ├── Loss: 5.3484 2025-08-30 07:14:38 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:14:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:15:31 - pico-train - INFO - Step 11500 -- 🔄 Training Metrics 2025-08-30 07:15:31 - pico-train - INFO - ├── Loss: 5.3399 2025-08-30 07:15:31 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:15:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:16:24 - pico-train - INFO - Step 11600 -- 🔄 Training Metrics 2025-08-30 07:16:24 - pico-train - INFO - ├── Loss: 5.3252 2025-08-30 07:16:24 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:16:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:17:17 - pico-train - INFO - Step 11700 -- 🔄 Training Metrics 2025-08-30 07:17:17 - pico-train - INFO - ├── Loss: 5.3194 2025-08-30 07:17:17 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:17:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:18:09 - pico-train - INFO - Step 11800 -- 🔄 Training Metrics 2025-08-30 07:18:09 - pico-train - INFO - ├── Loss: 5.3387 2025-08-30 07:18:09 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:18:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:19:01 - pico-train - INFO - Step 11900 -- 🔄 Training Metrics 2025-08-30 07:19:01 - pico-train - INFO - ├── Loss: 5.3459 2025-08-30 07:19:01 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:19:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:19:53 - pico-train - INFO - Step 12000 -- 💾 Saving Checkpoint 2025-08-30 07:22:04 - pico-train - INFO - Step 12000 -- 📊 Evaluation Results 2025-08-30 07:22:04 - pico-train - INFO - └── paloma: inf 2025-08-30 07:22:06 - pico-train - INFO - Step 12000 -- 🔄 Training Metrics 2025-08-30 07:22:06 - pico-train - INFO - ├── Loss: 5.3216 2025-08-30 07:22:06 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:22:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:22:06 - pico-train - INFO - Step 12000 -- 📈 Saving Learning Dynamics 2025-08-30 07:23:04 - pico-train - INFO - Step 12100 -- 🔄 Training Metrics 2025-08-30 07:23:04 - pico-train - INFO - ├── Loss: 5.3164 2025-08-30 07:23:04 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:23:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:23:57 - pico-train - INFO - Step 12200 -- 🔄 Training Metrics 2025-08-30 07:23:57 - pico-train - INFO - ├── Loss: 5.3075 2025-08-30 07:23:57 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:23:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:24:50 - pico-train - INFO - Step 12300 -- 🔄 Training Metrics 2025-08-30 07:24:50 - pico-train - INFO - ├── Loss: 5.2908 2025-08-30 07:24:50 - pico-train - INFO - ├── Learning Rate: 1.95e-04 2025-08-30 07:24:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:25:43 - pico-train - INFO - Step 12400 -- 🔄 Training Metrics 2025-08-30 07:25:43 - pico-train - INFO - ├── Loss: 5.2970 2025-08-30 07:25:43 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:25:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:26:35 - pico-train - INFO - Step 12500 -- 🔄 Training Metrics 2025-08-30 07:26:35 - pico-train - INFO - ├── Loss: 5.2850 2025-08-30 07:26:35 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:26:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:27:28 - pico-train - INFO - Step 12600 -- 🔄 Training Metrics 2025-08-30 07:27:28 - pico-train - INFO - ├── Loss: 5.3027 2025-08-30 07:27:28 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:27:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:28:20 - pico-train - INFO - Step 12700 -- 🔄 Training Metrics 2025-08-30 07:28:20 - pico-train - INFO - ├── Loss: 5.2792 2025-08-30 07:28:20 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:28:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:29:14 - pico-train - INFO - Step 12800 -- 🔄 Training Metrics 2025-08-30 07:29:14 - pico-train - INFO - ├── Loss: 5.3026 2025-08-30 07:29:14 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:29:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:30:05 - pico-train - INFO - Step 12900 -- 🔄 Training Metrics 2025-08-30 07:30:05 - pico-train - INFO - ├── Loss: 5.2918 2025-08-30 07:30:05 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:30:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:30:58 - pico-train - INFO - Step 13000 -- 🔄 Training Metrics 2025-08-30 07:30:58 - pico-train - INFO - ├── Loss: 5.3032 2025-08-30 07:30:58 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:30:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:31:50 - pico-train - INFO - Step 13100 -- 🔄 Training Metrics 2025-08-30 07:31:50 - pico-train - INFO - ├── Loss: 5.2887 2025-08-30 07:31:50 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:31:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:32:43 - pico-train - INFO - Step 13200 -- 🔄 Training Metrics 2025-08-30 07:32:43 - pico-train - INFO - ├── Loss: 5.2853 2025-08-30 07:32:43 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:32:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:33:35 - pico-train - INFO - Step 13300 -- 🔄 Training Metrics 2025-08-30 07:33:35 - pico-train - INFO - ├── Loss: 5.2829 2025-08-30 07:33:35 - pico-train - INFO - ├── Learning Rate: 1.94e-04 2025-08-30 07:33:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:34:27 - pico-train - INFO - Step 13400 -- 🔄 Training Metrics 2025-08-30 07:34:27 - pico-train - INFO - ├── Loss: 5.2773 2025-08-30 07:34:27 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:34:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:35:20 - pico-train - INFO - Step 13500 -- 🔄 Training Metrics 2025-08-30 07:35:20 - pico-train - INFO - ├── Loss: 5.2645 2025-08-30 07:35:20 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:35:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:36:13 - pico-train - INFO - Step 13600 -- 🔄 Training Metrics 2025-08-30 07:36:13 - pico-train - INFO - ├── Loss: 5.2692 2025-08-30 07:36:13 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:36:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:37:07 - pico-train - INFO - Step 13700 -- 🔄 Training Metrics 2025-08-30 07:37:07 - pico-train - INFO - ├── Loss: 5.2500 2025-08-30 07:37:07 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:37:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:38:01 - pico-train - INFO - Step 13800 -- 🔄 Training Metrics 2025-08-30 07:38:01 - pico-train - INFO - ├── Loss: 5.2655 2025-08-30 07:38:01 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:38:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:38:54 - pico-train - INFO - Step 13900 -- 🔄 Training Metrics 2025-08-30 07:38:54 - pico-train - INFO - ├── Loss: 5.2591 2025-08-30 07:38:54 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:38:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:39:46 - pico-train - INFO - Step 14000 -- 💾 Saving Checkpoint 2025-08-30 07:41:49 - pico-train - INFO - Step 14000 -- 📊 Evaluation Results 2025-08-30 07:41:49 - pico-train - INFO - └── paloma: inf 2025-08-30 07:41:51 - pico-train - INFO - Step 14000 -- 🔄 Training Metrics 2025-08-30 07:41:51 - pico-train - INFO - ├── Loss: 5.2632 2025-08-30 07:41:51 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:41:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:41:51 - pico-train - INFO - Step 14000 -- 📈 Saving Learning Dynamics 2025-08-30 07:42:49 - pico-train - INFO - Step 14100 -- 🔄 Training Metrics 2025-08-30 07:42:49 - pico-train - INFO - ├── Loss: 5.2383 2025-08-30 07:42:49 - pico-train - INFO - ├── Learning Rate: 1.93e-04 2025-08-30 07:42:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:43:41 - pico-train - INFO - Step 14200 -- 🔄 Training Metrics 2025-08-30 07:43:41 - pico-train - INFO - ├── Loss: 5.2505 2025-08-30 07:43:41 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:43:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:44:34 - pico-train - INFO - Step 14300 -- 🔄 Training Metrics 2025-08-30 07:44:34 - pico-train - INFO - ├── Loss: 5.2444 2025-08-30 07:44:34 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:44:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:45:26 - pico-train - INFO - Step 14400 -- 🔄 Training Metrics 2025-08-30 07:45:26 - pico-train - INFO - ├── Loss: 5.2410 2025-08-30 07:45:26 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:45:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:46:18 - pico-train - INFO - Step 14500 -- 🔄 Training Metrics 2025-08-30 07:46:18 - pico-train - INFO - ├── Loss: 5.2553 2025-08-30 07:46:18 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:46:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:47:11 - pico-train - INFO - Step 14600 -- 🔄 Training Metrics 2025-08-30 07:47:11 - pico-train - INFO - ├── Loss: 5.2326 2025-08-30 07:47:11 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:47:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:48:02 - pico-train - INFO - Step 14700 -- 🔄 Training Metrics 2025-08-30 07:48:02 - pico-train - INFO - ├── Loss: 5.2398 2025-08-30 07:48:02 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:48:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:48:55 - pico-train - INFO - Step 14800 -- 🔄 Training Metrics 2025-08-30 07:48:55 - pico-train - INFO - ├── Loss: 5.2355 2025-08-30 07:48:55 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:48:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:49:48 - pico-train - INFO - Step 14900 -- 🔄 Training Metrics 2025-08-30 07:49:48 - pico-train - INFO - ├── Loss: 5.2329 2025-08-30 07:49:48 - pico-train - INFO - ├── Learning Rate: 1.92e-04 2025-08-30 07:49:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:50:40 - pico-train - INFO - Step 15000 -- 🔄 Training Metrics 2025-08-30 07:50:40 - pico-train - INFO - ├── Loss: 5.2309 2025-08-30 07:50:40 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:50:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:51:32 - pico-train - INFO - Step 15100 -- 🔄 Training Metrics 2025-08-30 07:51:32 - pico-train - INFO - ├── Loss: 5.2283 2025-08-30 07:51:32 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:51:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:52:24 - pico-train - INFO - Step 15200 -- 🔄 Training Metrics 2025-08-30 07:52:24 - pico-train - INFO - ├── Loss: 5.2301 2025-08-30 07:52:24 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:52:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:53:16 - pico-train - INFO - Step 15300 -- 🔄 Training Metrics 2025-08-30 07:53:16 - pico-train - INFO - ├── Loss: 5.2524 2025-08-30 07:53:16 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:53:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:54:09 - pico-train - INFO - Step 15400 -- 🔄 Training Metrics 2025-08-30 07:54:09 - pico-train - INFO - ├── Loss: 5.2164 2025-08-30 07:54:09 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:54:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:55:01 - pico-train - INFO - Step 15500 -- 🔄 Training Metrics 2025-08-30 07:55:01 - pico-train - INFO - ├── Loss: 5.2332 2025-08-30 07:55:01 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:55:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:55:53 - pico-train - INFO - Step 15600 -- 🔄 Training Metrics 2025-08-30 07:55:53 - pico-train - INFO - ├── Loss: 5.2263 2025-08-30 07:55:53 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:55:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:56:46 - pico-train - INFO - Step 15700 -- 🔄 Training Metrics 2025-08-30 07:56:46 - pico-train - INFO - ├── Loss: 5.2087 2025-08-30 07:56:46 - pico-train - INFO - ├── Learning Rate: 1.91e-04 2025-08-30 07:56:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:57:38 - pico-train - INFO - Step 15800 -- 🔄 Training Metrics 2025-08-30 07:57:38 - pico-train - INFO - ├── Loss: 5.2199 2025-08-30 07:57:38 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 07:57:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:58:31 - pico-train - INFO - Step 15900 -- 🔄 Training Metrics 2025-08-30 07:58:31 - pico-train - INFO - ├── Loss: 5.2056 2025-08-30 07:58:31 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 07:58:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 07:59:23 - pico-train - INFO - Step 16000 -- 💾 Saving Checkpoint 2025-08-30 08:01:22 - pico-train - INFO - Step 16000 -- 📊 Evaluation Results 2025-08-30 08:01:22 - pico-train - INFO - └── paloma: inf 2025-08-30 08:01:23 - pico-train - INFO - Step 16000 -- 🔄 Training Metrics 2025-08-30 08:01:23 - pico-train - INFO - ├── Loss: 5.2088 2025-08-30 08:01:23 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 08:01:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:01:23 - pico-train - INFO - Step 16000 -- 📈 Saving Learning Dynamics 2025-08-30 08:02:20 - pico-train - INFO - Step 16100 -- 🔄 Training Metrics 2025-08-30 08:02:20 - pico-train - INFO - ├── Loss: 5.1931 2025-08-30 08:02:20 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 08:02:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:03:13 - pico-train - INFO - Step 16200 -- 🔄 Training Metrics 2025-08-30 08:03:13 - pico-train - INFO - ├── Loss: 5.1773 2025-08-30 08:03:13 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 08:03:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:04:07 - pico-train - INFO - Step 16300 -- 🔄 Training Metrics 2025-08-30 08:04:07 - pico-train - INFO - ├── Loss: 5.2032 2025-08-30 08:04:07 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 08:04:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:05:01 - pico-train - INFO - Step 16400 -- 🔄 Training Metrics 2025-08-30 08:05:01 - pico-train - INFO - ├── Loss: 5.1868 2025-08-30 08:05:01 - pico-train - INFO - ├── Learning Rate: 1.90e-04 2025-08-30 08:05:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:05:54 - pico-train - INFO - Step 16500 -- 🔄 Training Metrics 2025-08-30 08:05:54 - pico-train - INFO - ├── Loss: 5.1764 2025-08-30 08:05:54 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 08:05:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:06:46 - pico-train - INFO - Step 16600 -- 🔄 Training Metrics 2025-08-30 08:06:46 - pico-train - INFO - ├── Loss: 5.2021 2025-08-30 08:06:46 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 08:06:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:07:41 - pico-train - INFO - Step 16700 -- 🔄 Training Metrics 2025-08-30 08:07:41 - pico-train - INFO - ├── Loss: 5.1797 2025-08-30 08:07:41 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 08:07:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:08:33 - pico-train - INFO - Step 16800 -- 🔄 Training Metrics 2025-08-30 08:08:33 - pico-train - INFO - ├── Loss: 5.1489 2025-08-30 08:08:33 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 08:08:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:09:28 - pico-train - INFO - Step 16900 -- 🔄 Training Metrics 2025-08-30 08:09:28 - pico-train - INFO - ├── Loss: 5.1805 2025-08-30 08:09:28 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 08:09:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:10:20 - pico-train - INFO - Step 17000 -- 🔄 Training Metrics 2025-08-30 08:10:20 - pico-train - INFO - ├── Loss: 5.1844 2025-08-30 08:10:20 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 08:10:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:11:14 - pico-train - INFO - Step 17100 -- 🔄 Training Metrics 2025-08-30 08:11:14 - pico-train - INFO - ├── Loss: 5.1826 2025-08-30 08:11:14 - pico-train - INFO - ├── Learning Rate: 1.89e-04 2025-08-30 08:11:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:12:08 - pico-train - INFO - Step 17200 -- 🔄 Training Metrics 2025-08-30 08:12:08 - pico-train - INFO - ├── Loss: 5.1568 2025-08-30 08:12:08 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 08:12:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:13:02 - pico-train - INFO - Step 17300 -- 🔄 Training Metrics 2025-08-30 08:13:02 - pico-train - INFO - ├── Loss: 5.2075 2025-08-30 08:13:02 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 08:13:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:13:56 - pico-train - INFO - Step 17400 -- 🔄 Training Metrics 2025-08-30 08:13:56 - pico-train - INFO - ├── Loss: 5.1649 2025-08-30 08:13:56 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 08:13:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:14:49 - pico-train - INFO - Step 17500 -- 🔄 Training Metrics 2025-08-30 08:14:49 - pico-train - INFO - ├── Loss: 5.1506 2025-08-30 08:14:49 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 08:14:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:15:42 - pico-train - INFO - Step 17600 -- 🔄 Training Metrics 2025-08-30 08:15:42 - pico-train - INFO - ├── Loss: 5.1757 2025-08-30 08:15:42 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 08:15:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:16:36 - pico-train - INFO - Step 17700 -- 🔄 Training Metrics 2025-08-30 08:16:36 - pico-train - INFO - ├── Loss: 5.1580 2025-08-30 08:16:36 - pico-train - INFO - ├── Learning Rate: 1.88e-04 2025-08-30 08:16:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:17:30 - pico-train - INFO - Step 17800 -- 🔄 Training Metrics 2025-08-30 08:17:30 - pico-train - INFO - ├── Loss: 5.1309 2025-08-30 08:17:30 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 08:17:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:18:23 - pico-train - INFO - Step 17900 -- 🔄 Training Metrics 2025-08-30 08:18:23 - pico-train - INFO - ├── Loss: 5.1601 2025-08-30 08:18:23 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 08:18:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:19:16 - pico-train - INFO - Step 18000 -- 💾 Saving Checkpoint 2025-08-30 08:21:31 - pico-train - INFO - Step 18000 -- 📊 Evaluation Results 2025-08-30 08:21:31 - pico-train - INFO - └── paloma: inf 2025-08-30 08:21:32 - pico-train - INFO - Step 18000 -- 🔄 Training Metrics 2025-08-30 08:21:32 - pico-train - INFO - ├── Loss: 5.1612 2025-08-30 08:21:32 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 08:21:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:21:32 - pico-train - INFO - Step 18000 -- 📈 Saving Learning Dynamics 2025-08-30 08:22:30 - pico-train - INFO - Step 18100 -- 🔄 Training Metrics 2025-08-30 08:22:30 - pico-train - INFO - ├── Loss: 5.1556 2025-08-30 08:22:30 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 08:22:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:23:24 - pico-train - INFO - Step 18200 -- 🔄 Training Metrics 2025-08-30 08:23:24 - pico-train - INFO - ├── Loss: 5.1406 2025-08-30 08:23:24 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 08:23:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:24:17 - pico-train - INFO - Step 18300 -- 🔄 Training Metrics 2025-08-30 08:24:17 - pico-train - INFO - ├── Loss: 5.1410 2025-08-30 08:24:17 - pico-train - INFO - ├── Learning Rate: 1.87e-04 2025-08-30 08:24:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:25:10 - pico-train - INFO - Step 18400 -- 🔄 Training Metrics 2025-08-30 08:25:10 - pico-train - INFO - ├── Loss: 5.1468 2025-08-30 08:25:10 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 08:25:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:26:04 - pico-train - INFO - Step 18500 -- 🔄 Training Metrics 2025-08-30 08:26:04 - pico-train - INFO - ├── Loss: 5.1310 2025-08-30 08:26:04 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 08:26:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:26:57 - pico-train - INFO - Step 18600 -- 🔄 Training Metrics 2025-08-30 08:26:57 - pico-train - INFO - ├── Loss: 5.1406 2025-08-30 08:26:57 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 08:26:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:27:51 - pico-train - INFO - Step 18700 -- 🔄 Training Metrics 2025-08-30 08:27:51 - pico-train - INFO - ├── Loss: 5.1457 2025-08-30 08:27:51 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 08:27:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:28:45 - pico-train - INFO - Step 18800 -- 🔄 Training Metrics 2025-08-30 08:28:45 - pico-train - INFO - ├── Loss: 5.1176 2025-08-30 08:28:45 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 08:28:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:29:38 - pico-train - INFO - Step 18900 -- 🔄 Training Metrics 2025-08-30 08:29:38 - pico-train - INFO - ├── Loss: 5.1283 2025-08-30 08:29:38 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 08:29:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:30:32 - pico-train - INFO - Step 19000 -- 🔄 Training Metrics 2025-08-30 08:30:32 - pico-train - INFO - ├── Loss: 5.1459 2025-08-30 08:30:32 - pico-train - INFO - ├── Learning Rate: 1.86e-04 2025-08-30 08:30:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:31:25 - pico-train - INFO - Step 19100 -- 🔄 Training Metrics 2025-08-30 08:31:25 - pico-train - INFO - ├── Loss: 5.1400 2025-08-30 08:31:25 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 08:31:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:32:20 - pico-train - INFO - Step 19200 -- 🔄 Training Metrics 2025-08-30 08:32:20 - pico-train - INFO - ├── Loss: 5.1267 2025-08-30 08:32:20 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 08:32:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:33:12 - pico-train - INFO - Step 19300 -- 🔄 Training Metrics 2025-08-30 08:33:12 - pico-train - INFO - ├── Loss: 5.1289 2025-08-30 08:33:12 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 08:33:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:34:05 - pico-train - INFO - Step 19400 -- 🔄 Training Metrics 2025-08-30 08:34:05 - pico-train - INFO - ├── Loss: 5.1261 2025-08-30 08:34:05 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 08:34:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:34:58 - pico-train - INFO - Step 19500 -- 🔄 Training Metrics 2025-08-30 08:34:58 - pico-train - INFO - ├── Loss: 5.1383 2025-08-30 08:34:58 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 08:34:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:35:50 - pico-train - INFO - Step 19600 -- 🔄 Training Metrics 2025-08-30 08:35:50 - pico-train - INFO - ├── Loss: 5.1403 2025-08-30 08:35:50 - pico-train - INFO - ├── Learning Rate: 1.85e-04 2025-08-30 08:35:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:36:43 - pico-train - INFO - Step 19700 -- 🔄 Training Metrics 2025-08-30 08:36:43 - pico-train - INFO - ├── Loss: 5.1261 2025-08-30 08:36:43 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 08:36:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:37:35 - pico-train - INFO - Step 19800 -- 🔄 Training Metrics 2025-08-30 08:37:35 - pico-train - INFO - ├── Loss: 5.1311 2025-08-30 08:37:35 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 08:37:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:38:27 - pico-train - INFO - Step 19900 -- 🔄 Training Metrics 2025-08-30 08:38:27 - pico-train - INFO - ├── Loss: 5.1058 2025-08-30 08:38:27 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 08:38:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:39:19 - pico-train - INFO - Step 20000 -- 💾 Saving Checkpoint 2025-08-30 08:41:42 - pico-train - INFO - Step 20000 -- 📊 Evaluation Results 2025-08-30 08:41:42 - pico-train - INFO - └── paloma: inf 2025-08-30 08:41:44 - pico-train - INFO - Step 20000 -- 🔄 Training Metrics 2025-08-30 08:41:44 - pico-train - INFO - ├── Loss: 5.1195 2025-08-30 08:41:44 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 08:41:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:41:44 - pico-train - INFO - Step 20000 -- 📈 Saving Learning Dynamics 2025-08-30 08:42:41 - pico-train - INFO - Step 20100 -- 🔄 Training Metrics 2025-08-30 08:42:41 - pico-train - INFO - ├── Loss: 5.1018 2025-08-30 08:42:41 - pico-train - INFO - ├── Learning Rate: 1.84e-04 2025-08-30 08:42:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:43:34 - pico-train - INFO - Step 20200 -- 🔄 Training Metrics 2025-08-30 08:43:34 - pico-train - INFO - ├── Loss: 5.1165 2025-08-30 08:43:34 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 08:43:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:44:25 - pico-train - INFO - Step 20300 -- 🔄 Training Metrics 2025-08-30 08:44:25 - pico-train - INFO - ├── Loss: 5.1355 2025-08-30 08:44:25 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 08:44:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:45:18 - pico-train - INFO - Step 20400 -- 🔄 Training Metrics 2025-08-30 08:45:18 - pico-train - INFO - ├── Loss: 5.1157 2025-08-30 08:45:18 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 08:45:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:46:12 - pico-train - INFO - Step 20500 -- 🔄 Training Metrics 2025-08-30 08:46:12 - pico-train - INFO - ├── Loss: 5.1164 2025-08-30 08:46:12 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 08:46:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:47:04 - pico-train - INFO - Step 20600 -- 🔄 Training Metrics 2025-08-30 08:47:04 - pico-train - INFO - ├── Loss: 5.1290 2025-08-30 08:47:04 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 08:47:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:47:56 - pico-train - INFO - Step 20700 -- 🔄 Training Metrics 2025-08-30 08:47:56 - pico-train - INFO - ├── Loss: 5.1012 2025-08-30 08:47:56 - pico-train - INFO - ├── Learning Rate: 1.83e-04 2025-08-30 08:47:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:48:49 - pico-train - INFO - Step 20800 -- 🔄 Training Metrics 2025-08-30 08:48:49 - pico-train - INFO - ├── Loss: 5.1103 2025-08-30 08:48:49 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 08:48:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:49:42 - pico-train - INFO - Step 20900 -- 🔄 Training Metrics 2025-08-30 08:49:42 - pico-train - INFO - ├── Loss: 5.1041 2025-08-30 08:49:42 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 08:49:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:50:35 - pico-train - INFO - Step 21000 -- 🔄 Training Metrics 2025-08-30 08:50:35 - pico-train - INFO - ├── Loss: 5.1055 2025-08-30 08:50:35 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 08:50:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:51:28 - pico-train - INFO - Step 21100 -- 🔄 Training Metrics 2025-08-30 08:51:28 - pico-train - INFO - ├── Loss: 5.0964 2025-08-30 08:51:28 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 08:51:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:52:20 - pico-train - INFO - Step 21200 -- 🔄 Training Metrics 2025-08-30 08:52:20 - pico-train - INFO - ├── Loss: 5.1160 2025-08-30 08:52:20 - pico-train - INFO - ├── Learning Rate: 1.82e-04 2025-08-30 08:52:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:53:14 - pico-train - INFO - Step 21300 -- 🔄 Training Metrics 2025-08-30 08:53:14 - pico-train - INFO - ├── Loss: 5.1048 2025-08-30 08:53:14 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 08:53:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:54:07 - pico-train - INFO - Step 21400 -- 🔄 Training Metrics 2025-08-30 08:54:07 - pico-train - INFO - ├── Loss: 5.0806 2025-08-30 08:54:07 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 08:54:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:55:00 - pico-train - INFO - Step 21500 -- 🔄 Training Metrics 2025-08-30 08:55:00 - pico-train - INFO - ├── Loss: 5.1073 2025-08-30 08:55:00 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 08:55:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:55:53 - pico-train - INFO - Step 21600 -- 🔄 Training Metrics 2025-08-30 08:55:53 - pico-train - INFO - ├── Loss: 5.0786 2025-08-30 08:55:53 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 08:55:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:56:47 - pico-train - INFO - Step 21700 -- 🔄 Training Metrics 2025-08-30 08:56:47 - pico-train - INFO - ├── Loss: 5.0965 2025-08-30 08:56:47 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 08:56:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:57:41 - pico-train - INFO - Step 21800 -- 🔄 Training Metrics 2025-08-30 08:57:41 - pico-train - INFO - ├── Loss: 5.1086 2025-08-30 08:57:41 - pico-train - INFO - ├── Learning Rate: 1.81e-04 2025-08-30 08:57:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:58:33 - pico-train - INFO - Step 21900 -- 🔄 Training Metrics 2025-08-30 08:58:33 - pico-train - INFO - ├── Loss: 5.1030 2025-08-30 08:58:33 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 08:58:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 08:59:24 - pico-train - INFO - Step 22000 -- 💾 Saving Checkpoint 2025-08-30 09:01:28 - pico-train - INFO - Step 22000 -- 📊 Evaluation Results 2025-08-30 09:01:28 - pico-train - INFO - └── paloma: inf 2025-08-30 09:01:31 - pico-train - INFO - Step 22000 -- 🔄 Training Metrics 2025-08-30 09:01:31 - pico-train - INFO - ├── Loss: 5.0792 2025-08-30 09:01:31 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 09:01:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:01:31 - pico-train - INFO - Step 22000 -- 📈 Saving Learning Dynamics 2025-08-30 09:02:29 - pico-train - INFO - Step 22100 -- 🔄 Training Metrics 2025-08-30 09:02:29 - pico-train - INFO - ├── Loss: 5.0856 2025-08-30 09:02:29 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 09:02:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:03:21 - pico-train - INFO - Step 22200 -- 🔄 Training Metrics 2025-08-30 09:03:21 - pico-train - INFO - ├── Loss: 5.0824 2025-08-30 09:03:21 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 09:03:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:04:14 - pico-train - INFO - Step 22300 -- 🔄 Training Metrics 2025-08-30 09:04:14 - pico-train - INFO - ├── Loss: 5.0941 2025-08-30 09:04:14 - pico-train - INFO - ├── Learning Rate: 1.80e-04 2025-08-30 09:04:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:05:06 - pico-train - INFO - Step 22400 -- 🔄 Training Metrics 2025-08-30 09:05:06 - pico-train - INFO - ├── Loss: 5.0779 2025-08-30 09:05:06 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 09:05:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:05:58 - pico-train - INFO - Step 22500 -- 🔄 Training Metrics 2025-08-30 09:05:58 - pico-train - INFO - ├── Loss: 5.0808 2025-08-30 09:05:58 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 09:05:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:06:50 - pico-train - INFO - Step 22600 -- 🔄 Training Metrics 2025-08-30 09:06:50 - pico-train - INFO - ├── Loss: 5.0870 2025-08-30 09:06:50 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 09:06:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:07:42 - pico-train - INFO - Step 22700 -- 🔄 Training Metrics 2025-08-30 09:07:42 - pico-train - INFO - ├── Loss: 5.0751 2025-08-30 09:07:42 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 09:07:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:08:35 - pico-train - INFO - Step 22800 -- 🔄 Training Metrics 2025-08-30 09:08:35 - pico-train - INFO - ├── Loss: 5.0664 2025-08-30 09:08:35 - pico-train - INFO - ├── Learning Rate: 1.79e-04 2025-08-30 09:08:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:09:27 - pico-train - INFO - Step 22900 -- 🔄 Training Metrics 2025-08-30 09:09:27 - pico-train - INFO - ├── Loss: 5.0716 2025-08-30 09:09:27 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 09:09:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:10:19 - pico-train - INFO - Step 23000 -- 🔄 Training Metrics 2025-08-30 09:10:19 - pico-train - INFO - ├── Loss: 5.0720 2025-08-30 09:10:19 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 09:10:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:11:12 - pico-train - INFO - Step 23100 -- 🔄 Training Metrics 2025-08-30 09:11:12 - pico-train - INFO - ├── Loss: 5.0657 2025-08-30 09:11:12 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 09:11:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:12:04 - pico-train - INFO - Step 23200 -- 🔄 Training Metrics 2025-08-30 09:12:04 - pico-train - INFO - ├── Loss: 5.0631 2025-08-30 09:12:04 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 09:12:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:12:57 - pico-train - INFO - Step 23300 -- 🔄 Training Metrics 2025-08-30 09:12:57 - pico-train - INFO - ├── Loss: 5.0873 2025-08-30 09:12:57 - pico-train - INFO - ├── Learning Rate: 1.78e-04 2025-08-30 09:12:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:13:48 - pico-train - INFO - Step 23400 -- 🔄 Training Metrics 2025-08-30 09:13:48 - pico-train - INFO - ├── Loss: 5.0613 2025-08-30 09:13:48 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 09:13:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:14:41 - pico-train - INFO - Step 23500 -- 🔄 Training Metrics 2025-08-30 09:14:41 - pico-train - INFO - ├── Loss: 5.0463 2025-08-30 09:14:41 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 09:14:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:15:33 - pico-train - INFO - Step 23600 -- 🔄 Training Metrics 2025-08-30 09:15:33 - pico-train - INFO - ├── Loss: 5.0611 2025-08-30 09:15:33 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 09:15:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:16:26 - pico-train - INFO - Step 23700 -- 🔄 Training Metrics 2025-08-30 09:16:26 - pico-train - INFO - ├── Loss: 5.0502 2025-08-30 09:16:26 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 09:16:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:17:18 - pico-train - INFO - Step 23800 -- 🔄 Training Metrics 2025-08-30 09:17:18 - pico-train - INFO - ├── Loss: 5.0518 2025-08-30 09:17:18 - pico-train - INFO - ├── Learning Rate: 1.77e-04 2025-08-30 09:17:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:18:10 - pico-train - INFO - Step 23900 -- 🔄 Training Metrics 2025-08-30 09:18:10 - pico-train - INFO - ├── Loss: 5.0439 2025-08-30 09:18:10 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 09:18:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:19:02 - pico-train - INFO - Step 24000 -- 💾 Saving Checkpoint 2025-08-30 09:21:02 - pico-train - INFO - Step 24000 -- 📊 Evaluation Results 2025-08-30 09:21:02 - pico-train - INFO - └── paloma: inf 2025-08-30 09:21:04 - pico-train - INFO - Step 24000 -- 🔄 Training Metrics 2025-08-30 09:21:04 - pico-train - INFO - ├── Loss: 5.0522 2025-08-30 09:21:04 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 09:21:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:21:04 - pico-train - INFO - Step 24000 -- 📈 Saving Learning Dynamics 2025-08-30 09:22:01 - pico-train - INFO - Step 24100 -- 🔄 Training Metrics 2025-08-30 09:22:01 - pico-train - INFO - ├── Loss: 5.0477 2025-08-30 09:22:01 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 09:22:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:22:54 - pico-train - INFO - Step 24200 -- 🔄 Training Metrics 2025-08-30 09:22:54 - pico-train - INFO - ├── Loss: 5.0433 2025-08-30 09:22:54 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 09:22:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:23:46 - pico-train - INFO - Step 24300 -- 🔄 Training Metrics 2025-08-30 09:23:46 - pico-train - INFO - ├── Loss: 5.0522 2025-08-30 09:23:46 - pico-train - INFO - ├── Learning Rate: 1.76e-04 2025-08-30 09:23:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:24:39 - pico-train - INFO - Step 24400 -- 🔄 Training Metrics 2025-08-30 09:24:39 - pico-train - INFO - ├── Loss: 5.0452 2025-08-30 09:24:39 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 09:24:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:25:32 - pico-train - INFO - Step 24500 -- 🔄 Training Metrics 2025-08-30 09:25:32 - pico-train - INFO - ├── Loss: 5.0629 2025-08-30 09:25:32 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 09:25:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:26:24 - pico-train - INFO - Step 24600 -- 🔄 Training Metrics 2025-08-30 09:26:24 - pico-train - INFO - ├── Loss: 5.0439 2025-08-30 09:26:24 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 09:26:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:27:16 - pico-train - INFO - Step 24700 -- 🔄 Training Metrics 2025-08-30 09:27:16 - pico-train - INFO - ├── Loss: 5.0322 2025-08-30 09:27:16 - pico-train - INFO - ├── Learning Rate: 1.75e-04 2025-08-30 09:27:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:28:08 - pico-train - INFO - Step 24800 -- 🔄 Training Metrics 2025-08-30 09:28:08 - pico-train - INFO - ├── Loss: 5.0504 2025-08-30 09:28:08 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 09:28:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:29:00 - pico-train - INFO - Step 24900 -- 🔄 Training Metrics 2025-08-30 09:29:00 - pico-train - INFO - ├── Loss: 5.0361 2025-08-30 09:29:00 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 09:29:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:29:52 - pico-train - INFO - Step 25000 -- 🔄 Training Metrics 2025-08-30 09:29:52 - pico-train - INFO - ├── Loss: 5.0214 2025-08-30 09:29:52 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 09:29:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:30:44 - pico-train - INFO - Step 25100 -- 🔄 Training Metrics 2025-08-30 09:30:44 - pico-train - INFO - ├── Loss: 5.0437 2025-08-30 09:30:44 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 09:30:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:31:37 - pico-train - INFO - Step 25200 -- 🔄 Training Metrics 2025-08-30 09:31:37 - pico-train - INFO - ├── Loss: 5.0433 2025-08-30 09:31:37 - pico-train - INFO - ├── Learning Rate: 1.74e-04 2025-08-30 09:31:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:32:28 - pico-train - INFO - Step 25300 -- 🔄 Training Metrics 2025-08-30 09:32:28 - pico-train - INFO - ├── Loss: 5.0522 2025-08-30 09:32:28 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 09:32:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:33:21 - pico-train - INFO - Step 25400 -- 🔄 Training Metrics 2025-08-30 09:33:21 - pico-train - INFO - ├── Loss: 5.0399 2025-08-30 09:33:21 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 09:33:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:34:14 - pico-train - INFO - Step 25500 -- 🔄 Training Metrics 2025-08-30 09:34:14 - pico-train - INFO - ├── Loss: 5.0391 2025-08-30 09:34:14 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 09:34:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:35:07 - pico-train - INFO - Step 25600 -- 🔄 Training Metrics 2025-08-30 09:35:07 - pico-train - INFO - ├── Loss: 5.0489 2025-08-30 09:35:07 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 09:35:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:35:59 - pico-train - INFO - Step 25700 -- 🔄 Training Metrics 2025-08-30 09:35:59 - pico-train - INFO - ├── Loss: 5.0378 2025-08-30 09:35:59 - pico-train - INFO - ├── Learning Rate: 1.73e-04 2025-08-30 09:35:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:36:52 - pico-train - INFO - Step 25800 -- 🔄 Training Metrics 2025-08-30 09:36:52 - pico-train - INFO - ├── Loss: 5.0416 2025-08-30 09:36:52 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 09:36:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:37:44 - pico-train - INFO - Step 25900 -- 🔄 Training Metrics 2025-08-30 09:37:44 - pico-train - INFO - ├── Loss: 5.0106 2025-08-30 09:37:44 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 09:37:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:38:36 - pico-train - INFO - Step 26000 -- 💾 Saving Checkpoint 2025-08-30 09:40:36 - pico-train - INFO - Step 26000 -- 📊 Evaluation Results 2025-08-30 09:40:36 - pico-train - INFO - └── paloma: inf 2025-08-30 09:40:37 - pico-train - INFO - Step 26000 -- 🔄 Training Metrics 2025-08-30 09:40:37 - pico-train - INFO - ├── Loss: 5.0129 2025-08-30 09:40:37 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 09:40:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:40:37 - pico-train - INFO - Step 26000 -- 📈 Saving Learning Dynamics 2025-08-30 09:41:35 - pico-train - INFO - Step 26100 -- 🔄 Training Metrics 2025-08-30 09:41:35 - pico-train - INFO - ├── Loss: 5.0560 2025-08-30 09:41:35 - pico-train - INFO - ├── Learning Rate: 1.72e-04 2025-08-30 09:41:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:42:27 - pico-train - INFO - Step 26200 -- 🔄 Training Metrics 2025-08-30 09:42:27 - pico-train - INFO - ├── Loss: 5.0231 2025-08-30 09:42:27 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 09:42:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:43:20 - pico-train - INFO - Step 26300 -- 🔄 Training Metrics 2025-08-30 09:43:20 - pico-train - INFO - ├── Loss: 5.0203 2025-08-30 09:43:20 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 09:43:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:44:13 - pico-train - INFO - Step 26400 -- 🔄 Training Metrics 2025-08-30 09:44:13 - pico-train - INFO - ├── Loss: 5.0435 2025-08-30 09:44:13 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 09:44:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:45:05 - pico-train - INFO - Step 26500 -- 🔄 Training Metrics 2025-08-30 09:45:05 - pico-train - INFO - ├── Loss: 5.0079 2025-08-30 09:45:05 - pico-train - INFO - ├── Learning Rate: 1.71e-04 2025-08-30 09:45:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:45:59 - pico-train - INFO - Step 26600 -- 🔄 Training Metrics 2025-08-30 09:45:59 - pico-train - INFO - ├── Loss: 5.0246 2025-08-30 09:45:59 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 09:45:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:46:50 - pico-train - INFO - Step 26700 -- 🔄 Training Metrics 2025-08-30 09:46:50 - pico-train - INFO - ├── Loss: 5.0400 2025-08-30 09:46:50 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 09:46:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:47:43 - pico-train - INFO - Step 26800 -- 🔄 Training Metrics 2025-08-30 09:47:43 - pico-train - INFO - ├── Loss: 5.0359 2025-08-30 09:47:43 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 09:47:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:48:36 - pico-train - INFO - Step 26900 -- 🔄 Training Metrics 2025-08-30 09:48:36 - pico-train - INFO - ├── Loss: 4.9974 2025-08-30 09:48:36 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 09:48:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:49:28 - pico-train - INFO - Step 27000 -- 🔄 Training Metrics 2025-08-30 09:49:28 - pico-train - INFO - ├── Loss: 5.0186 2025-08-30 09:49:28 - pico-train - INFO - ├── Learning Rate: 1.70e-04 2025-08-30 09:49:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:50:21 - pico-train - INFO - Step 27100 -- 🔄 Training Metrics 2025-08-30 09:50:21 - pico-train - INFO - ├── Loss: 5.0101 2025-08-30 09:50:21 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 09:50:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:51:13 - pico-train - INFO - Step 27200 -- 🔄 Training Metrics 2025-08-30 09:51:13 - pico-train - INFO - ├── Loss: 5.0228 2025-08-30 09:51:13 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 09:51:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:52:05 - pico-train - INFO - Step 27300 -- 🔄 Training Metrics 2025-08-30 09:52:05 - pico-train - INFO - ├── Loss: 5.0295 2025-08-30 09:52:05 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 09:52:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:52:58 - pico-train - INFO - Step 27400 -- 🔄 Training Metrics 2025-08-30 09:52:58 - pico-train - INFO - ├── Loss: 5.0014 2025-08-30 09:52:58 - pico-train - INFO - ├── Learning Rate: 1.69e-04 2025-08-30 09:52:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:53:50 - pico-train - INFO - Step 27500 -- 🔄 Training Metrics 2025-08-30 09:53:50 - pico-train - INFO - ├── Loss: 5.0173 2025-08-30 09:53:50 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 09:53:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:54:42 - pico-train - INFO - Step 27600 -- 🔄 Training Metrics 2025-08-30 09:54:42 - pico-train - INFO - ├── Loss: 4.9924 2025-08-30 09:54:42 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 09:54:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:55:34 - pico-train - INFO - Step 27700 -- 🔄 Training Metrics 2025-08-30 09:55:34 - pico-train - INFO - ├── Loss: 5.0067 2025-08-30 09:55:34 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 09:55:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:56:26 - pico-train - INFO - Step 27800 -- 🔄 Training Metrics 2025-08-30 09:56:26 - pico-train - INFO - ├── Loss: 5.0232 2025-08-30 09:56:26 - pico-train - INFO - ├── Learning Rate: 1.68e-04 2025-08-30 09:56:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:57:19 - pico-train - INFO - Step 27900 -- 🔄 Training Metrics 2025-08-30 09:57:19 - pico-train - INFO - ├── Loss: 5.0190 2025-08-30 09:57:19 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 09:57:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 09:58:10 - pico-train - INFO - Step 28000 -- 💾 Saving Checkpoint 2025-08-30 10:00:15 - pico-train - INFO - Step 28000 -- 📊 Evaluation Results 2025-08-30 10:00:15 - pico-train - INFO - └── paloma: inf 2025-08-30 10:00:17 - pico-train - INFO - Step 28000 -- 🔄 Training Metrics 2025-08-30 10:00:17 - pico-train - INFO - ├── Loss: 5.0087 2025-08-30 10:00:17 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 10:00:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:00:17 - pico-train - INFO - Step 28000 -- 📈 Saving Learning Dynamics 2025-08-30 10:01:14 - pico-train - INFO - Step 28100 -- 🔄 Training Metrics 2025-08-30 10:01:14 - pico-train - INFO - ├── Loss: 4.9986 2025-08-30 10:01:14 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 10:01:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:02:07 - pico-train - INFO - Step 28200 -- 🔄 Training Metrics 2025-08-30 10:02:07 - pico-train - INFO - ├── Loss: 5.0120 2025-08-30 10:02:07 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 10:02:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:02:59 - pico-train - INFO - Step 28300 -- 🔄 Training Metrics 2025-08-30 10:02:59 - pico-train - INFO - ├── Loss: 4.9886 2025-08-30 10:02:59 - pico-train - INFO - ├── Learning Rate: 1.67e-04 2025-08-30 10:02:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:03:51 - pico-train - INFO - Step 28400 -- 🔄 Training Metrics 2025-08-30 10:03:51 - pico-train - INFO - ├── Loss: 5.0119 2025-08-30 10:03:51 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 10:03:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:04:44 - pico-train - INFO - Step 28500 -- 🔄 Training Metrics 2025-08-30 10:04:44 - pico-train - INFO - ├── Loss: 5.0120 2025-08-30 10:04:44 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 10:04:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:05:36 - pico-train - INFO - Step 28600 -- 🔄 Training Metrics 2025-08-30 10:05:36 - pico-train - INFO - ├── Loss: 5.0072 2025-08-30 10:05:36 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 10:05:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:06:28 - pico-train - INFO - Step 28700 -- 🔄 Training Metrics 2025-08-30 10:06:28 - pico-train - INFO - ├── Loss: 5.0099 2025-08-30 10:06:28 - pico-train - INFO - ├── Learning Rate: 1.66e-04 2025-08-30 10:06:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:07:21 - pico-train - INFO - Step 28800 -- 🔄 Training Metrics 2025-08-30 10:07:21 - pico-train - INFO - ├── Loss: 5.0086 2025-08-30 10:07:21 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 10:07:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:08:13 - pico-train - INFO - Step 28900 -- 🔄 Training Metrics 2025-08-30 10:08:13 - pico-train - INFO - ├── Loss: 4.9908 2025-08-30 10:08:13 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 10:08:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:09:06 - pico-train - INFO - Step 29000 -- 🔄 Training Metrics 2025-08-30 10:09:06 - pico-train - INFO - ├── Loss: 4.9947 2025-08-30 10:09:06 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 10:09:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:09:59 - pico-train - INFO - Step 29100 -- 🔄 Training Metrics 2025-08-30 10:09:59 - pico-train - INFO - ├── Loss: 5.0001 2025-08-30 10:09:59 - pico-train - INFO - ├── Learning Rate: 1.65e-04 2025-08-30 10:09:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:10:52 - pico-train - INFO - Step 29200 -- 🔄 Training Metrics 2025-08-30 10:10:52 - pico-train - INFO - ├── Loss: 4.9991 2025-08-30 10:10:52 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 10:10:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:11:44 - pico-train - INFO - Step 29300 -- 🔄 Training Metrics 2025-08-30 10:11:44 - pico-train - INFO - ├── Loss: 4.9885 2025-08-30 10:11:44 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 10:11:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:12:36 - pico-train - INFO - Step 29400 -- 🔄 Training Metrics 2025-08-30 10:12:36 - pico-train - INFO - ├── Loss: 4.9985 2025-08-30 10:12:36 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 10:12:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:13:29 - pico-train - INFO - Step 29500 -- 🔄 Training Metrics 2025-08-30 10:13:29 - pico-train - INFO - ├── Loss: 4.9928 2025-08-30 10:13:29 - pico-train - INFO - ├── Learning Rate: 1.64e-04 2025-08-30 10:13:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:14:22 - pico-train - INFO - Step 29600 -- 🔄 Training Metrics 2025-08-30 10:14:22 - pico-train - INFO - ├── Loss: 5.0076 2025-08-30 10:14:22 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 10:14:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:15:16 - pico-train - INFO - Step 29700 -- 🔄 Training Metrics 2025-08-30 10:15:16 - pico-train - INFO - ├── Loss: 4.9919 2025-08-30 10:15:16 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 10:15:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:16:09 - pico-train - INFO - Step 29800 -- 🔄 Training Metrics 2025-08-30 10:16:09 - pico-train - INFO - ├── Loss: 5.0125 2025-08-30 10:16:09 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 10:16:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:17:01 - pico-train - INFO - Step 29900 -- 🔄 Training Metrics 2025-08-30 10:17:01 - pico-train - INFO - ├── Loss: 4.9857 2025-08-30 10:17:01 - pico-train - INFO - ├── Learning Rate: 1.63e-04 2025-08-30 10:17:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:17:53 - pico-train - INFO - Step 30000 -- 💾 Saving Checkpoint 2025-08-30 10:20:02 - pico-train - INFO - Step 30000 -- 📊 Evaluation Results 2025-08-30 10:20:02 - pico-train - INFO - └── paloma: inf 2025-08-30 10:20:04 - pico-train - INFO - Step 30000 -- 🔄 Training Metrics 2025-08-30 10:20:04 - pico-train - INFO - ├── Loss: 4.9901 2025-08-30 10:20:04 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 10:20:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:20:04 - pico-train - INFO - Step 30000 -- 📈 Saving Learning Dynamics 2025-08-30 10:21:01 - pico-train - INFO - Step 30100 -- 🔄 Training Metrics 2025-08-30 10:21:01 - pico-train - INFO - ├── Loss: 4.9848 2025-08-30 10:21:01 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 10:21:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:21:53 - pico-train - INFO - Step 30200 -- 🔄 Training Metrics 2025-08-30 10:21:53 - pico-train - INFO - ├── Loss: 4.9702 2025-08-30 10:21:53 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 10:21:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:22:45 - pico-train - INFO - Step 30300 -- 🔄 Training Metrics 2025-08-30 10:22:45 - pico-train - INFO - ├── Loss: 4.9776 2025-08-30 10:22:45 - pico-train - INFO - ├── Learning Rate: 1.62e-04 2025-08-30 10:22:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:23:37 - pico-train - INFO - Step 30400 -- 🔄 Training Metrics 2025-08-30 10:23:37 - pico-train - INFO - ├── Loss: 4.9791 2025-08-30 10:23:37 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 10:23:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:24:31 - pico-train - INFO - Step 30500 -- 🔄 Training Metrics 2025-08-30 10:24:31 - pico-train - INFO - ├── Loss: 4.9795 2025-08-30 10:24:31 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 