2025-08-30 02:46:39 - pico-train - INFO - Step 32500 -- 📊 Evaluation Results 2025-08-30 02:46:39 - pico-train - INFO - └── paloma: 3.383932336875151e+26 2025-08-30 02:46:41 - pico-train - INFO - ================================================== 2025-08-30 02:46:41 - pico-train - INFO - ✨ Training Configuration 2025-08-30 02:46:41 - pico-train - INFO - ================================================== 2025-08-30 02:46:41 - pico-train - INFO - ╭─────────────────────────────────────────────────────╮ 2025-08-30 02:46:41 - pico-train - INFO - │ checkpointing: │ 2025-08-30 02:46:41 - pico-train - INFO - │ checkpoints_dir: checkpoints │ 2025-08-30 02:46:41 - pico-train - INFO - │ evaluation: │ 2025-08-30 02:46:41 - pico-train - INFO - │ eval_results_dir: eval_results │ 2025-08-30 02:46:41 - pico-train - INFO - │ fabric_checkpoint_dir: fabric_state │ 2025-08-30 02:46:41 - pico-train - INFO - │ fabric_checkpoint_filename: checkpoint.pt │ 2025-08-30 02:46:41 - pico-train - INFO - │ hf_checkpoint: │ 2025-08-30 02:46:41 - pico-train - INFO - │ collection_slug: null │ 2025-08-30 02:46:41 - pico-train - INFO - │ repo_id: ThomasTheMaker/pico-decoder-tiny │ 2025-08-30 02:46:41 - pico-train - INFO - │ learning_dynamics: │ 2025-08-30 02:46:41 - pico-train - INFO - │ batch_size: 1 │ 2025-08-30 02:46:41 - pico-train - INFO - │ eval_data: null │ 2025-08-30 02:46:41 - pico-train - INFO - │ layer_suffixes: │ 2025-08-30 02:46:41 - pico-train - INFO - │ - attention.v_proj │ 2025-08-30 02:46:41 - pico-train - INFO - │ - attention.o_proj │ 2025-08-30 02:46:41 - pico-train - INFO - │ - swiglu.w_2 │ 2025-08-30 02:46:41 - pico-train - INFO - │ sequence_idx: -1 │ 2025-08-30 02:46:41 - pico-train - INFO - │ learning_dynamics_dir: learning_dynamics │ 2025-08-30 02:46:41 - pico-train - INFO - │ logs_dir: logs │ 2025-08-30 02:46:41 - pico-train - INFO - │ run_name: pico-decoder-tiny-dolma5M-v1 │ 2025-08-30 02:46:41 - pico-train - INFO - │ runs_dir: runs │ 2025-08-30 02:46:41 - pico-train - INFO - │ save_every_n_steps: 500 │ 2025-08-30 02:46:41 - pico-train - INFO - │ save_to_hf: true │ 2025-08-30 02:46:41 - pico-train - INFO - │ training: │ 2025-08-30 02:46:41 - pico-train - INFO - │ auto_resume: true │ 2025-08-30 02:46:41 - pico-train - INFO - │ data: │ 2025-08-30 02:46:41 - pico-train - INFO - │ dataloader: │ 2025-08-30 02:46:41 - pico-train - INFO - │ batch_size: 4 │ 2025-08-30 02:46:41 - pico-train - INFO - │ dataset: │ 2025-08-30 02:46:41 - pico-train - INFO - │ name: ThomasTheMaker/pretokenized-dolma-5M │ 2025-08-30 02:46:41 - pico-train - INFO - │ tokenizer: │ 2025-08-30 02:46:41 - pico-train - INFO - │ name: allenai/OLMo-7B-0724-hf │ 2025-08-30 02:46:41 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-30 02:46:41 - pico-train - INFO - │ evaluation: │ 2025-08-30 02:46:41 - pico-train - INFO - │ metrics: │ 2025-08-30 02:46:41 - pico-train - INFO - │ - paloma │ 2025-08-30 02:46:41 - pico-train - INFO - │ paloma: │ 2025-08-30 02:46:41 - pico-train - INFO - │ batch_size: 1 │ 2025-08-30 02:46:41 - pico-train - INFO - │ dataset_name: pico-lm/pretokenized-paloma-tinsy │ 2025-08-30 02:46:41 - pico-train - INFO - │ dataset_split: val │ 2025-08-30 02:46:41 - pico-train - INFO - │ max_length: 2048 │ 2025-08-30 02:46:41 - pico-train - INFO - │ model: │ 2025-08-30 02:46:41 - pico-train - INFO - │ activation_hidden_dim: 384 │ 2025-08-30 02:46:41 - pico-train - INFO - │ attention_n_heads: 12 │ 2025-08-30 02:46:41 - pico-train - INFO - │ attention_n_kv_heads: 4 │ 2025-08-30 02:46:41 - pico-train - INFO - │ batch_size: 1024 │ 2025-08-30 02:46:41 - pico-train - INFO - │ d_model: 96 │ 2025-08-30 02:46:41 - pico-train - INFO - │ max_seq_len: 2048 │ 2025-08-30 02:46:41 - pico-train - INFO - │ model_type: pico_decoder │ 2025-08-30 02:46:41 - pico-train - INFO - │ n_layers: 12 │ 2025-08-30 02:46:41 - pico-train - INFO - │ norm_eps: 1.0e-06 │ 2025-08-30 02:46:41 - pico-train - INFO - │ position_emb_theta: 10000.0 │ 2025-08-30 02:46:41 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-30 02:46:41 - pico-train - INFO - │ monitoring: │ 2025-08-30 02:46:41 - pico-train - INFO - │ logging: │ 2025-08-30 02:46:41 - pico-train - INFO - │ log_every_n_steps: 25 │ 2025-08-30 02:46:41 - pico-train - INFO - │ log_level: INFO │ 2025-08-30 02:46:41 - pico-train - INFO - │ save_to_wandb: false │ 2025-08-30 02:46:41 - pico-train - INFO - │ wandb: │ 2025-08-30 02:46:41 - pico-train - INFO - │ entity: boymyc │ 2025-08-30 02:46:41 - pico-train - INFO - │ project: pico-decoder-tiny │ 2025-08-30 02:46:41 - pico-train - INFO - │ training: │ 2025-08-30 02:46:41 - pico-train - INFO - │ fabric: │ 2025-08-30 02:46:41 - pico-train - INFO - │ accelerator: cuda │ 2025-08-30 02:46:41 - pico-train - INFO - │ num_devices: 1 │ 2025-08-30 02:46:41 - pico-train - INFO - │ num_nodes: 1 │ 2025-08-30 02:46:41 - pico-train - INFO - │ precision: bf16-mixed │ 2025-08-30 02:46:41 - pico-train - INFO - │ max_steps: 20000 │ 2025-08-30 02:46:41 - pico-train - INFO - │ optimization: │ 2025-08-30 02:46:41 - pico-train - INFO - │ gradient_accumulation_steps: 4 │ 2025-08-30 02:46:41 - pico-train - INFO - │ lr: 5.0e-05 │ 2025-08-30 02:46:41 - pico-train - INFO - │ lr_scheduler: cosine │ 2025-08-30 02:46:41 - pico-train - INFO - │ lr_warmup_steps: 8000 │ 2025-08-30 02:46:41 - pico-train - INFO - │ optimizer: adamw │ 2025-08-30 02:46:41 - pico-train - INFO - │ │ 2025-08-30 02:46:41 - pico-train - INFO - ╰─────────────────────────────────────────────────────╯ 2025-08-30 02:46:41 - pico-train - INFO - ================================================== 2025-08-30 02:46:41 - pico-train - INFO - ⛭ Runtime Summary: 2025-08-30 02:46:41 - pico-train - INFO - ================================================== 2025-08-30 02:46:41 - pico-train - INFO - Starting from step: 32500 2025-08-30 02:46:41 - pico-train - INFO - Model Setup: 2025-08-30 02:46:41 - pico-train - INFO - └─ Total Parameters: 11,282,784 2025-08-30 02:46:41 - pico-train - INFO - └─ Trainable Parameters: 11,282,784 2025-08-30 02:46:41 - pico-train - INFO - Distributed Setup: 2025-08-30 02:46:41 - pico-train - INFO - └─ Number of Devices: 1 2025-08-30 02:46:41 - pico-train - INFO - └─ Device Type: NVIDIA GeForce RTX 5090 2025-08-30 02:46:41 - pico-train - INFO - └─ Available Memory: 33.68 GB 2025-08-30 02:46:41 - pico-train - INFO - Software Setup: 2025-08-30 02:46:41 - pico-train - INFO - └─ Python Version: 3.10.12 2025-08-30 02:46:41 - pico-train - INFO - └─ PyTorch Version: 2.8.0+cu128 2025-08-30 02:46:41 - pico-train - INFO - └─ CUDA Version: 12.8 2025-08-30 02:46:41 - pico-train - INFO - └─ Operating System: Linux 6.8.0-63-generic 2025-08-30 02:46:41 - pico-train - INFO - Batch Size Configuration: 2025-08-30 02:46:41 - pico-train - INFO - └─ Global Batch Size: 4 2025-08-30 02:46:41 - pico-train - INFO - └─ Per Device Batch Size: 1 2025-08-30 02:46:41 - pico-train - INFO - └─ Gradient Accumulation Steps: 4 2025-08-30 02:46:41 - pico-train - INFO - ================================================== 2025-08-30 02:46:42 - pico-train - INFO - Step 32500 -- 🔄 Training Metrics 2025-08-30 02:46:42 - pico-train - INFO - ├── Loss: 6.3328 2025-08-30 02:46:42 - pico-train - INFO - ├── Learning Rate: 6.48e-06 2025-08-30 02:46:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:46:42 - pico-train - INFO - Step 32500 -- 📈 Saving Learning Dynamics 2025-08-30 02:46:58 - pico-train - INFO - Step 32525 -- 🔄 Training Metrics 2025-08-30 02:46:58 - pico-train - INFO - ├── Loss: 6.1925 2025-08-30 02:46:58 - pico-train - INFO - ├── Learning Rate: 6.44e-06 2025-08-30 02:46:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:47:11 - pico-train - INFO - Step 32550 -- 🔄 Training Metrics 2025-08-30 02:47:11 - pico-train - INFO - ├── Loss: 6.1404 2025-08-30 02:47:11 - pico-train - INFO - ├── Learning Rate: 6.39e-06 2025-08-30 02:47:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:47:23 - pico-train - INFO - Step 32575 -- 🔄 Training Metrics 2025-08-30 02:47:23 - pico-train - INFO - ├── Loss: 6.0377 2025-08-30 02:47:23 - pico-train - INFO - ├── Learning Rate: 6.35e-06 2025-08-30 02:47:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:47:36 - pico-train - INFO - Step 32600 -- 🔄 Training Metrics 2025-08-30 02:47:36 - pico-train - INFO - ├── Loss: 6.1541 2025-08-30 02:47:36 - pico-train - INFO - ├── Learning Rate: 6.31e-06 2025-08-30 02:47:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:47:49 - pico-train - INFO - Step 32625 -- 🔄 Training Metrics 2025-08-30 02:47:49 - pico-train - INFO - ├── Loss: 6.1989 2025-08-30 02:47:49 - pico-train - INFO - ├── Learning Rate: 6.27e-06 2025-08-30 02:47:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:48:01 - pico-train - INFO - Step 32650 -- 🔄 Training Metrics 2025-08-30 02:48:01 - pico-train - INFO - ├── Loss: 6.1580 2025-08-30 02:48:01 - pico-train - INFO - ├── Learning Rate: 6.23e-06 2025-08-30 02:48:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:48:14 - pico-train - INFO - Step 32675 -- 🔄 Training Metrics 2025-08-30 02:48:14 - pico-train - INFO - ├── Loss: 6.1637 2025-08-30 02:48:14 - pico-train - INFO - ├── Learning Rate: 6.19e-06 2025-08-30 02:48:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:48:27 - pico-train - INFO - Step 32700 -- 🔄 Training Metrics 2025-08-30 02:48:27 - pico-train - INFO - ├── Loss: 6.2011 2025-08-30 02:48:27 - pico-train - INFO - ├── Learning Rate: 6.15e-06 2025-08-30 02:48:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:48:44 - pico-train - INFO - Step 32725 -- 🔄 Training Metrics 2025-08-30 02:48:44 - pico-train - INFO - ├── Loss: 6.1889 2025-08-30 02:48:44 - pico-train - INFO - ├── Learning Rate: 6.11e-06 2025-08-30 02:48:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:49:00 - pico-train - INFO - Step 32750 -- 🔄 Training Metrics 2025-08-30 02:49:00 - pico-train - INFO - ├── Loss: 6.1063 2025-08-30 02:49:00 - pico-train - INFO - ├── Learning Rate: 6.07e-06 2025-08-30 02:49:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:49:16 - pico-train - INFO - Step 32775 -- 🔄 Training Metrics 2025-08-30 02:49:16 - pico-train - INFO - ├── Loss: 6.0999 2025-08-30 02:49:16 - pico-train - INFO - ├── Learning Rate: 6.03e-06 2025-08-30 02:49:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:49:33 - pico-train - INFO - Step 32800 -- 🔄 Training Metrics 2025-08-30 02:49:33 - pico-train - INFO - ├── Loss: 6.0746 2025-08-30 02:49:33 - pico-train - INFO - ├── Learning Rate: 5.99e-06 2025-08-30 02:49:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:49:49 - pico-train - INFO - Step 32825 -- 🔄 Training Metrics 2025-08-30 02:49:49 - pico-train - INFO - ├── Loss: 6.0813 2025-08-30 02:49:49 - pico-train - INFO - ├── Learning Rate: 5.95e-06 2025-08-30 02:49:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:50:06 - pico-train - INFO - Step 32850 -- 🔄 Training Metrics 2025-08-30 02:50:06 - pico-train - INFO - ├── Loss: 6.1923 2025-08-30 02:50:06 - pico-train - INFO - ├── Learning Rate: 5.91e-06 2025-08-30 02:50:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:50:22 - pico-train - INFO - Step 32875 -- 🔄 Training Metrics 2025-08-30 02:50:22 - pico-train - INFO - ├── Loss: 6.1305 2025-08-30 02:50:22 - pico-train - INFO - ├── Learning Rate: 5.87e-06 2025-08-30 02:50:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:50:39 - pico-train - INFO - Step 32900 -- 🔄 Training Metrics 2025-08-30 02:50:39 - pico-train - INFO - ├── Loss: 6.1007 2025-08-30 02:50:39 - pico-train - INFO - ├── Learning Rate: 5.83e-06 2025-08-30 02:50:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:50:55 - pico-train - INFO - Step 32925 -- 🔄 Training Metrics 2025-08-30 02:50:55 - pico-train - INFO - ├── Loss: 6.2576 2025-08-30 02:50:55 - pico-train - INFO - ├── Learning Rate: 5.79e-06 2025-08-30 02:50:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:51:12 - pico-train - INFO - Step 32950 -- 🔄 Training Metrics 2025-08-30 02:51:12 - pico-train - INFO - ├── Loss: 6.0948 2025-08-30 02:51:12 - pico-train - INFO - ├── Learning Rate: 5.75e-06 2025-08-30 02:51:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:51:28 - pico-train - INFO - Step 32975 -- 🔄 Training Metrics 2025-08-30 02:51:28 - pico-train - INFO - ├── Loss: 6.2078 2025-08-30 02:51:28 - pico-train - INFO - ├── Learning Rate: 5.71e-06 2025-08-30 02:51:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:51:44 - pico-train - INFO - Step 33000 -- 💾 Saving Checkpoint 2025-08-30 02:54:25 - pico-train - INFO - Step 33000 -- 📊 Evaluation Results 2025-08-30 02:54:25 - pico-train - INFO - └── paloma: 3.740115385495705e+26 2025-08-30 02:54:28 - pico-train - INFO - Step 33000 -- 🔄 Training Metrics 2025-08-30 02:54:28 - pico-train - INFO - ├── Loss: 6.1535 2025-08-30 02:54:28 - pico-train - INFO - ├── Learning Rate: 5.67e-06 2025-08-30 02:54:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:54:28 - pico-train - INFO - Step 33000 -- 📈 Saving Learning Dynamics 2025-08-30 02:54:48 - pico-train - INFO - Step 33025 -- 🔄 Training Metrics 2025-08-30 02:54:48 - pico-train - INFO - ├── Loss: 6.1780 2025-08-30 02:54:48 - pico-train - INFO - ├── Learning Rate: 5.64e-06 2025-08-30 02:54:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:55:00 - pico-train - INFO - Step 33050 -- 🔄 Training Metrics 2025-08-30 02:55:00 - pico-train - INFO - ├── Loss: 6.1420 2025-08-30 02:55:00 - pico-train - INFO - ├── Learning Rate: 5.60e-06 2025-08-30 02:55:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:55:13 - pico-train - INFO - Step 33075 -- 🔄 Training Metrics 2025-08-30 02:55:13 - pico-train - INFO - ├── Loss: 6.1944 2025-08-30 02:55:13 - pico-train - INFO - ├── Learning Rate: 5.56e-06 2025-08-30 02:55:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:55:26 - pico-train - INFO - Step 33100 -- 🔄 Training Metrics 2025-08-30 02:55:26 - pico-train - INFO - ├── Loss: 6.2635 2025-08-30 02:55:26 - pico-train - INFO - ├── Learning Rate: 5.52e-06 2025-08-30 02:55:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:55:38 - pico-train - INFO - Step 33125 -- 🔄 Training Metrics 2025-08-30 02:55:38 - pico-train - INFO - ├── Loss: 6.1137 2025-08-30 02:55:38 - pico-train - INFO - ├── Learning Rate: 5.48e-06 2025-08-30 02:55:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:55:51 - pico-train - INFO - Step 33150 -- 🔄 Training Metrics 2025-08-30 02:55:51 - pico-train - INFO - ├── Loss: 6.2020 2025-08-30 02:55:51 - pico-train - INFO - ├── Learning Rate: 5.44e-06 2025-08-30 02:55:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:56:03 - pico-train - INFO - Step 33175 -- 🔄 Training Metrics 2025-08-30 02:56:03 - pico-train - INFO - ├── Loss: 6.1916 2025-08-30 02:56:03 - pico-train - INFO - ├── Learning Rate: 5.41e-06 2025-08-30 02:56:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:56:16 - pico-train - INFO - Step 33200 -- 🔄 Training Metrics 2025-08-30 02:56:16 - pico-train - INFO - ├── Loss: 6.1736 2025-08-30 02:56:16 - pico-train - INFO - ├── Learning Rate: 5.37e-06 2025-08-30 02:56:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:56:29 - pico-train - INFO - Step 33225 -- 🔄 Training Metrics 2025-08-30 02:56:29 - pico-train - INFO - ├── Loss: 6.1748 2025-08-30 02:56:29 - pico-train - INFO - ├── Learning Rate: 5.33e-06 2025-08-30 02:56:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:56:41 - pico-train - INFO - Step 33250 -- 🔄 Training Metrics 2025-08-30 02:56:41 - pico-train - INFO - ├── Loss: 6.1251 2025-08-30 02:56:41 - pico-train - INFO - ├── Learning Rate: 5.29e-06 2025-08-30 02:56:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:56:54 - pico-train - INFO - Step 33275 -- 🔄 Training Metrics 2025-08-30 02:56:54 - pico-train - INFO - ├── Loss: 6.1933 2025-08-30 02:56:54 - pico-train - INFO - ├── Learning Rate: 5.25e-06 2025-08-30 02:56:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:57:07 - pico-train - INFO - Step 33300 -- 🔄 Training Metrics 2025-08-30 02:57:07 - pico-train - INFO - ├── Loss: 6.1758 2025-08-30 02:57:07 - pico-train - INFO - ├── Learning Rate: 5.22e-06 2025-08-30 02:57:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:57:19 - pico-train - INFO - Step 33325 -- 🔄 Training Metrics 2025-08-30 02:57:19 - pico-train - INFO - ├── Loss: 6.1299 2025-08-30 02:57:19 - pico-train - INFO - ├── Learning Rate: 5.18e-06 2025-08-30 02:57:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:57:32 - pico-train - INFO - Step 33350 -- 🔄 Training Metrics 2025-08-30 02:57:32 - pico-train - INFO - ├── Loss: 6.1500 2025-08-30 02:57:32 - pico-train - INFO - ├── Learning Rate: 5.14e-06 2025-08-30 02:57:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:57:45 - pico-train - INFO - Step 33375 -- 🔄 Training Metrics 2025-08-30 02:57:45 - pico-train - INFO - ├── Loss: 6.1306 2025-08-30 02:57:45 - pico-train - INFO - ├── Learning Rate: 5.10e-06 2025-08-30 02:57:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:57:57 - pico-train - INFO - Step 33400 -- 🔄 Training Metrics 2025-08-30 02:57:57 - pico-train - INFO - ├── Loss: 6.1234 2025-08-30 02:57:57 - pico-train - INFO - ├── Learning Rate: 5.07e-06 2025-08-30 02:57:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:58:10 - pico-train - INFO - Step 33425 -- 🔄 Training Metrics 2025-08-30 02:58:10 - pico-train - INFO - ├── Loss: 6.1160 2025-08-30 02:58:10 - pico-train - INFO - ├── Learning Rate: 5.03e-06 2025-08-30 02:58:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:58:22 - pico-train - INFO - Step 33450 -- 🔄 Training Metrics 2025-08-30 02:58:22 - pico-train - INFO - ├── Loss: 6.2380 2025-08-30 02:58:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 02:58:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:58:35 - pico-train - INFO - Step 33475 -- 🔄 Training Metrics 2025-08-30 02:58:35 - pico-train - INFO - ├── Loss: 6.2252 2025-08-30 02:58:35 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 02:58:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 02:58:47 - pico-train - INFO - Step 33500 -- 💾 Saving Checkpoint 2025-08-30 03:00:50 - pico-train - INFO - Step 33500 -- 📊 Evaluation Results 2025-08-30 03:00:50 - pico-train - INFO - └── paloma: 3.820544484937776e+26 2025-08-30 03:00:53 - pico-train - INFO - Step 33500 -- 🔄 Training Metrics 2025-08-30 03:00:53 - pico-train - INFO - ├── Loss: 6.0954 2025-08-30 03:00:53 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:00:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:00:53 - pico-train - INFO - Step 33500 -- 📈 Saving Learning Dynamics 2025-08-30 03:01:09 - pico-train - INFO - Step 33525 -- 🔄 Training Metrics 2025-08-30 03:01:09 - pico-train - INFO - ├── Loss: 6.1169 2025-08-30 03:01:09 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:01:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:01:21 - pico-train - INFO - Step 33550 -- 🔄 Training Metrics 2025-08-30 03:01:21 - pico-train - INFO - ├── Loss: 6.1243 2025-08-30 03:01:21 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:01:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:01:34 - pico-train - INFO - Step 33575 -- 🔄 Training Metrics 2025-08-30 03:01:34 - pico-train - INFO - ├── Loss: 6.1169 2025-08-30 03:01:34 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:01:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:01:47 - pico-train - INFO - Step 33600 -- 🔄 Training Metrics 2025-08-30 03:01:47 - pico-train - INFO - ├── Loss: 6.2248 2025-08-30 03:01:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:01:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:01:59 - pico-train - INFO - Step 33625 -- 🔄 Training Metrics 2025-08-30 03:01:59 - pico-train - INFO - ├── Loss: 6.1610 2025-08-30 03:01:59 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:01:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:02:12 - pico-train - INFO - Step 33650 -- 🔄 Training Metrics 2025-08-30 03:02:12 - pico-train - INFO - ├── Loss: 6.0577 2025-08-30 03:02:12 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:02:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:02:24 - pico-train - INFO - Step 33675 -- 🔄 Training Metrics 2025-08-30 03:02:24 - pico-train - INFO - ├── Loss: 6.2475 2025-08-30 03:02:24 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:02:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:02:37 - pico-train - INFO - Step 33700 -- 🔄 Training Metrics 2025-08-30 03:02:37 - pico-train - INFO - ├── Loss: 6.2246 2025-08-30 03:02:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:02:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:02:49 - pico-train - INFO - Step 33725 -- 🔄 Training Metrics 2025-08-30 03:02:49 - pico-train - INFO - ├── Loss: 6.1246 2025-08-30 03:02:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:02:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:03:02 - pico-train - INFO - Step 33750 -- 🔄 Training Metrics 2025-08-30 03:03:02 - pico-train - INFO - ├── Loss: 6.0986 2025-08-30 03:03:02 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:03:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:03:14 - pico-train - INFO - Step 33775 -- 🔄 Training Metrics 2025-08-30 03:03:14 - pico-train - INFO - ├── Loss: 6.1151 2025-08-30 03:03:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:03:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:03:27 - pico-train - INFO - Step 33800 -- 🔄 Training Metrics 2025-08-30 03:03:27 - pico-train - INFO - ├── Loss: 6.0620 2025-08-30 03:03:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:03:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:03:40 - pico-train - INFO - Step 33825 -- 🔄 Training Metrics 2025-08-30 03:03:40 - pico-train - INFO - ├── Loss: 6.0791 2025-08-30 03:03:40 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:03:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:03:52 - pico-train - INFO - Step 33850 -- 🔄 Training Metrics 2025-08-30 03:03:52 - pico-train - INFO - ├── Loss: 6.1092 2025-08-30 03:03:52 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:03:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:04:05 - pico-train - INFO - Step 33875 -- 🔄 Training Metrics 2025-08-30 03:04:05 - pico-train - INFO - ├── Loss: 6.2018 2025-08-30 03:04:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:04:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:04:17 - pico-train - INFO - Step 33900 -- 🔄 Training Metrics 2025-08-30 03:04:17 - pico-train - INFO - ├── Loss: 6.0896 2025-08-30 03:04:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:04:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:04:30 - pico-train - INFO - Step 33925 -- 🔄 Training Metrics 2025-08-30 03:04:30 - pico-train - INFO - ├── Loss: 6.1839 2025-08-30 03:04:30 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:04:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:04:43 - pico-train - INFO - Step 33950 -- 🔄 Training Metrics 2025-08-30 03:04:43 - pico-train - INFO - ├── Loss: 6.2086 2025-08-30 03:04:43 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:04:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:04:55 - pico-train - INFO - Step 33975 -- 🔄 Training Metrics 2025-08-30 03:04:55 - pico-train - INFO - ├── Loss: 6.1246 2025-08-30 03:04:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:04:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:05:07 - pico-train - INFO - Step 34000 -- 💾 Saving Checkpoint 2025-08-30 03:07:21 - pico-train - INFO - Step 34000 -- 📊 Evaluation Results 2025-08-30 03:07:21 - pico-train - INFO - └── paloma: 4.142503590895774e+26 2025-08-30 03:07:23 - pico-train - INFO - Step 34000 -- 🔄 Training Metrics 2025-08-30 03:07:23 - pico-train - INFO - ├── Loss: 6.1339 2025-08-30 03:07:23 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:07:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:07:23 - pico-train - INFO - Step 34000 -- 📈 Saving Learning Dynamics 2025-08-30 03:07:38 - pico-train - INFO - Step 34025 -- 🔄 Training Metrics 2025-08-30 03:07:38 - pico-train - INFO - ├── Loss: 6.1100 2025-08-30 03:07:38 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:07:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:07:51 - pico-train - INFO - Step 34050 -- 🔄 Training Metrics 2025-08-30 03:07:51 - pico-train - INFO - ├── Loss: 6.1062 2025-08-30 03:07:51 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:07:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:08:03 - pico-train - INFO - Step 34075 -- 🔄 Training Metrics 2025-08-30 03:08:03 - pico-train - INFO - ├── Loss: 6.1263 2025-08-30 03:08:03 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:08:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:08:16 - pico-train - INFO - Step 34100 -- 🔄 Training Metrics 2025-08-30 03:08:16 - pico-train - INFO - ├── Loss: 6.1318 2025-08-30 03:08:16 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:08:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:08:29 - pico-train - INFO - Step 34125 -- 🔄 Training Metrics 2025-08-30 03:08:29 - pico-train - INFO - ├── Loss: 6.1323 2025-08-30 03:08:29 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:08:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:08:41 - pico-train - INFO - Step 34150 -- 🔄 Training Metrics 2025-08-30 03:08:41 - pico-train - INFO - ├── Loss: 6.1358 2025-08-30 03:08:41 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:08:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:08:54 - pico-train - INFO - Step 34175 -- 🔄 Training Metrics 2025-08-30 03:08:54 - pico-train - INFO - ├── Loss: 6.0957 2025-08-30 03:08:54 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:08:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:09:06 - pico-train - INFO - Step 34200 -- 🔄 Training Metrics 2025-08-30 03:09:06 - pico-train - INFO - ├── Loss: 6.1673 2025-08-30 03:09:06 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:09:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:09:19 - pico-train - INFO - Step 34225 -- 🔄 Training Metrics 2025-08-30 03:09:19 - pico-train - INFO - ├── Loss: 6.1770 2025-08-30 03:09:19 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:09:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:09:32 - pico-train - INFO - Step 34250 -- 🔄 Training Metrics 2025-08-30 03:09:32 - pico-train - INFO - ├── Loss: 6.1482 2025-08-30 03:09:32 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:09:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:09:44 - pico-train - INFO - Step 34275 -- 🔄 Training Metrics 2025-08-30 03:09:44 - pico-train - INFO - ├── Loss: 6.1460 2025-08-30 03:09:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:09:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:09:57 - pico-train - INFO - Step 34300 -- 🔄 Training Metrics 2025-08-30 03:09:57 - pico-train - INFO - ├── Loss: 6.1870 2025-08-30 03:09:57 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:09:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:10:09 - pico-train - INFO - Step 34325 -- 🔄 Training Metrics 2025-08-30 03:10:09 - pico-train - INFO - ├── Loss: 6.1438 2025-08-30 03:10:09 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:10:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:10:22 - pico-train - INFO - Step 34350 -- 🔄 Training Metrics 2025-08-30 03:10:22 - pico-train - INFO - ├── Loss: 6.1337 2025-08-30 03:10:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:10:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:10:34 - pico-train - INFO - Step 34375 -- 🔄 Training Metrics 2025-08-30 03:10:34 - pico-train - INFO - ├── Loss: 6.2022 2025-08-30 03:10:34 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:10:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:10:47 - pico-train - INFO - Step 34400 -- 🔄 Training Metrics 2025-08-30 03:10:47 - pico-train - INFO - ├── Loss: 6.1670 2025-08-30 03:10:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:10:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:11:00 - pico-train - INFO - Step 34425 -- 🔄 Training Metrics 2025-08-30 03:11:00 - pico-train - INFO - ├── Loss: 6.2327 2025-08-30 03:11:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:11:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:11:12 - pico-train - INFO - Step 34450 -- 🔄 Training Metrics 2025-08-30 03:11:12 - pico-train - INFO - ├── Loss: 6.1547 2025-08-30 03:11:12 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:11:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:11:25 - pico-train - INFO - Step 34475 -- 🔄 Training Metrics 2025-08-30 03:11:25 - pico-train - INFO - ├── Loss: 6.2192 2025-08-30 03:11:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:11:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:11:37 - pico-train - INFO - Step 34500 -- 💾 Saving Checkpoint 2025-08-30 03:13:33 - pico-train - INFO - Step 34500 -- 📊 Evaluation Results 2025-08-30 03:13:33 - pico-train - INFO - └── paloma: 4.2151375516962886e+26 2025-08-30 03:13:37 - pico-train - INFO - Step 34500 -- 🔄 Training Metrics 2025-08-30 03:13:37 - pico-train - INFO - ├── Loss: 6.1697 2025-08-30 03:13:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:13:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:13:37 - pico-train - INFO - Step 34500 -- 📈 Saving Learning Dynamics 2025-08-30 03:13:52 - pico-train - INFO - Step 34525 -- 🔄 Training Metrics 2025-08-30 03:13:52 - pico-train - INFO - ├── Loss: 6.2365 2025-08-30 03:13:52 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:13:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:14:05 - pico-train - INFO - Step 34550 -- 🔄 Training Metrics 2025-08-30 03:14:05 - pico-train - INFO - ├── Loss: 6.1503 2025-08-30 03:14:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:14:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:14:17 - pico-train - INFO - Step 34575 -- 🔄 Training Metrics 2025-08-30 03:14:17 - pico-train - INFO - ├── Loss: 6.0855 2025-08-30 03:14:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:14:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:14:30 - pico-train - INFO - Step 34600 -- 🔄 Training Metrics 2025-08-30 03:14:30 - pico-train - INFO - ├── Loss: 6.0957 2025-08-30 03:14:30 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:14:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:14:43 - pico-train - INFO - Step 34625 -- 🔄 Training Metrics 2025-08-30 03:14:43 - pico-train - INFO - ├── Loss: 6.1098 2025-08-30 03:14:43 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:14:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:14:55 - pico-train - INFO - Step 34650 -- 🔄 Training Metrics 2025-08-30 03:14:55 - pico-train - INFO - ├── Loss: 6.2054 2025-08-30 03:14:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:14:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:15:08 - pico-train - INFO - Step 34675 -- 🔄 Training Metrics 2025-08-30 03:15:08 - pico-train - INFO - ├── Loss: 6.2291 2025-08-30 03:15:08 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:15:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:15:20 - pico-train - INFO - Step 34700 -- 🔄 Training Metrics 2025-08-30 03:15:20 - pico-train - INFO - ├── Loss: 6.1366 2025-08-30 03:15:20 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:15:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:15:33 - pico-train - INFO - Step 34725 -- 🔄 Training Metrics 2025-08-30 03:15:33 - pico-train - INFO - ├── Loss: 6.2234 2025-08-30 03:15:33 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:15:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:15:46 - pico-train - INFO - Step 34750 -- 🔄 Training Metrics 2025-08-30 03:15:46 - pico-train - INFO - ├── Loss: 6.2019 2025-08-30 03:15:46 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:15:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:15:58 - pico-train - INFO - Step 34775 -- 🔄 Training Metrics 2025-08-30 03:15:58 - pico-train - INFO - ├── Loss: 6.1355 2025-08-30 03:15:58 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:15:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:16:11 - pico-train - INFO - Step 34800 -- 🔄 Training Metrics 2025-08-30 03:16:11 - pico-train - INFO - ├── Loss: 6.1488 2025-08-30 03:16:11 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:16:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:16:23 - pico-train - INFO - Step 34825 -- 🔄 Training Metrics 2025-08-30 03:16:23 - pico-train - INFO - ├── Loss: 6.2028 2025-08-30 03:16:23 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:16:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:16:36 - pico-train - INFO - Step 34850 -- 🔄 Training Metrics 2025-08-30 03:16:36 - pico-train - INFO - ├── Loss: 6.1645 2025-08-30 03:16:36 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:16:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:16:49 - pico-train - INFO - Step 34875 -- 🔄 Training Metrics 2025-08-30 03:16:49 - pico-train - INFO - ├── Loss: 6.0661 2025-08-30 03:16:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:16:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:17:01 - pico-train - INFO - Step 34900 -- 🔄 Training Metrics 2025-08-30 03:17:01 - pico-train - INFO - ├── Loss: 6.2181 