10:24:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:25:23 - pico-train - INFO - Step 30600 -- 🔄 Training Metrics 2025-08-30 10:25:23 - pico-train - INFO - ├── Loss: 4.9955 2025-08-30 10:25:23 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 10:25:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:26:15 - pico-train - INFO - Step 30700 -- 🔄 Training Metrics 2025-08-30 10:26:15 - pico-train - INFO - ├── Loss: 4.9795 2025-08-30 10:26:15 - pico-train - INFO - ├── Learning Rate: 1.61e-04 2025-08-30 10:26:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:27:08 - pico-train - INFO - Step 30800 -- 🔄 Training Metrics 2025-08-30 10:27:08 - pico-train - INFO - ├── Loss: 4.9634 2025-08-30 10:27:08 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 10:27:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:28:01 - pico-train - INFO - Step 30900 -- 🔄 Training Metrics 2025-08-30 10:28:01 - pico-train - INFO - ├── Loss: 4.9775 2025-08-30 10:28:01 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 10:28:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:28:54 - pico-train - INFO - Step 31000 -- 🔄 Training Metrics 2025-08-30 10:28:54 - pico-train - INFO - ├── Loss: 4.9883 2025-08-30 10:28:54 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 10:28:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:29:46 - pico-train - INFO - Step 31100 -- 🔄 Training Metrics 2025-08-30 10:29:46 - pico-train - INFO - ├── Loss: 4.9492 2025-08-30 10:29:46 - pico-train - INFO - ├── Learning Rate: 1.60e-04 2025-08-30 10:29:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:30:38 - pico-train - INFO - Step 31200 -- 🔄 Training Metrics 2025-08-30 10:30:38 - pico-train - INFO - ├── Loss: 4.9783 2025-08-30 10:30:38 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 10:30:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:31:30 - pico-train - INFO - Step 31300 -- 🔄 Training Metrics 2025-08-30 10:31:30 - pico-train - INFO - ├── Loss: 4.9732 2025-08-30 10:31:30 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 10:31:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:32:23 - pico-train - INFO - Step 31400 -- 🔄 Training Metrics 2025-08-30 10:32:23 - pico-train - INFO - ├── Loss: 4.9639 2025-08-30 10:32:23 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 10:32:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:33:16 - pico-train - INFO - Step 31500 -- 🔄 Training Metrics 2025-08-30 10:33:16 - pico-train - INFO - ├── Loss: 4.9706 2025-08-30 10:33:16 - pico-train - INFO - ├── Learning Rate: 1.59e-04 2025-08-30 10:33:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:34:09 - pico-train - INFO - Step 31600 -- 🔄 Training Metrics 2025-08-30 10:34:09 - pico-train - INFO - ├── Loss: 4.9916 2025-08-30 10:34:09 - pico-train - INFO - ├── Learning Rate: 1.58e-04 2025-08-30 10:34:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:35:00 - pico-train - INFO - Step 31700 -- 🔄 Training Metrics 2025-08-30 10:35:00 - pico-train - INFO - ├── Loss: 4.9708 2025-08-30 10:35:00 - pico-train - INFO - ├── Learning Rate: 1.58e-04 2025-08-30 10:35:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:35:53 - pico-train - INFO - Step 31800 -- 🔄 Training Metrics 2025-08-30 10:35:53 - pico-train - INFO - ├── Loss: 4.9447 2025-08-30 10:35:53 - pico-train - INFO - ├── Learning Rate: 1.58e-04 2025-08-30 10:35:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:36:46 - pico-train - INFO - Step 31900 -- 🔄 Training Metrics 2025-08-30 10:36:46 - pico-train - INFO - ├── Loss: 4.9892 2025-08-30 10:36:46 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 10:36:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:37:37 - pico-train - INFO - Step 32000 -- 💾 Saving Checkpoint 2025-08-30 10:39:53 - pico-train - INFO - Step 32000 -- 📊 Evaluation Results 2025-08-30 10:39:53 - pico-train - INFO - └── paloma: inf 2025-08-30 10:39:55 - pico-train - INFO - Step 32000 -- 🔄 Training Metrics 2025-08-30 10:39:55 - pico-train - INFO - ├── Loss: 4.9585 2025-08-30 10:39:55 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 10:39:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:39:55 - pico-train - INFO - Step 32000 -- 📈 Saving Learning Dynamics 2025-08-30 10:40:52 - pico-train - INFO - Step 32100 -- 🔄 Training Metrics 2025-08-30 10:40:52 - pico-train - INFO - ├── Loss: 4.9840 2025-08-30 10:40:52 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 10:40:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:41:44 - pico-train - INFO - Step 32200 -- 🔄 Training Metrics 2025-08-30 10:41:44 - pico-train - INFO - ├── Loss: 4.9498 2025-08-30 10:41:44 - pico-train - INFO - ├── Learning Rate: 1.57e-04 2025-08-30 10:41:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:42:37 - pico-train - INFO - Step 32300 -- 🔄 Training Metrics 2025-08-30 10:42:37 - pico-train - INFO - ├── Loss: 4.9513 2025-08-30 10:42:37 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 10:42:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:43:29 - pico-train - INFO - Step 32400 -- 🔄 Training Metrics 2025-08-30 10:43:29 - pico-train - INFO - ├── Loss: 4.9563 2025-08-30 10:43:29 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 10:43:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:44:21 - pico-train - INFO - Step 32500 -- 🔄 Training Metrics 2025-08-30 10:44:21 - pico-train - INFO - ├── Loss: 4.9439 2025-08-30 10:44:21 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 10:44:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:45:13 - pico-train - INFO - Step 32600 -- 🔄 Training Metrics 2025-08-30 10:45:13 - pico-train - INFO - ├── Loss: 4.9768 2025-08-30 10:45:13 - pico-train - INFO - ├── Learning Rate: 1.56e-04 2025-08-30 10:45:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:46:06 - pico-train - INFO - Step 32700 -- 🔄 Training Metrics 2025-08-30 10:46:06 - pico-train - INFO - ├── Loss: 4.9640 2025-08-30 10:46:06 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-30 10:46:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:46:59 - pico-train - INFO - Step 32800 -- 🔄 Training Metrics 2025-08-30 10:46:59 - pico-train - INFO - ├── Loss: 4.9570 2025-08-30 10:46:59 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-30 10:46:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:47:51 - pico-train - INFO - Step 32900 -- 🔄 Training Metrics 2025-08-30 10:47:51 - pico-train - INFO - ├── Loss: 4.9885 2025-08-30 10:47:51 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-30 10:47:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:48:44 - pico-train - INFO - Step 33000 -- 🔄 Training Metrics 2025-08-30 10:48:44 - pico-train - INFO - ├── Loss: 4.9528 2025-08-30 10:48:44 - pico-train - INFO - ├── Learning Rate: 1.55e-04 2025-08-30 10:48:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:49:35 - pico-train - INFO - Step 33100 -- 🔄 Training Metrics 2025-08-30 10:49:35 - pico-train - INFO - ├── Loss: 4.9572 2025-08-30 10:49:35 - pico-train - INFO - ├── Learning Rate: 1.54e-04 2025-08-30 10:49:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:50:28 - pico-train - INFO - Step 33200 -- 🔄 Training Metrics 2025-08-30 10:50:28 - pico-train - INFO - ├── Loss: 4.9850 2025-08-30 10:50:28 - pico-train - INFO - ├── Learning Rate: 1.54e-04 2025-08-30 10:50:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:51:21 - pico-train - INFO - Step 33300 -- 🔄 Training Metrics 2025-08-30 10:51:21 - pico-train - INFO - ├── Loss: 4.9591 2025-08-30 10:51:21 - pico-train - INFO - ├── Learning Rate: 1.54e-04 2025-08-30 10:51:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:52:14 - pico-train - INFO - Step 33400 -- 🔄 Training Metrics 2025-08-30 10:52:14 - pico-train - INFO - ├── Loss: 4.9522 2025-08-30 10:52:14 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-30 10:52:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:53:08 - pico-train - INFO - Step 33500 -- 🔄 Training Metrics 2025-08-30 10:53:08 - pico-train - INFO - ├── Loss: 4.9655 2025-08-30 10:53:08 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-30 10:53:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:54:01 - pico-train - INFO - Step 33600 -- 🔄 Training Metrics 2025-08-30 10:54:01 - pico-train - INFO - ├── Loss: 4.9481 2025-08-30 10:54:01 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-30 10:54:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:54:54 - pico-train - INFO - Step 33700 -- 🔄 Training Metrics 2025-08-30 10:54:54 - pico-train - INFO - ├── Loss: 4.9614 2025-08-30 10:54:54 - pico-train - INFO - ├── Learning Rate: 1.53e-04 2025-08-30 10:54:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:55:48 - pico-train - INFO - Step 33800 -- 🔄 Training Metrics 2025-08-30 10:55:48 - pico-train - INFO - ├── Loss: 4.9347 2025-08-30 10:55:48 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-30 10:55:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:56:40 - pico-train - INFO - Step 33900 -- 🔄 Training Metrics 2025-08-30 10:56:40 - pico-train - INFO - ├── Loss: 4.9518 2025-08-30 10:56:40 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-30 10:56:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:57:34 - pico-train - INFO - Step 34000 -- 💾 Saving Checkpoint 2025-08-30 10:59:40 - pico-train - INFO - Step 34000 -- 📊 Evaluation Results 2025-08-30 10:59:40 - pico-train - INFO - └── paloma: inf 2025-08-30 10:59:42 - pico-train - INFO - Step 34000 -- 🔄 Training Metrics 2025-08-30 10:59:42 - pico-train - INFO - ├── Loss: 4.9519 2025-08-30 10:59:42 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-30 10:59:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 10:59:42 - pico-train - INFO - Step 34000 -- 📈 Saving Learning Dynamics 2025-08-30 11:00:45 - pico-train - INFO - Step 34100 -- 🔄 Training Metrics 2025-08-30 11:00:45 - pico-train - INFO - ├── Loss: 4.9583 2025-08-30 11:00:45 - pico-train - INFO - ├── Learning Rate: 1.52e-04 2025-08-30 11:00:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:01:38 - pico-train - INFO - Step 34200 -- 🔄 Training Metrics 2025-08-30 11:01:38 - pico-train - INFO - ├── Loss: 4.9762 2025-08-30 11:01:38 - pico-train - INFO - ├── Learning Rate: 1.51e-04 2025-08-30 11:01:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:02:32 - pico-train - INFO - Step 34300 -- 🔄 Training Metrics 2025-08-30 11:02:32 - pico-train - INFO - ├── Loss: 4.9671 2025-08-30 11:02:32 - pico-train - INFO - ├── Learning Rate: 1.51e-04 2025-08-30 11:02:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:03:24 - pico-train - INFO - Step 34400 -- 🔄 Training Metrics 2025-08-30 11:03:24 - pico-train - INFO - ├── Loss: 4.9657 2025-08-30 11:03:24 - pico-train - INFO - ├── Learning Rate: 1.51e-04 2025-08-30 11:03:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:04:18 - pico-train - INFO - Step 34500 -- 🔄 Training Metrics 2025-08-30 11:04:18 - pico-train - INFO - ├── Loss: 4.9669 2025-08-30 11:04:18 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-30 11:04:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:05:13 - pico-train - INFO - Step 34600 -- 🔄 Training Metrics 2025-08-30 11:05:13 - pico-train - INFO - ├── Loss: 4.9462 2025-08-30 11:05:13 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-30 11:05:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:06:05 - pico-train - INFO - Step 34700 -- 🔄 Training Metrics 2025-08-30 11:06:05 - pico-train - INFO - ├── Loss: 4.9412 2025-08-30 11:06:05 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-30 11:06:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:06:58 - pico-train - INFO - Step 34800 -- 🔄 Training Metrics 2025-08-30 11:06:58 - pico-train - INFO - ├── Loss: 4.9356 2025-08-30 11:06:58 - pico-train - INFO - ├── Learning Rate: 1.50e-04 2025-08-30 11:06:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:07:52 - pico-train - INFO - Step 34900 -- 🔄 Training Metrics 2025-08-30 11:07:52 - pico-train - INFO - ├── Loss: 4.9345 2025-08-30 11:07:52 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-30 11:07:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:08:45 - pico-train - INFO - Step 35000 -- 🔄 Training Metrics 2025-08-30 11:08:45 - pico-train - INFO - ├── Loss: 4.9402 2025-08-30 11:08:45 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-30 11:08:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:09:39 - pico-train - INFO - Step 35100 -- 🔄 Training Metrics 2025-08-30 11:09:39 - pico-train - INFO - ├── Loss: 4.9421 2025-08-30 11:09:39 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-30 11:09:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:10:33 - pico-train - INFO - Step 35200 -- 🔄 Training Metrics 2025-08-30 11:10:33 - pico-train - INFO - ├── Loss: 4.9274 2025-08-30 11:10:33 - pico-train - INFO - ├── Learning Rate: 1.49e-04 2025-08-30 11:10:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:11:25 - pico-train - INFO - Step 35300 -- 🔄 Training Metrics 2025-08-30 11:11:25 - pico-train - INFO - ├── Loss: 4.9680 2025-08-30 11:11:25 - pico-train - INFO - ├── Learning Rate: 1.48e-04 2025-08-30 11:11:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:12:20 - pico-train - INFO - Step 35400 -- 🔄 Training Metrics 2025-08-30 11:12:20 - pico-train - INFO - ├── Loss: 4.9663 2025-08-30 11:12:20 - pico-train - INFO - ├── Learning Rate: 1.48e-04 2025-08-30 11:12:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:13:13 - pico-train - INFO - Step 35500 -- 🔄 Training Metrics 2025-08-30 11:13:13 - pico-train - INFO - ├── Loss: 4.9410 2025-08-30 11:13:13 - pico-train - INFO - ├── Learning Rate: 1.48e-04 2025-08-30 11:13:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:14:07 - pico-train - INFO - Step 35600 -- 🔄 Training Metrics 2025-08-30 11:14:07 - pico-train - INFO - ├── Loss: 4.9500 2025-08-30 11:14:07 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-30 11:14:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:15:01 - pico-train - INFO - Step 35700 -- 🔄 Training Metrics 2025-08-30 11:15:01 - pico-train - INFO - ├── Loss: 4.9276 2025-08-30 11:15:01 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-30 11:15:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:15:54 - pico-train - INFO - Step 35800 -- 🔄 Training Metrics 2025-08-30 11:15:54 - pico-train - INFO - ├── Loss: 4.9673 2025-08-30 11:15:54 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-30 11:15:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:16:48 - pico-train - INFO - Step 35900 -- 🔄 Training Metrics 2025-08-30 11:16:48 - pico-train - INFO - ├── Loss: 4.9396 2025-08-30 11:16:48 - pico-train - INFO - ├── Learning Rate: 1.47e-04 2025-08-30 11:16:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:17:41 - pico-train - INFO - Step 36000 -- 💾 Saving Checkpoint 2025-08-30 11:19:56 - pico-train - INFO - Step 36000 -- 📊 Evaluation Results 2025-08-30 11:19:56 - pico-train - INFO - └── paloma: inf 2025-08-30 11:19:58 - pico-train - INFO - Step 36000 -- 🔄 Training Metrics 2025-08-30 11:19:58 - pico-train - INFO - ├── Loss: 4.9613 2025-08-30 11:19:58 - pico-train - INFO - ├── Learning Rate: 1.46e-04 2025-08-30 11:19:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:19:58 - pico-train - INFO - Step 36000 -- 📈 Saving Learning Dynamics 2025-08-30 11:20:56 - pico-train - INFO - Step 36100 -- 🔄 Training Metrics 2025-08-30 11:20:56 - pico-train - INFO - ├── Loss: 4.9352 2025-08-30 11:20:56 - pico-train - INFO - ├── Learning Rate: 1.46e-04 2025-08-30 11:20:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:21:47 - pico-train - INFO - Step 36200 -- 🔄 Training Metrics 2025-08-30 11:21:47 - pico-train - INFO - ├── Loss: 4.9431 2025-08-30 11:21:47 - pico-train - INFO - ├── Learning Rate: 1.46e-04 2025-08-30 11:21:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:22:40 - pico-train - INFO - Step 36300 -- 🔄 Training Metrics 2025-08-30 11:22:40 - pico-train - INFO - ├── Loss: 4.9406 2025-08-30 11:22:40 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-30 11:22:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:23:33 - pico-train - INFO - Step 36400 -- 🔄 Training Metrics 2025-08-30 11:23:33 - pico-train - INFO - ├── Loss: 4.9587 2025-08-30 11:23:33 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-30 11:23:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:24:26 - pico-train - INFO - Step 36500 -- 🔄 Training Metrics 2025-08-30 11:24:26 - pico-train - INFO - ├── Loss: 4.9296 2025-08-30 11:24:26 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-30 11:24:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:25:19 - pico-train - INFO - Step 36600 -- 🔄 Training Metrics 2025-08-30 11:25:19 - pico-train - INFO - ├── Loss: 4.9252 2025-08-30 11:25:19 - pico-train - INFO - ├── Learning Rate: 1.45e-04 2025-08-30 11:25:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:26:10 - pico-train - INFO - Step 36700 -- 🔄 Training Metrics 2025-08-30 11:26:10 - pico-train - INFO - ├── Loss: 4.9333 2025-08-30 11:26:10 - pico-train - INFO - ├── Learning Rate: 1.44e-04 2025-08-30 11:26:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:27:03 - pico-train - INFO - Step 36800 -- 🔄 Training Metrics 2025-08-30 11:27:03 - pico-train - INFO - ├── Loss: 4.9394 2025-08-30 11:27:03 - pico-train - INFO - ├── Learning Rate: 1.44e-04 2025-08-30 11:27:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:27:55 - pico-train - INFO - Step 36900 -- 🔄 Training Metrics 2025-08-30 11:27:55 - pico-train - INFO - ├── Loss: 4.9517 2025-08-30 11:27:55 - pico-train - INFO - ├── Learning Rate: 1.44e-04 2025-08-30 11:27:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:28:47 - pico-train - INFO - Step 37000 -- 🔄 Training Metrics 2025-08-30 11:28:47 - pico-train - INFO - ├── Loss: 4.9360 2025-08-30 11:28:47 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-30 11:28:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:29:39 - pico-train - INFO - Step 37100 -- 🔄 Training Metrics 2025-08-30 11:29:39 - pico-train - INFO - ├── Loss: 4.9356 2025-08-30 11:29:39 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-30 11:29:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:30:32 - pico-train - INFO - Step 37200 -- 🔄 Training Metrics 2025-08-30 11:30:32 - pico-train - INFO - ├── Loss: 4.9186 2025-08-30 11:30:32 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-30 11:30:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:31:25 - pico-train - INFO - Step 37300 -- 🔄 Training Metrics 2025-08-30 11:31:25 - pico-train - INFO - ├── Loss: 4.9428 2025-08-30 11:31:25 - pico-train - INFO - ├── Learning Rate: 1.43e-04 2025-08-30 11:31:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:32:17 - pico-train - INFO - Step 37400 -- 🔄 Training Metrics 2025-08-30 11:32:17 - pico-train - INFO - ├── Loss: 4.9358 2025-08-30 11:32:17 - pico-train - INFO - ├── Learning Rate: 1.42e-04 2025-08-30 11:32:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:33:09 - pico-train - INFO - Step 37500 -- 🔄 Training Metrics 2025-08-30 11:33:09 - pico-train - INFO - ├── Loss: 4.9206 2025-08-30 11:33:09 - pico-train - INFO - ├── Learning Rate: 1.42e-04 2025-08-30 11:33:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:34:01 - pico-train - INFO - Step 37600 -- 🔄 Training Metrics 2025-08-30 11:34:01 - pico-train - INFO - ├── Loss: 4.9373 2025-08-30 11:34:01 - pico-train - INFO - ├── Learning Rate: 1.42e-04 2025-08-30 11:34:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:34:53 - pico-train - INFO - Step 37700 -- 🔄 Training Metrics 2025-08-30 11:34:53 - pico-train - INFO - ├── Loss: 4.9388 2025-08-30 11:34:53 - pico-train - INFO - ├── Learning Rate: 1.41e-04 2025-08-30 11:34:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:35:46 - pico-train - INFO - Step 37800 -- 🔄 Training Metrics 2025-08-30 11:35:46 - pico-train - INFO - ├── Loss: 4.9301 2025-08-30 11:35:46 - pico-train - INFO - ├── Learning Rate: 1.41e-04 2025-08-30 11:35:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:36:38 - pico-train - INFO - Step 37900 -- 🔄 Training Metrics 2025-08-30 11:36:38 - pico-train - INFO - ├── Loss: 4.9262 2025-08-30 11:36:38 - pico-train - INFO - ├── Learning Rate: 1.41e-04 2025-08-30 11:36:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:37:30 - pico-train - INFO - Step 38000 -- 💾 Saving Checkpoint 2025-08-30 11:39:29 - pico-train - INFO - Step 38000 -- 📊 Evaluation Results 2025-08-30 11:39:29 - pico-train - INFO - └── paloma: inf 2025-08-30 11:39:30 - pico-train - INFO - Step 38000 -- 🔄 Training Metrics 2025-08-30 11:39:30 - pico-train - INFO - ├── Loss: 4.9291 2025-08-30 11:39:30 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-30 11:39:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:39:30 - pico-train - INFO - Step 38000 -- 📈 Saving Learning Dynamics 2025-08-30 11:40:26 - pico-train - INFO - Step 38100 -- 🔄 Training Metrics 2025-08-30 11:40:26 - pico-train - INFO - ├── Loss: 4.9438 2025-08-30 11:40:26 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-30 11:40:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:41:19 - pico-train - INFO - Step 38200 -- 🔄 Training Metrics 2025-08-30 11:41:19 - pico-train - INFO - ├── Loss: 4.9386 2025-08-30 11:41:19 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-30 11:41:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:42:11 - pico-train - INFO - Step 38300 -- 🔄 Training Metrics 2025-08-30 11:42:11 - pico-train - INFO - ├── Loss: 4.9439 2025-08-30 11:42:11 - pico-train - INFO - ├── Learning Rate: 1.40e-04 2025-08-30 11:42:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:43:04 - pico-train - INFO - Step 38400 -- 🔄 Training Metrics 2025-08-30 11:43:04 - pico-train - INFO - ├── Loss: 4.9467 2025-08-30 11:43:04 - pico-train - INFO - ├── Learning Rate: 1.39e-04 2025-08-30 11:43:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:43:56 - pico-train - INFO - Step 38500 -- 🔄 Training Metrics 2025-08-30 11:43:56 - pico-train - INFO - ├── Loss: 4.9535 2025-08-30 11:43:56 - pico-train - INFO - ├── Learning Rate: 1.39e-04 2025-08-30 11:43:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:44:49 - pico-train - INFO - Step 38600 -- 🔄 Training Metrics 2025-08-30 11:44:49 - pico-train - INFO - ├── Loss: 4.9062 2025-08-30 11:44:49 - pico-train - INFO - ├── Learning Rate: 1.39e-04 2025-08-30 11:44:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:45:42 - pico-train - INFO - Step 38700 -- 🔄 Training Metrics 2025-08-30 11:45:42 - pico-train - INFO - ├── Loss: 4.9308 2025-08-30 11:45:42 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-30 11:45:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:46:35 - pico-train - INFO - Step 38800 -- 🔄 Training Metrics 2025-08-30 11:46:35 - pico-train - INFO - ├── Loss: 4.9026 2025-08-30 11:46:35 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-30 11:46:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:47:27 - pico-train - INFO - Step 38900 -- 🔄 Training Metrics 2025-08-30 11:47:27 - pico-train - INFO - ├── Loss: 4.9223 2025-08-30 11:47:27 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-30 11:47:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:48:19 - pico-train - INFO - Step 39000 -- 🔄 Training Metrics 2025-08-30 11:48:19 - pico-train - INFO - ├── Loss: 4.9212 2025-08-30 11:48:19 - pico-train - INFO - ├── Learning Rate: 1.38e-04 2025-08-30 11:48:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:49:11 - pico-train - INFO - Step 39100 -- 🔄 Training Metrics 2025-08-30 11:49:11 - pico-train - INFO - ├── Loss: 4.9162 2025-08-30 11:49:11 - pico-train - INFO - ├── Learning Rate: 1.37e-04 2025-08-30 11:49:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:50:03 - pico-train - INFO - Step 39200 -- 🔄 Training Metrics 2025-08-30 11:50:03 - pico-train - INFO - ├── Loss: 4.9188 2025-08-30 11:50:03 - pico-train - INFO - ├── Learning Rate: 1.37e-04 2025-08-30 11:50:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:50:55 - pico-train - INFO - Step 39300 -- 🔄 Training Metrics 2025-08-30 11:50:55 - pico-train - INFO - ├── Loss: 4.9239 2025-08-30 11:50:55 - pico-train - INFO - ├── Learning Rate: 1.37e-04 2025-08-30 11:50:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:51:48 - pico-train - INFO - Step 39400 -- 🔄 Training Metrics 2025-08-30 11:51:48 - pico-train - INFO - ├── Loss: 4.9182 2025-08-30 11:51:48 - pico-train - INFO - ├── Learning Rate: 1.36e-04 2025-08-30 11:51:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:52:40 - pico-train - INFO - Step 39500 -- 🔄 Training Metrics 2025-08-30 11:52:40 - pico-train - INFO - ├── Loss: 4.9126 2025-08-30 11:52:40 - pico-train - INFO - ├── Learning Rate: 1.36e-04 2025-08-30 11:52:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:53:32 - pico-train - INFO - Step 39600 -- 🔄 Training Metrics 2025-08-30 11:53:32 - pico-train - INFO - ├── Loss: 4.9245 2025-08-30 11:53:32 - pico-train - INFO - ├── Learning Rate: 1.36e-04 2025-08-30 11:53:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:54:25 - pico-train - INFO - Step 39700 -- 🔄 Training Metrics 2025-08-30 11:54:25 - pico-train - INFO - ├── Loss: 4.9458 2025-08-30 11:54:25 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-30 11:54:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:55:17 - pico-train - INFO - Step 39800 -- 🔄 Training Metrics 2025-08-30 11:55:17 - pico-train - INFO - ├── Loss: 4.9233 2025-08-30 11:55:17 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-30 11:55:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:56:09 - pico-train - INFO - Step 39900 -- 🔄 Training Metrics 2025-08-30 11:56:09 - pico-train - INFO - ├── Loss: 4.9178 2025-08-30 11:56:09 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-30 11:56:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:57:01 - pico-train - INFO - Step 40000 -- 💾 Saving Checkpoint 2025-08-30 11:59:02 - pico-train - INFO - Step 40000 -- 📊 Evaluation Results 2025-08-30 11:59:02 - pico-train - INFO - └── paloma: inf 2025-08-30 11:59:03 - pico-train - INFO - Step 40000 -- 🔄 Training Metrics 2025-08-30 11:59:03 - pico-train - INFO - ├── Loss: 4.9145 2025-08-30 11:59:03 - pico-train - INFO - ├── Learning Rate: 1.35e-04 2025-08-30 11:59:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 11:59:03 - pico-train - INFO - Step 40000 -- 📈 Saving Learning Dynamics 2025-08-30 12:00:02 - pico-train - INFO - Step 40100 -- 🔄 Training Metrics 2025-08-30 12:00:02 - pico-train - INFO - ├── Loss: 4.9239 2025-08-30 12:00:02 - pico-train - INFO - ├── Learning Rate: 1.34e-04 2025-08-30 12:00:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:00:55 - pico-train - INFO - Step 40200 -- 🔄 Training Metrics 2025-08-30 12:00:55 - pico-train - INFO - ├── Loss: 4.9170 2025-08-30 12:00:55 - pico-train - INFO - ├── Learning Rate: 1.34e-04 2025-08-30 12:00:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:01:48 - pico-train - INFO - Step 40300 -- 🔄 Training Metrics 2025-08-30 12:01:48 - pico-train - INFO - ├── Loss: 4.9209 2025-08-30 12:01:48 - pico-train - INFO - ├── Learning Rate: 1.34e-04 2025-08-30 12:01:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:02:42 - pico-train - INFO - Step 40400 -- 🔄 Training Metrics 2025-08-30 12:02:42 - pico-train - INFO - ├── Loss: 4.9120 2025-08-30 12:02:42 - pico-train - INFO - ├── Learning Rate: 1.33e-04 2025-08-30 12:02:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:03:35 - pico-train - INFO - Step 40500 -- 🔄 Training Metrics 2025-08-30 12:03:35 - pico-train - INFO - ├── Loss: 4.9072 2025-08-30 12:03:35 - pico-train - INFO - ├── Learning Rate: 1.33e-04 2025-08-30 12:03:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:04:29 - pico-train - INFO - Step 40600 -- 🔄 Training Metrics 2025-08-30 12:04:29 - pico-train - INFO - ├── Loss: 4.9122 2025-08-30 12:04:29 - pico-train - INFO - ├── Learning Rate: 1.33e-04 2025-08-30 12:04:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:05:23 - pico-train - INFO - Step 40700 -- 🔄 Training Metrics 2025-08-30 12:05:23 - pico-train - INFO - ├── Loss: 4.9219 2025-08-30 12:05:23 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-30 12:05:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:06:15 - pico-train - INFO - Step 40800 -- 🔄 Training Metrics 2025-08-30 12:06:15 - pico-train - INFO - ├── Loss: 4.8843 2025-08-30 12:06:15 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-30 12:06:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:07:09 - pico-train - INFO - Step 40900 -- 🔄 Training Metrics 2025-08-30 12:07:09 - pico-train - INFO - ├── Loss: 4.9325 2025-08-30 12:07:09 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-30 12:07:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:08:04 - pico-train - INFO - Step 41000 -- 🔄 Training Metrics 2025-08-30 12:08:04 - pico-train - INFO - ├── Loss: 4.8745 2025-08-30 12:08:04 - pico-train - INFO - ├── Learning Rate: 1.32e-04 2025-08-30 12:08:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:08:57 - pico-train - INFO - Step 41100 -- 🔄 Training Metrics 2025-08-30 12:08:57 - pico-train - INFO - ├── Loss: 4.9077 2025-08-30 12:08:57 - pico-train - INFO - ├── Learning Rate: 1.31e-04 2025-08-30 12:08:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:09:50 - pico-train - INFO - Step 41200 -- 🔄 Training Metrics 2025-08-30 12:09:50 - pico-train - INFO - ├── Loss: 4.9190 2025-08-30 12:09:50 - pico-train - INFO - ├── Learning Rate: 1.31e-04 2025-08-30 12:09:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:10:43 - pico-train - INFO - Step 41300 -- 🔄 Training Metrics 2025-08-30 12:10:43 - pico-train - INFO - ├── Loss: 4.9054 2025-08-30 12:10:43 - pico-train - INFO - ├── Learning Rate: 1.31e-04 2025-08-30 12:10:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:11:36 - pico-train - INFO - Step 41400 -- 🔄 Training Metrics 2025-08-30 12:11:36 - pico-train - INFO - ├── Loss: 4.8996 2025-08-30 12:11:36 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-30 12:11:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:12:30 - pico-train - INFO - Step 41500 -- 🔄 Training Metrics 2025-08-30 12:12:30 - pico-train - INFO - ├── Loss: 4.9230 2025-08-30 12:12:30 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-30 12:12:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:13:25 - pico-train - INFO - Step 41600 -- 🔄 Training Metrics 2025-08-30 12:13:25 - pico-train - INFO - ├── Loss: 4.9031 2025-08-30 12:13:25 - pico-train - INFO - ├── Learning Rate: 1.30e-04 2025-08-30 12:13:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:14:17 - pico-train - INFO - Step 41700 -- 🔄 Training Metrics 2025-08-30 12:14:17 - pico-train - INFO - ├── Loss: 4.9136 2025-08-30 12:14:17 - pico-train - INFO - ├── Learning Rate: 1.29e-04 2025-08-30 12:14:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:15:11 - pico-train - INFO - Step 41800 -- 🔄 Training Metrics 2025-08-30 12:15:11 - pico-train - INFO - ├── Loss: 4.9200 2025-08-30 12:15:11 - pico-train - INFO - ├── Learning Rate: 1.29e-04 2025-08-30 12:15:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:16:04 - pico-train - INFO - Step 41900 -- 🔄 Training Metrics 2025-08-30 12:16:04 - pico-train - INFO - ├── Loss: 4.8982 2025-08-30 12:16:04 - pico-train - INFO - ├── Learning Rate: 1.29e-04 2025-08-30 12:16:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:16:58 - pico-train - INFO - Step 42000 -- 💾 Saving Checkpoint 2025-08-30 12:19:10 - pico-train - INFO - Step 42000 -- 📊 Evaluation Results 2025-08-30 12:19:10 - pico-train - INFO - └── paloma: inf 2025-08-30 12:19:12 - pico-train - INFO - Step 42000 -- 🔄 Training Metrics 2025-08-30 12:19:12 - pico-train - INFO - ├── Loss: 4.8824 2025-08-30 12:19:12 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-30 12:19:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:19:12 - pico-train - INFO - Step 42000 -- 📈 Saving Learning Dynamics 2025-08-30 12:20:09 - pico-train - INFO - Step 42100 -- 🔄 Training Metrics 2025-08-30 12:20:09 - pico-train - INFO - ├── Loss: 4.8966 2025-08-30 12:20:09 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-30 12:20:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:21:01 - pico-train - INFO - Step 42200 -- 🔄 Training Metrics 2025-08-30 12:21:01 - pico-train - INFO - ├── Loss: 4.8971 2025-08-30 12:21:01 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-30 12:21:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:21:55 - pico-train - INFO - Step 42300 -- 🔄 Training Metrics 2025-08-30 12:21:55 - pico-train - INFO - ├── Loss: 4.9271 2025-08-30 12:21:55 - pico-train - INFO - ├── Learning Rate: 1.28e-04 2025-08-30 12:21:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:22:47 - pico-train - INFO - Step 42400 -- 🔄 Training Metrics 2025-08-30 12:22:47 - pico-train - INFO - ├── Loss: 4.9046 2025-08-30 12:22:47 - pico-train - INFO - ├── Learning Rate: 1.27e-04 2025-08-30 12:22:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:23:40 - pico-train - INFO - Step 42500 -- 🔄 Training Metrics 2025-08-30 12:23:40 - pico-train - INFO - ├── Loss: 4.9010 2025-08-30 12:23:40 - pico-train - INFO - ├── Learning Rate: 1.27e-04 2025-08-30 12:23:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:24:42 - pico-train - INFO - Step 42600 -- 🔄 Training Metrics 2025-08-30 12:24:42 - pico-train - INFO - ├── Loss: 4.9314 2025-08-30 12:24:42 - pico-train - INFO - ├── Learning Rate: 1.27e-04 2025-08-30 12:24:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:25:54 - pico-train - INFO - Step 42700 -- 🔄 Training Metrics 2025-08-30 12:25:54 - pico-train - INFO - ├── Loss: 4.8923 2025-08-30 12:25:54 - pico-train - INFO - ├── Learning Rate: 1.26e-04 2025-08-30 12:25:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:26:58 - pico-train - INFO - Step 42800 -- 🔄 Training Metrics 2025-08-30 12:26:58 - pico-train - INFO - ├── Loss: 4.9007 2025-08-30 12:26:58 - pico-train - INFO - ├── Learning Rate: 1.26e-04 2025-08-30 12:26:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:27:52 - pico-train - INFO - Step 42900 -- 🔄 Training Metrics 2025-08-30 12:27:52 - pico-train - INFO - ├── Loss: 4.8903 2025-08-30 12:27:52 - pico-train - INFO - ├── Learning Rate: 1.26e-04 2025-08-30 12:27:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:28:46 - pico-train - INFO - Step 43000 -- 🔄 Training Metrics 2025-08-30 12:28:46 - pico-train - INFO - ├── Loss: 4.9252 2025-08-30 12:28:46 - pico-train - INFO - ├── Learning Rate: 1.25e-04 2025-08-30 12:28:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:29:38 - pico-train - INFO - Step 43100 -- 🔄 Training Metrics 2025-08-30 12:29:38 - pico-train - INFO - ├── Loss: 4.8924 2025-08-30 12:29:38 - pico-train - INFO - ├── Learning Rate: 1.25e-04 2025-08-30 12:29:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:30:32 - pico-train - INFO - Step 43200 -- 🔄 Training Metrics 2025-08-30 12:30:32 - pico-train - INFO - ├── Loss: 4.8955 2025-08-30 12:30:32 - pico-train - INFO - ├── Learning Rate: 1.25e-04 2025-08-30 12:30:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:31:26 - pico-train - INFO - Step 43300 -- 🔄 Training Metrics 2025-08-30 12:31:26 - pico-train - INFO - ├── Loss: 4.8651 2025-08-30 12:31:26 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-30 12:31:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:32:20 - pico-train - INFO - Step 43400 -- 🔄 Training Metrics 2025-08-30 12:32:20 - pico-train - INFO - ├── Loss: 4.9018 2025-08-30 12:32:20 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-30 12:32:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:33:13 - pico-train - INFO - Step 43500 -- 🔄 Training Metrics 2025-08-30 12:33:13 - pico-train - INFO - ├── Loss: 4.9001 2025-08-30 12:33:13 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-30 12:33:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:34:07 - pico-train - INFO - Step 43600 -- 🔄 Training Metrics 2025-08-30 12:34:07 - pico-train - INFO - ├── Loss: 4.8980 2025-08-30 12:34:07 - pico-train - INFO - ├── Learning Rate: 1.24e-04 2025-08-30 12:34:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:35:01 - pico-train - INFO - Step 43700 -- 🔄 Training Metrics 2025-08-30 12:35:01 - pico-train - INFO - ├── Loss: 4.9205 2025-08-30 12:35:01 - pico-train - INFO - ├── Learning Rate: 1.23e-04 2025-08-30 12:35:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:35:55 - pico-train - INFO - Step 43800 -- 🔄 Training Metrics 2025-08-30 12:35:55 - pico-train - INFO - ├── Loss: 4.8935 2025-08-30 12:35:55 - pico-train - INFO - ├── Learning Rate: 1.23e-04 2025-08-30 12:35:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:36:48 - pico-train - INFO - Step 43900 -- 🔄 Training Metrics 2025-08-30 12:36:48 - pico-train - INFO - ├── Loss: 4.8905 2025-08-30 12:36:48 - pico-train - INFO - ├── Learning Rate: 1.23e-04 2025-08-30 12:36:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:37:41 - pico-train - INFO - Step 44000 -- 💾 Saving Checkpoint 2025-08-30 12:39:45 - pico-train - INFO - Step 44000 -- 📊 Evaluation Results 2025-08-30 12:39:45 - pico-train - INFO - └── paloma: inf 2025-08-30 12:39:47 - pico-train - INFO - Step 44000 -- 🔄 Training Metrics 2025-08-30 12:39:47 - pico-train - INFO - ├── Loss: 4.9013 2025-08-30 12:39:47 - pico-train - INFO - ├── Learning Rate: 1.22e-04 2025-08-30 12:39:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:39:47 - pico-train - INFO - Step 44000 -- 📈 Saving Learning Dynamics 2025-08-30 12:40:45 - pico-train - INFO - Step 44100 -- 🔄 Training Metrics 2025-08-30 12:40:45 - pico-train - INFO - ├── Loss: 4.8915 2025-08-30 12:40:45 - pico-train - INFO - ├── Learning Rate: 1.22e-04 2025-08-30 12:40:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:41:39 - pico-train - INFO - Step 44200 -- 🔄 Training Metrics 2025-08-30 12:41:39 - pico-train - INFO - ├── Loss: 4.8805 2025-08-30 12:41:39 - pico-train - INFO - ├── Learning Rate: 1.22e-04 2025-08-30 12:41:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:42:32 - pico-train - INFO - Step 44300 -- 🔄 Training Metrics 2025-08-30 12:42:32 - pico-train - INFO - ├── Loss: 4.8928 2025-08-30 12:42:32 - pico-train - INFO - ├── Learning Rate: 1.21e-04 2025-08-30 12:42:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:43:26 - pico-train - INFO - Step 44400 -- 🔄 Training Metrics 2025-08-30 12:43:26 - pico-train - INFO - ├── Loss: 4.8799 2025-08-30 12:43:26 - pico-train - INFO - ├── Learning Rate: 1.21e-04 2025-08-30 12:43:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:44:19 - pico-train - INFO - Step 44500 -- 🔄 Training Metrics 2025-08-30 12:44:19 - pico-train - INFO - ├── Loss: 4.9167 2025-08-30 12:44:19 - pico-train - INFO - ├── Learning Rate: 1.21e-04 2025-08-30 12:44:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:45:12 - pico-train - INFO - Step 44600 -- 🔄 Training Metrics 2025-08-30 12:45:12 - pico-train - INFO - ├── Loss: 4.8424 2025-08-30 12:45:12 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-30 12:45:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:46:05 - pico-train - INFO - Step 44700 -- 🔄 Training Metrics 2025-08-30 12:46:05 - pico-train - INFO - ├── Loss: 4.8779 2025-08-30 12:46:05 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-30 12:46:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:47:00 - pico-train - INFO - Step 44800 -- 🔄 Training Metrics 2025-08-30 12:47:00 - pico-train - INFO - ├── Loss: 4.9088 2025-08-30 12:47:00 - pico-train - INFO - ├── Learning Rate: 1.20e-04 2025-08-30 12:47:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:47:52 - pico-train - INFO - Step 44900 -- 🔄 Training Metrics 2025-08-30 12:47:52 - pico-train - INFO - ├── Loss: 4.9030 2025-08-30 12:47:52 - pico-train - INFO - ├── Learning Rate: 1.19e-04 2025-08-30 12:47:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:48:44 - pico-train - INFO - Step 45000 -- 🔄 Training Metrics 2025-08-30 12:48:44 - pico-train - INFO - ├── Loss: 4.8993 2025-08-30 12:48:44 - pico-train - INFO - ├── Learning Rate: 1.19e-04 2025-08-30 12:48:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:49:37 - pico-train - INFO - Step 45100 -- 🔄 Training Metrics 2025-08-30 12:49:37 - pico-train - INFO - ├── Loss: 4.8970 2025-08-30 12:49:37 - pico-train - INFO - ├── Learning Rate: 1.19e-04 2025-08-30 12:49:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:50:30 - pico-train - INFO - Step 45200 -- 🔄 Training Metrics 2025-08-30 12:50:30 - pico-train - INFO - ├── Loss: 4.8831 2025-08-30 12:50:30 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-30 12:50:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:51:23 - pico-train - INFO - Step 45300 -- 🔄 Training Metrics 2025-08-30 12:51:23 - pico-train - INFO - ├── Loss: 4.8729 2025-08-30 12:51:23 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-30 12:51:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:52:16 - pico-train - INFO - Step 45400 -- 🔄 Training Metrics 2025-08-30 12:52:16 - pico-train - INFO - ├── Loss: 4.8859 2025-08-30 12:52:16 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-30 12:52:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:53:09 - pico-train - INFO - Step 45500 -- 🔄 Training Metrics 2025-08-30 12:53:09 - pico-train - INFO - ├── Loss: 4.9129 2025-08-30 12:53:09 - pico-train - INFO - ├── Learning Rate: 1.18e-04 2025-08-30 12:53:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:54:03 - pico-train - INFO - Step 45600 -- 🔄 Training Metrics 2025-08-30 12:54:03 - pico-train - INFO - ├── Loss: 4.8550 2025-08-30 12:54:03 - pico-train - INFO - ├── Learning Rate: 1.17e-04 2025-08-30 12:54:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:54:56 - pico-train - INFO - Step 45700 -- 🔄 Training Metrics 2025-08-30 12:54:56 - pico-train - INFO - ├── Loss: 4.8901 2025-08-30 12:54:56 - pico-train - INFO - ├── Learning Rate: 1.17e-04 2025-08-30 12:54:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:55:50 - pico-train - INFO - Step 45800 -- 🔄 Training Metrics 2025-08-30 12:55:50 - pico-train - INFO - ├── Loss: 4.8900 2025-08-30 12:55:50 - pico-train - INFO - ├── Learning Rate: 1.17e-04 2025-08-30 12:55:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:56:41 - pico-train - INFO - Step 45900 -- 🔄 Training Metrics 2025-08-30 12:56:41 - pico-train - INFO - ├── Loss: 4.8725 2025-08-30 12:56:41 - pico-train - INFO - ├── Learning Rate: 1.16e-04 2025-08-30 12:56:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:57:33 - pico-train - INFO - Step 46000 -- 💾 Saving Checkpoint 2025-08-30 12:59:41 - pico-train - INFO - Step 46000 -- 📊 Evaluation Results 2025-08-30 12:59:41 - pico-train - INFO - └── paloma: inf 2025-08-30 12:59:43 - pico-train - INFO - Step 46000 -- 🔄 Training Metrics 2025-08-30 12:59:43 - pico-train - INFO - ├── Loss: 4.8772 2025-08-30 12:59:43 - pico-train - INFO - ├── Learning Rate: 1.16e-04 2025-08-30 12:59:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 12:59:43 - pico-train - INFO - Step 46000 -- 📈 Saving Learning Dynamics 2025-08-30 13:00:43 - pico-train - INFO - Step 46100 -- 🔄 Training Metrics 2025-08-30 13:00:43 - pico-train - INFO - ├── Loss: 4.8649 2025-08-30 13:00:43 - pico-train - INFO - ├── Learning Rate: 1.16e-04 2025-08-30 13:00:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:01:35 - pico-train - INFO - Step 46200 -- 🔄 Training Metrics 2025-08-30 13:01:35 - pico-train - INFO - ├── Loss: 4.8980 2025-08-30 13:01:35 - pico-train - INFO - ├── Learning Rate: 1.15e-04 2025-08-30 13:01:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:02:29 - pico-train - INFO - Step 46300 -- 🔄 Training Metrics 2025-08-30 13:02:29 - pico-train - INFO - ├── Loss: 4.8867 2025-08-30 13:02:29 - pico-train - INFO - ├── Learning Rate: 1.15e-04 2025-08-30 13:02:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:03:22 - pico-train - INFO - Step 46400 -- 🔄 Training Metrics 2025-08-30 13:03:22 - pico-train - INFO - ├── Loss: 4.8807 2025-08-30 13:03:22 - pico-train - INFO - ├── Learning Rate: 1.15e-04 2025-08-30 13:03:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:04:15 - pico-train - INFO - Step 46500 -- 🔄 Training Metrics 2025-08-30 13:04:15 - pico-train - INFO - ├── Loss: 4.8779 2025-08-30 13:04:15 - pico-train - INFO - ├── Learning Rate: 1.14e-04 2025-08-30 13:04:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:05:09 - pico-train - INFO - Step 46600 -- 🔄 Training Metrics 2025-08-30 13:05:09 - pico-train - INFO - ├── Loss: 4.8908 2025-08-30 13:05:09 - pico-train - INFO - ├── Learning Rate: 1.14e-04 2025-08-30 13:05:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:06:01 - pico-train - INFO - Step 46700 -- 🔄 Training Metrics 2025-08-30 13:06:01 - pico-train - INFO - ├── Loss: 4.8882 2025-08-30 13:06:01 - pico-train - INFO - ├── Learning Rate: 1.14e-04 2025-08-30 13:06:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:06:55 - pico-train - INFO - Step 46800 -- 🔄 Training Metrics 2025-08-30 13:06:55 - pico-train - INFO - ├── Loss: 4.8877 2025-08-30 13:06:55 - pico-train - INFO - ├── Learning Rate: 1.13e-04 2025-08-30 13:06:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:07:49 - pico-train - INFO - Step 46900 -- 🔄 Training Metrics 2025-08-30 13:07:49 - pico-train - INFO - ├── Loss: 4.8686 2025-08-30 13:07:49 - pico-train - INFO - ├── Learning Rate: 1.13e-04 2025-08-30 13:07:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:08:42 - pico-train - INFO - Step 47000 -- 🔄 Training Metrics 2025-08-30 13:08:42 - pico-train - INFO - ├── Loss: 4.8701 2025-08-30 13:08:42 - pico-train - INFO - ├── Learning Rate: 1.13e-04 2025-08-30 13:08:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:09:35 - pico-train - INFO - Step 47100 -- 🔄 Training Metrics 2025-08-30 13:09:35 - pico-train - INFO - ├── Loss: 4.8670 2025-08-30 13:09:35 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-30 13:09:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:10:28 - pico-train - INFO - Step 47200 -- 🔄 Training Metrics 2025-08-30 13:10:28 - pico-train - INFO - ├── Loss: 4.8849 2025-08-30 13:10:28 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-30 13:10:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:11:22 - pico-train - INFO - Step 47300 -- 🔄 Training Metrics 2025-08-30 13:11:22 - pico-train - INFO - ├── Loss: 4.8665 2025-08-30 13:11:22 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-30 13:11:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:12:16 - pico-train - INFO - Step 47400 -- 🔄 Training Metrics 2025-08-30 13:12:16 - pico-train - INFO - ├── Loss: 4.8595 2025-08-30 13:12:16 - pico-train - INFO - ├── Learning Rate: 1.12e-04 2025-08-30 13:12:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:13:08 - pico-train - INFO - Step 47500 -- 🔄 Training Metrics 2025-08-30 13:13:08 - pico-train - INFO - ├── Loss: 4.8680 2025-08-30 13:13:08 - pico-train - INFO - ├── Learning Rate: 1.11e-04 2025-08-30 13:13:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:14:00 - pico-train - INFO - Step 47600 -- 🔄 Training Metrics 2025-08-30 13:14:00 - pico-train - INFO - ├── Loss: 4.8867 2025-08-30 13:14:00 - pico-train - INFO - ├── Learning Rate: 1.11e-04 2025-08-30 13:14:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:14:52 - pico-train - INFO - Step 47700 -- 🔄 Training Metrics 2025-08-30 13:14:52 - pico-train - INFO - ├── Loss: 4.8761 2025-08-30 13:14:52 - pico-train - INFO - ├── Learning Rate: 1.11e-04 2025-08-30 13:14:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:15:44 - pico-train - INFO - Step 47800 -- 🔄 Training Metrics 2025-08-30 13:15:44 - pico-train - INFO - ├── Loss: 4.8965 2025-08-30 13:15:44 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-30 13:15:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:16:36 - pico-train - INFO - Step 47900 -- 🔄 Training Metrics 2025-08-30 13:16:36 - pico-train - INFO - ├── Loss: 4.8890 2025-08-30 13:16:36 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-30 13:16:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:17:28 - pico-train - INFO - Step 48000 -- 💾 Saving Checkpoint 2025-08-30 13:19:28 - pico-train - INFO - Step 48000 -- 📊 Evaluation Results 2025-08-30 13:19:28 - pico-train - INFO - └── paloma: inf 2025-08-30 13:19:29 - pico-train - INFO - Step 48000 -- 🔄 Training Metrics 2025-08-30 13:19:29 - pico-train - INFO - ├── Loss: 4.8801 2025-08-30 13:19:29 - pico-train - INFO - ├── Learning Rate: 1.10e-04 2025-08-30 13:19:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:19:29 - pico-train - INFO - Step 48000 -- 📈 Saving Learning Dynamics 2025-08-30 13:20:26 - pico-train - INFO - Step 48100 -- 🔄 Training Metrics 2025-08-30 13:20:26 - pico-train - INFO - ├── Loss: 4.8751 2025-08-30 13:20:26 - pico-train - INFO - ├── Learning Rate: 1.09e-04 2025-08-30 13:20:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:21:18 - pico-train - INFO - Step 48200 -- 🔄 Training Metrics 2025-08-30 13:21:18 - pico-train - INFO - ├── Loss: 4.8703 2025-08-30 13:21:18 - pico-train - INFO - ├── Learning Rate: 1.09e-04 2025-08-30 13:21:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:22:10 - pico-train - INFO - Step 48300 -- 🔄 Training Metrics 2025-08-30 13:22:10 - pico-train - INFO - ├── Loss: 4.8749 2025-08-30 13:22:10 - pico-train - INFO - ├── Learning Rate: 1.09e-04 2025-08-30 13:22:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:23:03 - pico-train - INFO - Step 48400 -- 🔄 Training Metrics 2025-08-30 13:23:03 - pico-train - INFO - ├── Loss: 4.8782 2025-08-30 13:23:03 - pico-train - INFO - ├── Learning Rate: 1.08e-04 2025-08-30 13:23:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:23:55 - pico-train - INFO - Step 48500 -- 🔄 Training Metrics 2025-08-30 13:23:55 - pico-train - INFO - ├── Loss: 4.8676 2025-08-30 13:23:55 - pico-train - INFO - ├── Learning Rate: 1.08e-04 2025-08-30 13:23:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:24:46 - pico-train - INFO - Step 48600 -- 🔄 Training Metrics 2025-08-30 13:24:46 - pico-train - INFO - ├── Loss: 4.8610 2025-08-30 13:24:46 - pico-train - INFO - ├── Learning Rate: 1.08e-04 2025-08-30 13:24:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:25:40 - pico-train - INFO - Step 48700 -- 🔄 Training Metrics 2025-08-30 13:25:40 - pico-train - INFO - ├── Loss: 4.8672 2025-08-30 13:25:40 - pico-train - INFO - ├── Learning Rate: 1.07e-04 2025-08-30 13:25:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:26:32 - pico-train - INFO - Step 48800 -- 🔄 Training Metrics 2025-08-30 13:26:32 - pico-train - INFO - ├── Loss: 4.8771 2025-08-30 13:26:32 - pico-train - INFO - ├── Learning Rate: 1.07e-04 2025-08-30 13:26:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:27:24 - pico-train - INFO - Step 48900 -- 🔄 Training Metrics 2025-08-30 13:27:24 - pico-train - INFO - ├── Loss: 4.8739 2025-08-30 13:27:24 - pico-train - INFO - ├── Learning Rate: 1.07e-04 2025-08-30 13:27:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:28:16 - pico-train - INFO - Step 49000 -- 🔄 Training Metrics 2025-08-30 13:28:16 - pico-train - INFO - ├── Loss: 4.8754 2025-08-30 13:28:16 - pico-train - INFO - ├── Learning Rate: 1.06e-04 2025-08-30 13:28:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:29:08 - pico-train - INFO - Step 49100 -- 🔄 Training Metrics 2025-08-30 13:29:08 - pico-train - INFO - ├── Loss: 4.8521 2025-08-30 13:29:08 - pico-train - INFO - ├── Learning Rate: 1.06e-04 2025-08-30 13:29:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:30:01 - pico-train - INFO - Step 49200 -- 🔄 Training Metrics 2025-08-30 13:30:01 - pico-train - INFO - ├── Loss: 4.8698 2025-08-30 13:30:01 - pico-train - INFO - ├── Learning Rate: 1.06e-04 2025-08-30 13:30:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:30:53 - pico-train - INFO - Step 49300 -- 🔄 Training Metrics 2025-08-30 13:30:53 - pico-train - INFO - ├── Loss: 4.8818 2025-08-30 13:30:53 - pico-train - INFO - ├── Learning Rate: 1.05e-04 2025-08-30 13:30:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:31:45 - pico-train - INFO - Step 49400 -- 🔄 Training Metrics 2025-08-30 13:31:45 - pico-train - INFO - ├── Loss: 4.8477 2025-08-30 13:31:45 - pico-train - INFO - ├── Learning Rate: 1.05e-04 2025-08-30 13:31:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:32:37 - pico-train - INFO - Step 49500 -- 🔄 Training Metrics 2025-08-30 13:32:37 - pico-train - INFO - ├── Loss: 4.8804 2025-08-30 13:32:37 - pico-train - INFO - ├── Learning Rate: 1.05e-04 2025-08-30 13:32:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:33:29 - pico-train - INFO - Step 49600 -- 🔄 Training Metrics 2025-08-30 13:33:29 - pico-train - INFO - ├── Loss: 4.8608 2025-08-30 13:33:29 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-30 13:33:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:34:21 - pico-train - INFO - Step 49700 -- 🔄 Training Metrics 2025-08-30 13:34:21 - pico-train - INFO - ├── Loss: 4.8419 2025-08-30 13:34:21 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-30 13:34:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:35:14 - pico-train - INFO - Step 49800 -- 🔄 Training Metrics 2025-08-30 13:35:14 - pico-train - INFO - ├── Loss: 4.8767 2025-08-30 13:35:14 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-30 13:35:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:36:07 - pico-train - INFO - Step 49900 -- 🔄 Training Metrics 2025-08-30 13:36:07 - pico-train - INFO - ├── Loss: 4.8593 2025-08-30 13:36:07 - pico-train - INFO - ├── Learning Rate: 1.04e-04 2025-08-30 13:36:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:36:59 - pico-train - INFO - Step 50000 -- 💾 Saving Checkpoint 2025-08-30 13:39:13 - pico-train - INFO - Step 50000 -- 📊 Evaluation Results 2025-08-30 13:39:13 - pico-train - INFO - └── paloma: inf 2025-08-30 13:39:14 - pico-train - INFO - Step 50000 -- 🔄 Training Metrics 2025-08-30 13:39:14 - pico-train - INFO - ├── Loss: 4.8786 2025-08-30 13:39:14 - pico-train - INFO - ├── Learning Rate: 1.03e-04 2025-08-30 13:39:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:39:14 - pico-train - INFO - Step 50000 -- 📈 Saving Learning Dynamics 2025-08-30 13:40:12 - pico-train - INFO - Step 50100 -- 🔄 Training Metrics 2025-08-30 13:40:12 - pico-train - INFO - ├── Loss: 4.8819 2025-08-30 13:40:12 - pico-train - INFO - ├── Learning Rate: 1.03e-04 2025-08-30 13:40:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:41:06 - pico-train - INFO - Step 50200 -- 🔄 Training Metrics 2025-08-30 13:41:06 - pico-train - INFO - ├── Loss: 4.8675 2025-08-30 13:41:06 - pico-train - INFO - ├── Learning Rate: 1.03e-04 2025-08-30 13:41:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:41:59 - pico-train - INFO - Step 50300 -- 🔄 Training Metrics 2025-08-30 13:41:59 - pico-train - INFO - ├── Loss: 4.8522 2025-08-30 13:41:59 - pico-train - INFO - ├── Learning Rate: 1.02e-04 2025-08-30 13:41:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:42:52 - pico-train - INFO - Step 50400 -- 🔄 Training Metrics 2025-08-30 13:42:52 - pico-train - INFO - ├── Loss: 4.8488 2025-08-30 13:42:52 - pico-train - INFO - ├── Learning Rate: 1.02e-04 2025-08-30 13:42:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:43:46 - pico-train - INFO - Step 50500 -- 🔄 Training Metrics 2025-08-30 13:43:46 - pico-train - INFO - ├── Loss: 4.8619 2025-08-30 13:43:46 - pico-train - INFO - ├── Learning Rate: 1.02e-04 2025-08-30 13:43:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:44:39 - pico-train - INFO - Step 50600 -- 🔄 Training Metrics 2025-08-30 13:44:39 - pico-train - INFO - ├── Loss: 4.8661 2025-08-30 13:44:39 - pico-train - INFO - ├── Learning Rate: 1.01e-04 2025-08-30 13:44:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:45:33 - pico-train - INFO - Step 50700 -- 🔄 Training Metrics 2025-08-30 13:45:33 - pico-train - INFO - ├── Loss: 4.8595 2025-08-30 13:45:33 - pico-train - INFO - ├── Learning Rate: 1.01e-04 2025-08-30 13:45:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:46:27 - pico-train - INFO - Step 50800 -- 🔄 Training Metrics 2025-08-30 13:46:27 - pico-train - INFO - ├── Loss: 4.8543 2025-08-30 13:46:27 - pico-train - INFO - ├── Learning Rate: 1.01e-04 2025-08-30 13:46:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:47:19 - pico-train - INFO - Step 50900 -- 🔄 Training Metrics 2025-08-30 13:47:19 - pico-train - INFO - ├── Loss: 4.8711 2025-08-30 13:47:19 - pico-train - INFO - ├── Learning Rate: 1.00e-04 2025-08-30 13:47:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:48:13 - pico-train - INFO - Step 51000 -- 🔄 Training Metrics 2025-08-30 13:48:13 - pico-train - INFO - ├── Loss: 4.8639 2025-08-30 13:48:13 - pico-train - INFO - ├── Learning Rate: 1.00e-04 2025-08-30 13:48:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:49:06 - pico-train - INFO - Step 51100 -- 🔄 Training Metrics 2025-08-30 13:49:06 - pico-train - INFO - ├── Loss: 4.8527 2025-08-30 13:49:06 - pico-train - INFO - ├── Learning Rate: 9.97e-05 2025-08-30 13:49:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:50:01 - pico-train - INFO - Step 51200 -- 🔄 Training Metrics 2025-08-30 13:50:01 - pico-train - INFO - ├── Loss: 4.8604 2025-08-30 13:50:01 - pico-train - INFO - ├── Learning Rate: 9.94e-05 2025-08-30 13:50:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:50:54 - pico-train - INFO - Step 51300 -- 🔄 Training Metrics 2025-08-30 13:50:54 - pico-train - INFO - ├── Loss: 4.8577 2025-08-30 13:50:54 - pico-train - INFO - ├── Learning Rate: 9.90e-05 2025-08-30 13:50:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:51:47 - pico-train - INFO - Step 51400 -- 🔄 Training Metrics 2025-08-30 13:51:47 - pico-train - INFO - ├── Loss: 4.8589 2025-08-30 13:51:47 - pico-train - INFO - ├── Learning Rate: 9.87e-05 2025-08-30 13:51:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:52:40 - pico-train - INFO - Step 51500 -- 🔄 Training Metrics 2025-08-30 13:52:40 - pico-train - INFO - ├── Loss: 4.8714 2025-08-30 13:52:40 - pico-train - INFO - ├── Learning Rate: 9.84e-05 2025-08-30 13:52:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:53:34 - pico-train - INFO - Step 51600 -- 🔄 Training Metrics 2025-08-30 13:53:34 - pico-train - INFO - ├── Loss: 4.8822 2025-08-30 13:53:34 - pico-train - INFO - ├── Learning Rate: 9.81e-05 2025-08-30 13:53:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:54:27 - pico-train - INFO - Step 51700 -- 🔄 Training Metrics 2025-08-30 13:54:27 - pico-train - INFO - ├── Loss: 4.8642 2025-08-30 13:54:27 - pico-train - INFO - ├── Learning Rate: 9.78e-05 2025-08-30 13:54:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:55:20 - pico-train - INFO - Step 51800 -- 🔄 Training Metrics 2025-08-30 13:55:20 - pico-train - INFO - ├── Loss: 4.8631 2025-08-30 13:55:20 - pico-train - INFO - ├── Learning Rate: 9.74e-05 2025-08-30 13:55:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:56:13 - pico-train - INFO - Step 51900 -- 🔄 Training Metrics 2025-08-30 13:56:13 - pico-train - INFO - ├── Loss: 4.8383 2025-08-30 13:56:13 - pico-train - INFO - ├── Learning Rate: 9.71e-05 2025-08-30 13:56:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:57:06 - pico-train - INFO - Step 52000 -- 💾 Saving Checkpoint 2025-08-30 13:59:17 - pico-train - INFO - Step 52000 -- 📊 Evaluation Results 2025-08-30 13:59:17 - pico-train - INFO - └── paloma: inf 2025-08-30 13:59:18 - pico-train - INFO - Step 52000 -- 🔄 Training Metrics 2025-08-30 13:59:18 - pico-train - INFO - ├── Loss: 4.8496 2025-08-30 13:59:18 - pico-train - INFO - ├── Learning Rate: 9.68e-05 2025-08-30 13:59:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 13:59:18 - pico-train - INFO - Step 52000 -- 📈 Saving Learning Dynamics 2025-08-30 14:00:16 - pico-train - INFO - Step 52100 -- 🔄 Training Metrics 2025-08-30 14:00:16 - pico-train - INFO - ├── Loss: 4.8515 2025-08-30 14:00:16 - pico-train - INFO - ├── Learning Rate: 9.65e-05 2025-08-30 14:00:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:01:10 - pico-train - INFO - Step 52200 -- 🔄 Training Metrics 2025-08-30 14:01:10 - pico-train - INFO - ├── Loss: 4.8598 2025-08-30 14:01:10 - pico-train - INFO - ├── Learning Rate: 9.62e-05 2025-08-30 14:01:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:02:03 - pico-train - INFO - Step 52300 -- 🔄 Training Metrics 2025-08-30 14:02:03 - pico-train - INFO - ├── Loss: 4.8696 2025-08-30 14:02:03 - pico-train - INFO - ├── Learning Rate: 9.58e-05 2025-08-30 14:02:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:02:56 - pico-train - INFO - Step 52400 -- 🔄 Training Metrics 2025-08-30 14:02:56 - pico-train - INFO - ├── Loss: 4.8359 2025-08-30 14:02:56 - pico-train - INFO - ├── Learning Rate: 9.55e-05 2025-08-30 14:02:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:03:51 - pico-train - INFO - Step 52500 -- 🔄 Training Metrics 2025-08-30 14:03:51 - pico-train - INFO - ├── Loss: 4.8444 2025-08-30 14:03:51 - pico-train - INFO - ├── Learning Rate: 9.52e-05 2025-08-30 14:03:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:04:44 - pico-train - INFO - Step 52600 -- 🔄 Training Metrics 2025-08-30 14:04:44 - pico-train - INFO - ├── Loss: 4.8626 2025-08-30 14:04:44 - pico-train - INFO - ├── Learning Rate: 9.49e-05 2025-08-30 14:04:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:05:37 - pico-train - INFO - Step 52700 -- 🔄 Training Metrics 2025-08-30 14:05:37 - pico-train - INFO - ├── Loss: 4.8555 2025-08-30 14:05:37 - pico-train - INFO - ├── Learning Rate: 9.46e-05 2025-08-30 14:05:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:06:31 - pico-train - INFO - Step 52800 -- 🔄 Training Metrics 2025-08-30 14:06:31 - pico-train - INFO - ├── Loss: 4.8361 2025-08-30 14:06:31 - pico-train - INFO - ├── Learning Rate: 9.42e-05 2025-08-30 14:06:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:07:24 - pico-train - INFO - Step 52900 -- 🔄 Training Metrics 2025-08-30 14:07:24 - pico-train - INFO - ├── Loss: 4.8518 2025-08-30 14:07:24 - pico-train - INFO - ├── Learning Rate: 9.39e-05 2025-08-30 14:07:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:08:17 - pico-train - INFO - Step 53000 -- 🔄 Training Metrics 2025-08-30 14:08:17 - pico-train - INFO - ├── Loss: 4.8508 2025-08-30 14:08:17 - pico-train - INFO - ├── Learning Rate: 9.36e-05 2025-08-30 14:08:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:09:10 - pico-train - INFO - Step 53100 -- 🔄 Training Metrics 2025-08-30 14:09:10 - pico-train - INFO - ├── Loss: 4.8585 2025-08-30 14:09:10 - pico-train - INFO - ├── Learning Rate: 9.33e-05 2025-08-30 14:09:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:10:03 - pico-train - INFO - Step 53200 -- 🔄 Training Metrics 2025-08-30 14:10:03 - pico-train - INFO - ├── Loss: 4.8520 2025-08-30 14:10:03 - pico-train - INFO - ├── Learning Rate: 9.30e-05 2025-08-30 14:10:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:10:57 - pico-train - INFO - Step 53300 -- 🔄 Training Metrics 2025-08-30 14:10:57 - pico-train - INFO - ├── Loss: 4.8462 2025-08-30 14:10:57 - pico-train - INFO - ├── Learning Rate: 9.26e-05 2025-08-30 14:10:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:11:50 - pico-train - INFO - Step 53400 -- 🔄 Training Metrics 2025-08-30 14:11:50 - pico-train - INFO - ├── Loss: 4.8443 2025-08-30 14:11:50 - pico-train - INFO - ├── Learning Rate: 9.23e-05 2025-08-30 14:11:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:12:44 - pico-train - INFO - Step 53500 -- 🔄 Training Metrics 2025-08-30 14:12:44 - pico-train - INFO - ├── Loss: 4.8567 2025-08-30 14:12:44 - pico-train - INFO - ├── Learning Rate: 9.20e-05 2025-08-30 14:12:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:13:36 - pico-train - INFO - Step 53600 -- 🔄 Training Metrics 2025-08-30 14:13:36 - pico-train - INFO - ├── Loss: 4.8256 2025-08-30 14:13:36 - pico-train - INFO - ├── Learning Rate: 9.17e-05 2025-08-30 14:13:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:14:30 - pico-train - INFO - Step 53700 -- 🔄 Training Metrics 2025-08-30 14:14:30 - pico-train - INFO - ├── Loss: 4.8237 2025-08-30 14:14:30 - pico-train - INFO - ├── Learning Rate: 9.14e-05 2025-08-30 14:14:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:15:24 - pico-train - INFO - Step 53800 -- 🔄 Training Metrics 2025-08-30 14:15:24 - pico-train - INFO - ├── Loss: 4.8332 2025-08-30 14:15:24 - pico-train - INFO - ├── Learning Rate: 9.10e-05 2025-08-30 14:15:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:16:17 - pico-train - INFO - Step 53900 -- 🔄 Training Metrics 2025-08-30 14:16:17 - pico-train - INFO - ├── Loss: 4.8663 2025-08-30 14:16:17 - pico-train - INFO - ├── Learning Rate: 9.07e-05 2025-08-30 14:16:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:17:08 - pico-train - INFO - Step 54000 -- 💾 Saving Checkpoint 2025-08-30 14:19:06 - pico-train - INFO - Step 54000 -- 📊 Evaluation Results 2025-08-30 14:19:06 - pico-train - INFO - └── paloma: inf 2025-08-30 14:19:08 - pico-train - INFO - Step 54000 -- 🔄 Training Metrics 2025-08-30 14:19:08 - pico-train - INFO - ├── Loss: 4.8621 2025-08-30 14:19:08 - pico-train - INFO - ├── Learning Rate: 9.04e-05 2025-08-30 14:19:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:19:08 - pico-train - INFO - Step 54000 -- 📈 Saving Learning Dynamics 2025-08-30 14:20:05 - pico-train - INFO - Step 54100 -- 🔄 Training Metrics 2025-08-30 14:20:05 - pico-train - INFO - ├── Loss: 4.8374 2025-08-30 14:20:05 - pico-train - INFO - ├── Learning Rate: 9.01e-05 2025-08-30 14:20:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:20:59 - pico-train - INFO - Step 54200 -- 🔄 Training Metrics 2025-08-30 14:20:59 - pico-train - INFO - ├── Loss: 4.8494 2025-08-30 14:20:59 - pico-train - INFO - ├── Learning Rate: 8.98e-05 2025-08-30 14:20:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:21:52 - pico-train - INFO - Step 54300 -- 🔄 Training Metrics 2025-08-30 14:21:52 - pico-train - INFO - ├── Loss: 4.8265 2025-08-30 14:21:52 - pico-train - INFO - ├── Learning Rate: 8.94e-05 2025-08-30 14:21:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:22:45 - pico-train - INFO - Step 54400 -- 🔄 Training Metrics 2025-08-30 14:22:45 - pico-train - INFO - ├── Loss: 4.8626 2025-08-30 14:22:45 - pico-train - INFO - ├── Learning Rate: 8.91e-05 2025-08-30 14:22:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:23:38 - pico-train - INFO - Step 54500 -- 🔄 Training Metrics 2025-08-30 14:23:38 - pico-train - INFO - ├── Loss: 4.8459 2025-08-30 14:23:38 - pico-train - INFO - ├── Learning Rate: 8.88e-05 2025-08-30 14:23:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:24:32 - pico-train - INFO - Step 54600 -- 🔄 Training Metrics 2025-08-30 14:24:32 - pico-train - INFO - ├── Loss: 4.8332 2025-08-30 14:24:32 - pico-train - INFO - ├── Learning Rate: 8.85e-05 2025-08-30 14:24:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:25:25 - pico-train - INFO - Step 54700 -- 🔄 Training Metrics 2025-08-30 14:25:25 - pico-train - INFO - ├── Loss: 4.8507 2025-08-30 14:25:25 - pico-train - INFO - ├── Learning Rate: 8.82e-05 2025-08-30 14:25:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:26:19 - pico-train - INFO - Step 54800 -- 🔄 Training Metrics 2025-08-30 14:26:19 - pico-train - INFO - ├── Loss: 4.8588 2025-08-30 14:26:19 - pico-train - INFO - ├── Learning Rate: 8.78e-05 2025-08-30 14:26:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:27:12 - pico-train - INFO - Step 54900 -- 🔄 Training Metrics 2025-08-30 14:27:12 - pico-train - INFO - ├── Loss: 4.8781 2025-08-30 14:27:12 - pico-train - INFO - ├── Learning Rate: 8.75e-05 2025-08-30 14:27:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:28:05 - pico-train - INFO - Step 55000 -- 🔄 Training Metrics 2025-08-30 14:28:05 - pico-train - INFO - ├── Loss: 4.8365 2025-08-30 14:28:05 - pico-train - INFO - ├── Learning Rate: 8.72e-05 2025-08-30 14:28:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:29:00 - pico-train - INFO - Step 55100 -- 🔄 Training Metrics 2025-08-30 14:29:00 - pico-train - INFO - ├── Loss: 4.8395 2025-08-30 14:29:00 - pico-train - INFO - ├── Learning Rate: 8.69e-05 2025-08-30 14:29:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:29:53 - pico-train - INFO - Step 55200 -- 🔄 Training Metrics 2025-08-30 14:29:53 - pico-train - INFO - ├── Loss: 4.8306 2025-08-30 14:29:53 - pico-train - INFO - ├── Learning Rate: 8.66e-05 2025-08-30 14:29:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:30:47 - pico-train - INFO - Step 55300 -- 🔄 Training Metrics 2025-08-30 14:30:47 - pico-train - INFO - ├── Loss: 4.8421 2025-08-30 14:30:47 - pico-train - INFO - ├── Learning Rate: 8.63e-05 2025-08-30 14:30:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:31:40 - pico-train - INFO - Step 55400 -- 🔄 Training Metrics 2025-08-30 14:31:40 - pico-train - INFO - ├── Loss: 4.8538 2025-08-30 14:31:40 - pico-train - INFO - ├── Learning Rate: 8.59e-05 2025-08-30 14:31:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:32:33 - pico-train - INFO - Step 55500 -- 🔄 Training Metrics 2025-08-30 14:32:33 - pico-train - INFO - ├── Loss: 4.8317 2025-08-30 14:32:33 - pico-train - INFO - ├── Learning Rate: 8.56e-05 2025-08-30 14:32:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:33:27 - pico-train - INFO - Step 55600 -- 🔄 Training Metrics 2025-08-30 14:33:27 - pico-train - INFO - ├── Loss: 4.8330 2025-08-30 14:33:27 - pico-train - INFO - ├── Learning Rate: 8.53e-05 2025-08-30 14:33:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:34:21 - pico-train - INFO - Step 55700 -- 🔄 Training Metrics 2025-08-30 14:34:21 - pico-train - INFO - ├── Loss: 4.8138 2025-08-30 14:34:21 - pico-train - INFO - ├── Learning Rate: 8.50e-05 2025-08-30 14:34:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:35:14 - pico-train - INFO - Step 55800 -- 🔄 Training Metrics 2025-08-30 14:35:14 - pico-train - INFO - ├── Loss: 4.8473 2025-08-30 14:35:14 - pico-train - INFO - ├── Learning Rate: 8.47e-05 2025-08-30 14:35:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:36:05 - pico-train - INFO - Step 55900 -- 🔄 Training Metrics 2025-08-30 14:36:05 - pico-train - INFO - ├── Loss: 4.8469 2025-08-30 14:36:05 - pico-train - INFO - ├── Learning Rate: 8.44e-05 2025-08-30 14:36:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:36:57 - pico-train - INFO - Step 56000 -- 💾 Saving Checkpoint 2025-08-30 14:39:13 - pico-train - INFO - Step 56000 -- 📊 Evaluation Results 2025-08-30 14:39:13 - pico-train - INFO - └── paloma: inf 2025-08-30 14:39:15 - pico-train - INFO - Step 56000 -- 🔄 Training Metrics 2025-08-30 14:39:15 - pico-train - INFO - ├── Loss: 4.8561 2025-08-30 14:39:15 - pico-train - INFO - ├── Learning Rate: 8.40e-05 2025-08-30 14:39:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:39:15 - pico-train - INFO - Step 56000 -- 📈 Saving Learning Dynamics 2025-08-30 14:40:12 - pico-train - INFO - Step 56100 -- 🔄 Training Metrics 2025-08-30 14:40:12 - pico-train - INFO - ├── Loss: 4.8491 2025-08-30 14:40:12 - pico-train - INFO - ├── Learning Rate: 8.37e-05 2025-08-30 14:40:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:41:05 - pico-train - INFO - Step 56200 -- 🔄 Training Metrics 2025-08-30 14:41:05 - pico-train - INFO - ├── Loss: 4.8459 2025-08-30 14:41:05 - pico-train - INFO - ├── Learning Rate: 8.34e-05 2025-08-30 14:41:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:41:57 - pico-train - INFO - Step 56300 -- 🔄 Training Metrics 2025-08-30 14:41:57 - pico-train - INFO - ├── Loss: 4.8345 2025-08-30 14:41:57 - pico-train - INFO - ├── Learning Rate: 8.31e-05 2025-08-30 14:41:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:42:50 - pico-train - INFO - Step 56400 -- 🔄 Training Metrics 2025-08-30 14:42:50 - pico-train - INFO - ├── Loss: 4.8510 2025-08-30 14:42:50 - pico-train - INFO - ├── Learning Rate: 8.28e-05 2025-08-30 14:42:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:43:43 - pico-train - INFO - Step 56500 -- 🔄 Training Metrics 2025-08-30 14:43:43 - pico-train - INFO - ├── Loss: 4.8172 2025-08-30 14:43:43 - pico-train - INFO - ├── Learning Rate: 8.25e-05 2025-08-30 14:43:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:44:35 - pico-train - INFO - Step 56600 -- 🔄 Training Metrics 2025-08-30 14:44:35 - pico-train - INFO - ├── Loss: 4.8297 2025-08-30 14:44:35 - pico-train - INFO - ├── Learning Rate: 8.21e-05 2025-08-30 14:44:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:45:27 - pico-train - INFO - Step 56700 -- 🔄 Training Metrics 2025-08-30 14:45:27 - pico-train - INFO - ├── Loss: 4.8399 2025-08-30 14:45:27 - pico-train - INFO - ├── Learning Rate: 8.18e-05 2025-08-30 14:45:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:46:19 - pico-train - INFO - Step 56800 -- 🔄 Training Metrics 2025-08-30 14:46:19 - pico-train - INFO - ├── Loss: 4.8370 2025-08-30 14:46:19 - pico-train - INFO - ├── Learning Rate: 8.15e-05 2025-08-30 14:46:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:47:11 - pico-train - INFO - Step 56900 -- 🔄 Training Metrics 2025-08-30 14:47:11 - pico-train - INFO - ├── Loss: 4.8458 2025-08-30 14:47:11 - pico-train - INFO - ├── Learning Rate: 8.12e-05 2025-08-30 14:47:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:48:04 - pico-train - INFO - Step 57000 -- 🔄 Training Metrics 2025-08-30 14:48:04 - pico-train - INFO - ├── Loss: 4.8466 2025-08-30 14:48:04 - pico-train - INFO - ├── Learning Rate: 8.09e-05 2025-08-30 14:48:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:48:57 - pico-train - INFO - Step 57100 -- 🔄 Training Metrics 2025-08-30 14:48:57 - pico-train - INFO - ├── Loss: 4.8173 2025-08-30 14:48:57 - pico-train - INFO - ├── Learning Rate: 8.06e-05 2025-08-30 14:48:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:49:49 - pico-train - INFO - Step 57200 -- 🔄 Training Metrics 2025-08-30 14:49:49 - pico-train - INFO - ├── Loss: 4.8302 2025-08-30 14:49:49 - pico-train - INFO - ├── Learning Rate: 8.03e-05 2025-08-30 14:49:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:50:41 - pico-train - INFO - Step 57300 -- 🔄 Training Metrics 2025-08-30 14:50:41 - pico-train - INFO - ├── Loss: 4.8262 2025-08-30 14:50:41 - pico-train - INFO - ├── Learning Rate: 7.99e-05 2025-08-30 14:50:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:51:33 - pico-train - INFO - Step 57400 -- 🔄 Training Metrics 2025-08-30 14:51:33 - pico-train - INFO - ├── Loss: 4.8268 2025-08-30 14:51:33 - pico-train - INFO - ├── Learning Rate: 7.96e-05 2025-08-30 14:51:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:52:25 - pico-train - INFO - Step 57500 -- 🔄 Training Metrics 2025-08-30 14:52:25 - pico-train - INFO - ├── Loss: 4.8415 2025-08-30 14:52:25 - pico-train - INFO - ├── Learning Rate: 7.93e-05 2025-08-30 14:52:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:53:19 - pico-train - INFO - Step 57600 -- 🔄 Training Metrics 2025-08-30 14:53:19 - pico-train - INFO - ├── Loss: 4.8350 2025-08-30 14:53:19 - pico-train - INFO - ├── Learning Rate: 7.90e-05 2025-08-30 14:53:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:54:11 - pico-train - INFO - Step 57700 -- 🔄 Training Metrics 2025-08-30 14:54:11 - pico-train - INFO - ├── Loss: 4.8597 2025-08-30 14:54:11 - pico-train - INFO - ├── Learning Rate: 7.87e-05 2025-08-30 14:54:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:55:03 - pico-train - INFO - Step 57800 -- 🔄 Training Metrics 2025-08-30 14:55:03 - pico-train - INFO - ├── Loss: 4.8310 2025-08-30 14:55:03 - pico-train - INFO - ├── Learning Rate: 7.84e-05 2025-08-30 14:55:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:55:55 - pico-train - INFO - Step 57900 -- 🔄 Training Metrics 2025-08-30 14:55:55 - pico-train - INFO - ├── Loss: 4.8333 2025-08-30 14:55:55 - pico-train - INFO - ├── Learning Rate: 7.81e-05 2025-08-30 14:55:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:56:47 - pico-train - INFO - Step 58000 -- 💾 Saving Checkpoint 2025-08-30 14:58:46 - pico-train - INFO - Step 58000 -- 📊 Evaluation Results 2025-08-30 14:58:46 - pico-train - INFO - └── paloma: inf 2025-08-30 14:58:48 - pico-train - INFO - Step 58000 -- 🔄 Training Metrics 2025-08-30 14:58:48 - pico-train - INFO - ├── Loss: 4.8290 2025-08-30 14:58:48 - pico-train - INFO - ├── Learning Rate: 7.77e-05 2025-08-30 14:58:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 14:58:48 - pico-train - INFO - Step 58000 -- 📈 Saving Learning Dynamics 2025-08-30 14:59:46 - pico-train - INFO - Step 58100 -- 🔄 Training Metrics 2025-08-30 14:59:46 - pico-train - INFO - ├── Loss: 4.8301 2025-08-30 14:59:46 - pico-train - INFO - ├── Learning Rate: 7.74e-05 2025-08-30 14:59:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:00:39 - pico-train - INFO - Step 58200 -- 🔄 Training Metrics 2025-08-30 15:00:39 - pico-train - INFO - ├── Loss: 4.8193 2025-08-30 15:00:39 - pico-train - INFO - ├── Learning Rate: 7.71e-05 2025-08-30 15:00:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:01:32 - pico-train - INFO - Step 58300 -- 🔄 Training Metrics 2025-08-30 15:01:32 - pico-train - INFO - ├── Loss: 4.8361 2025-08-30 15:01:32 - pico-train - INFO - ├── Learning Rate: 7.68e-05 2025-08-30 15:01:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:02:25 - pico-train - INFO - Step 58400 -- 🔄 Training Metrics 2025-08-30 15:02:25 - pico-train - INFO - ├── Loss: 4.8375 2025-08-30 15:02:25 - pico-train - INFO - ├── Learning Rate: 7.65e-05 2025-08-30 15:02:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:03:19 - pico-train - INFO - Step 58500 -- 🔄 Training Metrics 2025-08-30 15:03:19 - pico-train - INFO - ├── Loss: 4.8183 2025-08-30 15:03:19 - pico-train - INFO - ├── Learning Rate: 7.62e-05 2025-08-30 15:03:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:04:13 - pico-train - INFO - Step 58600 -- 🔄 Training Metrics 2025-08-30 15:04:13 - pico-train - INFO - ├── Loss: 4.8259 2025-08-30 15:04:13 - pico-train - INFO - ├── Learning Rate: 7.59e-05 2025-08-30 15:04:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:05:05 - pico-train - INFO - Step 58700 -- 🔄 Training Metrics 2025-08-30 15:05:05 - pico-train - INFO - ├── Loss: 4.8395 2025-08-30 15:05:05 - pico-train - INFO - ├── Learning Rate: 7.56e-05 2025-08-30 15:05:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:05:59 - pico-train - INFO - Step 58800 -- 🔄 Training Metrics 2025-08-30 15:05:59 - pico-train - INFO - ├── Loss: 4.8104 2025-08-30 15:05:59 - pico-train - INFO - ├── Learning Rate: 7.53e-05 2025-08-30 15:05:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:06:53 - pico-train - INFO - Step 58900 -- 🔄 Training Metrics 2025-08-30 15:06:53 - pico-train - INFO - ├── Loss: 4.8455 2025-08-30 15:06:53 - pico-train - INFO - ├── Learning Rate: 7.49e-05 2025-08-30 15:06:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:07:46 - pico-train - INFO - Step 59000 -- 🔄 Training Metrics 2025-08-30 15:07:46 - pico-train - INFO - ├── Loss: 4.8379 2025-08-30 15:07:46 - pico-train - INFO - ├── Learning Rate: 7.46e-05 2025-08-30 15:07:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:08:39 - pico-train - INFO - Step 59100 -- 🔄 Training Metrics 2025-08-30 15:08:39 - pico-train - INFO - ├── Loss: 4.8267 2025-08-30 15:08:39 - pico-train - INFO - ├── Learning Rate: 7.43e-05 2025-08-30 15:08:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:09:32 - pico-train - INFO - Step 59200 -- 🔄 Training Metrics 2025-08-30 15:09:32 - pico-train - INFO - ├── Loss: 4.8410 2025-08-30 15:09:32 - pico-train - INFO - ├── Learning Rate: 7.40e-05 2025-08-30 15:09:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:10:26 - pico-train - INFO - Step 59300 -- 🔄 Training Metrics 2025-08-30 15:10:26 - pico-train - INFO - ├── Loss: 4.8488 2025-08-30 15:10:26 - pico-train - INFO - ├── Learning Rate: 7.37e-05 2025-08-30 15:10:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:11:19 - pico-train - INFO - Step 59400 -- 🔄 Training Metrics 2025-08-30 15:11:19 - pico-train - INFO - ├── Loss: 4.8227 2025-08-30 15:11:19 - pico-train - INFO - ├── Learning Rate: 7.34e-05 2025-08-30 15:11:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:12:12 - pico-train - INFO - Step 59500 -- 🔄 Training Metrics 2025-08-30 15:12:12 - pico-train - INFO - ├── Loss: 4.8042 2025-08-30 15:12:12 - pico-train - INFO - ├── Learning Rate: 7.31e-05 2025-08-30 15:12:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:13:05 - pico-train - INFO - Step 59600 -- 🔄 Training Metrics 2025-08-30 15:13:05 - pico-train - INFO - ├── Loss: 4.8441 2025-08-30 15:13:05 - pico-train - INFO - ├── Learning Rate: 7.28e-05 2025-08-30 15:13:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:13:58 - pico-train - INFO - Step 59700 -- 🔄 Training Metrics 2025-08-30 15:13:58 - pico-train - INFO - ├── Loss: 4.8590 2025-08-30 15:13:58 - pico-train - INFO - ├── Learning Rate: 7.25e-05 2025-08-30 15:13:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:14:52 - pico-train - INFO - Step 59800 -- 🔄 Training Metrics 2025-08-30 15:14:52 - pico-train - INFO - ├── Loss: 4.8339 2025-08-30 15:14:52 - pico-train - INFO - ├── Learning Rate: 7.22e-05 2025-08-30 15:14:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:15:45 - pico-train - INFO - Step 59900 -- 🔄 Training Metrics 2025-08-30 15:15:45 - pico-train - INFO - ├── Loss: 4.8216 2025-08-30 15:15:45 - pico-train - INFO - ├── Learning Rate: 7.19e-05 2025-08-30 15:15:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:16:38 - pico-train - INFO - Step 60000 -- 💾 Saving Checkpoint 2025-08-30 15:18:54 - pico-train - INFO - Step 60000 -- 📊 Evaluation Results 2025-08-30 15:18:54 - pico-train - INFO - └── paloma: inf 2025-08-30 15:18:56 - pico-train - INFO - Step 60000 -- 🔄 Training Metrics 2025-08-30 15:18:56 - pico-train - INFO - ├── Loss: 4.8345 2025-08-30 15:18:56 - pico-train - INFO - ├── Learning Rate: 7.15e-05 2025-08-30 15:18:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:18:56 - pico-train - INFO - Step 60000 -- 📈 Saving Learning Dynamics 2025-08-30 15:19:55 - pico-train - INFO - Step 60100 -- 🔄 Training Metrics 2025-08-30 15:19:55 - pico-train - INFO - ├── Loss: 4.8207 2025-08-30 15:19:55 - pico-train - INFO - ├── Learning Rate: 7.12e-05 2025-08-30 15:19:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:20:49 - pico-train - INFO - Step 60200 -- 🔄 Training Metrics 2025-08-30 15:20:49 - pico-train - INFO - ├── Loss: 4.8181 2025-08-30 15:20:49 - pico-train - INFO - ├── Learning Rate: 7.09e-05 2025-08-30 15:20:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:21:41 - pico-train - INFO - Step 60300 -- 🔄 Training Metrics 2025-08-30 15:21:41 - pico-train - INFO - ├── Loss: 4.8059 2025-08-30 15:21:41 - pico-train - INFO - ├── Learning Rate: 7.06e-05 2025-08-30 15:21:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:22:33 - pico-train - INFO - Step 60400 -- 🔄 Training Metrics 2025-08-30 15:22:33 - pico-train - INFO - ├── Loss: 4.8367 2025-08-30 15:22:33 - pico-train - INFO - ├── Learning Rate: 7.03e-05 2025-08-30 15:22:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:23:25 - pico-train - INFO - Step 60500 -- 🔄 Training Metrics 2025-08-30 15:23:25 - pico-train - INFO - ├── Loss: 4.8237 2025-08-30 15:23:25 - pico-train - INFO - ├── Learning Rate: 7.00e-05 2025-08-30 15:23:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:24:18 - pico-train - INFO - Step 60600 -- 🔄 Training Metrics 2025-08-30 15:24:18 - pico-train - INFO - ├── Loss: 4.8291 2025-08-30 15:24:18 - pico-train - INFO - ├── Learning Rate: 6.97e-05 2025-08-30 15:24:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:25:10 - pico-train - INFO - Step 60700 -- 🔄 Training Metrics 2025-08-30 15:25:10 - pico-train - INFO - ├── Loss: 4.8317 2025-08-30 15:25:10 - pico-train - INFO - ├── Learning Rate: 6.94e-05 2025-08-30 15:25:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:26:03 - pico-train - INFO - Step 60800 -- 🔄 Training Metrics 2025-08-30 15:26:03 - pico-train - INFO - ├── Loss: 4.8204 2025-08-30 15:26:03 - pico-train - INFO - ├── Learning Rate: 6.91e-05 2025-08-30 15:26:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:26:54 - pico-train - INFO - Step 60900 -- 🔄 Training Metrics 2025-08-30 15:26:54 - pico-train - INFO - ├── Loss: 4.8455 2025-08-30 15:26:54 - pico-train - INFO - ├── Learning Rate: 6.88e-05 2025-08-30 15:26:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:27:47 - pico-train - INFO - Step 61000 -- 🔄 Training Metrics 2025-08-30 15:27:47 - pico-train - INFO - ├── Loss: 4.8133 2025-08-30 15:27:47 - pico-train - INFO - ├── Learning Rate: 6.85e-05 2025-08-30 15:27:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:28:39 - pico-train - INFO - Step 61100 -- 🔄 Training Metrics 2025-08-30 15:28:39 - pico-train - INFO - ├── Loss: 4.8155 2025-08-30 15:28:39 - pico-train - INFO - ├── Learning Rate: 6.82e-05 2025-08-30 15:28:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:29:32 - pico-train - INFO - Step 61200 -- 🔄 Training Metrics 2025-08-30 15:29:32 - pico-train - INFO - ├── Loss: 4.8151 2025-08-30 15:29:32 - pico-train - INFO - ├── Learning Rate: 6.79e-05 2025-08-30 15:29:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:30:24 - pico-train - INFO - Step 61300 -- 🔄 Training Metrics 2025-08-30 15:30:24 - pico-train - INFO - ├── Loss: 4.8111 2025-08-30 15:30:24 - pico-train - INFO - ├── Learning Rate: 6.76e-05 2025-08-30 15:30:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:31:16 - pico-train - INFO - Step 61400 -- 🔄 Training Metrics 2025-08-30 15:31:16 - pico-train - INFO - ├── Loss: 4.8221 2025-08-30 15:31:16 - pico-train - INFO - ├── Learning Rate: 6.73e-05 2025-08-30 15:31:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:32:09 - pico-train - INFO - Step 61500 -- 🔄 Training Metrics 2025-08-30 15:32:09 - pico-train - INFO - ├── Loss: 4.8183 2025-08-30 15:32:09 - pico-train - INFO - ├── Learning Rate: 6.70e-05 2025-08-30 15:32:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:33:02 - pico-train - INFO - Step 61600 -- 🔄 Training Metrics 2025-08-30 15:33:02 - pico-train - INFO - ├── Loss: 4.8133 2025-08-30 15:33:02 - pico-train - INFO - ├── Learning Rate: 6.67e-05 2025-08-30 15:33:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:33:54 - pico-train - INFO - Step 61700 -- 🔄 Training Metrics 2025-08-30 15:33:54 - pico-train - INFO - ├── Loss: 4.8242 2025-08-30 15:33:54 - pico-train - INFO - ├── Learning Rate: 6.64e-05 2025-08-30 15:33:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:34:46 - pico-train - INFO - Step 61800 -- 🔄 Training Metrics 2025-08-30 15:34:46 - pico-train - INFO - ├── Loss: 4.8117 2025-08-30 15:34:46 - pico-train - INFO - ├── Learning Rate: 6.61e-05 2025-08-30 15:34:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:35:38 - pico-train - INFO - Step 61900 -- 🔄 Training Metrics 2025-08-30 15:35:38 - pico-train - INFO - ├── Loss: 4.8329 2025-08-30 15:35:38 - pico-train - INFO - ├── Learning Rate: 6.58e-05 2025-08-30 15:35:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 15:36:30 - pico-train - INFO - Step 62000 -- 💾 Saving Checkpoint