2025-08-30 03:17:01 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:17:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:17:14 - pico-train - INFO - Step 34925 -- 🔄 Training Metrics 2025-08-30 03:17:14 - pico-train - INFO - ├── Loss: 6.1848 2025-08-30 03:17:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:17:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:17:26 - pico-train - INFO - Step 34950 -- 🔄 Training Metrics 2025-08-30 03:17:26 - pico-train - INFO - ├── Loss: 6.1827 2025-08-30 03:17:26 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:17:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:17:39 - pico-train - INFO - Step 34975 -- 🔄 Training Metrics 2025-08-30 03:17:39 - pico-train - INFO - ├── Loss: 6.2027 2025-08-30 03:17:39 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:17:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:17:51 - pico-train - INFO - Step 35000 -- 💾 Saving Checkpoint 2025-08-30 03:19:48 - pico-train - INFO - Step 35000 -- 📊 Evaluation Results 2025-08-30 03:19:48 - pico-train - INFO - └── paloma: 4.304627505909107e+26 2025-08-30 03:19:53 - pico-train - INFO - Step 35000 -- 🔄 Training Metrics 2025-08-30 03:19:53 - pico-train - INFO - ├── Loss: 6.1136 2025-08-30 03:19:53 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:19:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:19:53 - pico-train - INFO - Step 35000 -- 📈 Saving Learning Dynamics 2025-08-30 03:20:08 - pico-train - INFO - Step 35025 -- 🔄 Training Metrics 2025-08-30 03:20:08 - pico-train - INFO - ├── Loss: 6.1389 2025-08-30 03:20:08 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:20:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:20:21 - pico-train - INFO - Step 35050 -- 🔄 Training Metrics 2025-08-30 03:20:21 - pico-train - INFO - ├── Loss: 6.1484 2025-08-30 03:20:21 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:20:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:20:33 - pico-train - INFO - Step 35075 -- 🔄 Training Metrics 2025-08-30 03:20:33 - pico-train - INFO - ├── Loss: 6.1523 2025-08-30 03:20:33 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:20:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:20:46 - pico-train - INFO - Step 35100 -- 🔄 Training Metrics 2025-08-30 03:20:46 - pico-train - INFO - ├── Loss: 6.1193 2025-08-30 03:20:46 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:20:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:20:58 - pico-train - INFO - Step 35125 -- 🔄 Training Metrics 2025-08-30 03:20:58 - pico-train - INFO - ├── Loss: 6.1958 2025-08-30 03:20:58 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:20:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:21:11 - pico-train - INFO - Step 35150 -- 🔄 Training Metrics 2025-08-30 03:21:11 - pico-train - INFO - ├── Loss: 6.1430 2025-08-30 03:21:11 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:21:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:21:24 - pico-train - INFO - Step 35175 -- 🔄 Training Metrics 2025-08-30 03:21:24 - pico-train - INFO - ├── Loss: 6.1746 2025-08-30 03:21:24 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:21:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:21:37 - pico-train - INFO - Step 35200 -- 🔄 Training Metrics 2025-08-30 03:21:37 - pico-train - INFO - ├── Loss: 6.0335 2025-08-30 03:21:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:21:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:21:49 - pico-train - INFO - Step 35225 -- 🔄 Training Metrics 2025-08-30 03:21:49 - pico-train - INFO - ├── Loss: 6.1020 2025-08-30 03:21:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:21:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:22:02 - pico-train - INFO - Step 35250 -- 🔄 Training Metrics 2025-08-30 03:22:02 - pico-train - INFO - ├── Loss: 6.2283 2025-08-30 03:22:02 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:22:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:22:14 - pico-train - INFO - Step 35275 -- 🔄 Training Metrics 2025-08-30 03:22:14 - pico-train - INFO - ├── Loss: 6.1576 2025-08-30 03:22:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:22:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:22:27 - pico-train - INFO - Step 35300 -- 🔄 Training Metrics 2025-08-30 03:22:27 - pico-train - INFO - ├── Loss: 6.1987 2025-08-30 03:22:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:22:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:22:39 - pico-train - INFO - Step 35325 -- 🔄 Training Metrics 2025-08-30 03:22:39 - pico-train - INFO - ├── Loss: 6.1550 2025-08-30 03:22:39 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:22:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:22:52 - pico-train - INFO - Step 35350 -- 🔄 Training Metrics 2025-08-30 03:22:52 - pico-train - INFO - ├── Loss: 6.0981 2025-08-30 03:22:52 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:22:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:23:05 - pico-train - INFO - Step 35375 -- 🔄 Training Metrics 2025-08-30 03:23:05 - pico-train - INFO - ├── Loss: 6.1997 2025-08-30 03:23:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:23:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:23:17 - pico-train - INFO - Step 35400 -- 🔄 Training Metrics 2025-08-30 03:23:17 - pico-train - INFO - ├── Loss: 6.2458 2025-08-30 03:23:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:23:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:23:30 - pico-train - INFO - Step 35425 -- 🔄 Training Metrics 2025-08-30 03:23:30 - pico-train - INFO - ├── Loss: 6.0444 2025-08-30 03:23:30 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:23:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:23:42 - pico-train - INFO - Step 35450 -- 🔄 Training Metrics 2025-08-30 03:23:42 - pico-train - INFO - ├── Loss: 6.1476 2025-08-30 03:23:42 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:23:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:23:55 - pico-train - INFO - Step 35475 -- 🔄 Training Metrics 2025-08-30 03:23:55 - pico-train - INFO - ├── Loss: 6.1142 2025-08-30 03:23:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:23:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:24:07 - pico-train - INFO - Step 35500 -- 💾 Saving Checkpoint 2025-08-30 03:26:04 - pico-train - INFO - Step 35500 -- 📊 Evaluation Results 2025-08-30 03:26:04 - pico-train - INFO - └── paloma: 4.6700700670251875e+26 2025-08-30 03:26:07 - pico-train - INFO - Step 35500 -- 🔄 Training Metrics 2025-08-30 03:26:07 - pico-train - INFO - ├── Loss: 6.3161 2025-08-30 03:26:07 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:26:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:26:07 - pico-train - INFO - Step 35500 -- 📈 Saving Learning Dynamics 2025-08-30 03:26:22 - pico-train - INFO - Step 35525 -- 🔄 Training Metrics 2025-08-30 03:26:22 - pico-train - INFO - ├── Loss: 6.1685 2025-08-30 03:26:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:26:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:26:35 - pico-train - INFO - Step 35550 -- 🔄 Training Metrics 2025-08-30 03:26:35 - pico-train - INFO - ├── Loss: 6.1471 2025-08-30 03:26:35 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:26:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:26:47 - pico-train - INFO - Step 35575 -- 🔄 Training Metrics 2025-08-30 03:26:47 - pico-train - INFO - ├── Loss: 6.1814 2025-08-30 03:26:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:26:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:27:00 - pico-train - INFO - Step 35600 -- 🔄 Training Metrics 2025-08-30 03:27:00 - pico-train - INFO - ├── Loss: 6.1457 2025-08-30 03:27:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:27:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:27:12 - pico-train - INFO - Step 35625 -- 🔄 Training Metrics 2025-08-30 03:27:12 - pico-train - INFO - ├── Loss: 6.2045 2025-08-30 03:27:12 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:27:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:27:25 - pico-train - INFO - Step 35650 -- 🔄 Training Metrics 2025-08-30 03:27:25 - pico-train - INFO - ├── Loss: 6.1062 2025-08-30 03:27:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:27:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:27:37 - pico-train - INFO - Step 35675 -- 🔄 Training Metrics 2025-08-30 03:27:37 - pico-train - INFO - ├── Loss: 6.1095 2025-08-30 03:27:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:27:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:27:50 - pico-train - INFO - Step 35700 -- 🔄 Training Metrics 2025-08-30 03:27:50 - pico-train - INFO - ├── Loss: 6.1678 2025-08-30 03:27:50 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:27:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:28:03 - pico-train - INFO - Step 35725 -- 🔄 Training Metrics 2025-08-30 03:28:03 - pico-train - INFO - ├── Loss: 6.1324 2025-08-30 03:28:03 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:28:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:28:16 - pico-train - INFO - Step 35750 -- 🔄 Training Metrics 2025-08-30 03:28:16 - pico-train - INFO - ├── Loss: 6.1809 2025-08-30 03:28:16 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:28:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:28:29 - pico-train - INFO - Step 35775 -- 🔄 Training Metrics 2025-08-30 03:28:29 - pico-train - INFO - ├── Loss: 6.1851 2025-08-30 03:28:29 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:28:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:28:41 - pico-train - INFO - Step 35800 -- 🔄 Training Metrics 2025-08-30 03:28:41 - pico-train - INFO - ├── Loss: 6.2119 2025-08-30 03:28:41 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:28:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:28:54 - pico-train - INFO - Step 35825 -- 🔄 Training Metrics 2025-08-30 03:28:54 - pico-train - INFO - ├── Loss: 6.2010 2025-08-30 03:28:54 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:28:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:29:07 - pico-train - INFO - Step 35850 -- 🔄 Training Metrics 2025-08-30 03:29:07 - pico-train - INFO - ├── Loss: 6.1562 2025-08-30 03:29:07 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:29:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:29:19 - pico-train - INFO - Step 35875 -- 🔄 Training Metrics 2025-08-30 03:29:19 - pico-train - INFO - ├── Loss: 6.1291 2025-08-30 03:29:19 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:29:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:29:32 - pico-train - INFO - Step 35900 -- 🔄 Training Metrics 2025-08-30 03:29:32 - pico-train - INFO - ├── Loss: 6.1521 2025-08-30 03:29:32 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:29:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:29:44 - pico-train - INFO - Step 35925 -- 🔄 Training Metrics 2025-08-30 03:29:44 - pico-train - INFO - ├── Loss: 6.2151 2025-08-30 03:29:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:29:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:29:57 - pico-train - INFO - Step 35950 -- 🔄 Training Metrics 2025-08-30 03:29:57 - pico-train - INFO - ├── Loss: 6.2125 2025-08-30 03:29:57 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:29:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:30:09 - pico-train - INFO - Step 35975 -- 🔄 Training Metrics 2025-08-30 03:30:09 - pico-train - INFO - ├── Loss: 6.0902 2025-08-30 03:30:09 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:30:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:30:21 - pico-train - INFO - Step 36000 -- 💾 Saving Checkpoint 2025-08-30 03:32:16 - pico-train - INFO - Step 36000 -- 📊 Evaluation Results 2025-08-30 03:32:16 - pico-train - INFO - └── paloma: 4.715374868651716e+26 2025-08-30 03:32:17 - pico-train - INFO - Step 36000 -- 🔄 Training Metrics 2025-08-30 03:32:17 - pico-train - INFO - ├── Loss: 6.2189 2025-08-30 03:32:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:32:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:32:17 - pico-train - INFO - Step 36000 -- 📈 Saving Learning Dynamics 2025-08-30 03:32:33 - pico-train - INFO - Step 36025 -- 🔄 Training Metrics 2025-08-30 03:32:33 - pico-train - INFO - ├── Loss: 6.1215 2025-08-30 03:32:33 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:32:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:32:45 - pico-train - INFO - Step 36050 -- 🔄 Training Metrics 2025-08-30 03:32:45 - pico-train - INFO - ├── Loss: 6.1553 2025-08-30 03:32:45 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:32:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:32:58 - pico-train - INFO - Step 36075 -- 🔄 Training Metrics 2025-08-30 03:32:58 - pico-train - INFO - ├── Loss: 6.0888 2025-08-30 03:32:58 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:32:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:33:10 - pico-train - INFO - Step 36100 -- 🔄 Training Metrics 2025-08-30 03:33:10 - pico-train - INFO - ├── Loss: 6.0934 2025-08-30 03:33:10 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:33:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:33:23 - pico-train - INFO - Step 36125 -- 🔄 Training Metrics 2025-08-30 03:33:23 - pico-train - INFO - ├── Loss: 6.2055 2025-08-30 03:33:23 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:33:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:33:36 - pico-train - INFO - Step 36150 -- 🔄 Training Metrics 2025-08-30 03:33:36 - pico-train - INFO - ├── Loss: 6.1254 2025-08-30 03:33:36 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:33:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:33:48 - pico-train - INFO - Step 36175 -- 🔄 Training Metrics 2025-08-30 03:33:48 - pico-train - INFO - ├── Loss: 6.1199 2025-08-30 03:33:48 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:33:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:34:01 - pico-train - INFO - Step 36200 -- 🔄 Training Metrics 2025-08-30 03:34:01 - pico-train - INFO - ├── Loss: 6.1706 2025-08-30 03:34:01 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:34:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:34:14 - pico-train - INFO - Step 36225 -- 🔄 Training Metrics 2025-08-30 03:34:14 - pico-train - INFO - ├── Loss: 6.1231 2025-08-30 03:34:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:34:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:34:26 - pico-train - INFO - Step 36250 -- 🔄 Training Metrics 2025-08-30 03:34:26 - pico-train - INFO - ├── Loss: 6.1492 2025-08-30 03:34:26 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:34:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:34:39 - pico-train - INFO - Step 36275 -- 🔄 Training Metrics 2025-08-30 03:34:39 - pico-train - INFO - ├── Loss: 6.1860 2025-08-30 03:34:39 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:34:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:34:51 - pico-train - INFO - Step 36300 -- 🔄 Training Metrics 2025-08-30 03:34:51 - pico-train - INFO - ├── Loss: 6.1325 2025-08-30 03:34:51 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:34:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:35:04 - pico-train - INFO - Step 36325 -- 🔄 Training Metrics 2025-08-30 03:35:04 - pico-train - INFO - ├── Loss: 6.1265 2025-08-30 03:35:04 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:35:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:35:17 - pico-train - INFO - Step 36350 -- 🔄 Training Metrics 2025-08-30 03:35:17 - pico-train - INFO - ├── Loss: 6.1401 2025-08-30 03:35:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:35:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:35:29 - pico-train - INFO - Step 36375 -- 🔄 Training Metrics 2025-08-30 03:35:29 - pico-train - INFO - ├── Loss: 6.2003 2025-08-30 03:35:29 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:35:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:35:42 - pico-train - INFO - Step 36400 -- 🔄 Training Metrics 2025-08-30 03:35:42 - pico-train - INFO - ├── Loss: 6.2138 2025-08-30 03:35:42 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:35:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:35:54 - pico-train - INFO - Step 36425 -- 🔄 Training Metrics 2025-08-30 03:35:54 - pico-train - INFO - ├── Loss: 6.1670 2025-08-30 03:35:54 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:35:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:36:07 - pico-train - INFO - Step 36450 -- 🔄 Training Metrics 2025-08-30 03:36:07 - pico-train - INFO - ├── Loss: 6.1172 2025-08-30 03:36:07 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:36:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:36:20 - pico-train - INFO - Step 36475 -- 🔄 Training Metrics 2025-08-30 03:36:20 - pico-train - INFO - ├── Loss: 6.1339 2025-08-30 03:36:20 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:36:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:36:32 - pico-train - INFO - Step 36500 -- 💾 Saving Checkpoint 2025-08-30 03:38:26 - pico-train - INFO - Step 36500 -- 📊 Evaluation Results 2025-08-30 03:38:26 - pico-train - INFO - └── paloma: 5.3158347592675254e+26 2025-08-30 03:38:28 - pico-train - INFO - Step 36500 -- 🔄 Training Metrics 2025-08-30 03:38:28 - pico-train - INFO - ├── Loss: 6.0491 2025-08-30 03:38:28 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:38:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:38:28 - pico-train - INFO - Step 36500 -- 📈 Saving Learning Dynamics 2025-08-30 03:38:43 - pico-train - INFO - Step 36525 -- 🔄 Training Metrics 2025-08-30 03:38:43 - pico-train - INFO - ├── Loss: 6.1327 2025-08-30 03:38:43 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:38:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:38:55 - pico-train - INFO - Step 36550 -- 🔄 Training Metrics 2025-08-30 03:38:55 - pico-train - INFO - ├── Loss: 6.1302 2025-08-30 03:38:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:38:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:39:08 - pico-train - INFO - Step 36575 -- 🔄 Training Metrics 2025-08-30 03:39:08 - pico-train - INFO - ├── Loss: 6.0575 2025-08-30 03:39:08 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:39:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:39:20 - pico-train - INFO - Step 36600 -- 🔄 Training Metrics 2025-08-30 03:39:20 - pico-train - INFO - ├── Loss: 6.2042 2025-08-30 03:39:20 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:39:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:39:33 - pico-train - INFO - Step 36625 -- 🔄 Training Metrics 2025-08-30 03:39:33 - pico-train - INFO - ├── Loss: 6.1372 2025-08-30 03:39:33 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:39:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:39:46 - pico-train - INFO - Step 36650 -- 🔄 Training Metrics 2025-08-30 03:39:46 - pico-train - INFO - ├── Loss: 6.1700 2025-08-30 03:39:46 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:39:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:39:58 - pico-train - INFO - Step 36675 -- 🔄 Training Metrics 2025-08-30 03:39:58 - pico-train - INFO - ├── Loss: 6.1158 2025-08-30 03:39:58 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:39:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:40:11 - pico-train - INFO - Step 36700 -- 🔄 Training Metrics 2025-08-30 03:40:11 - pico-train - INFO - ├── Loss: 6.0870 2025-08-30 03:40:11 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:40:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:40:23 - pico-train - INFO - Step 36725 -- 🔄 Training Metrics 2025-08-30 03:40:23 - pico-train - INFO - ├── Loss: 6.1286 2025-08-30 03:40:23 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:40:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:40:36 - pico-train - INFO - Step 36750 -- 🔄 Training Metrics 2025-08-30 03:40:36 - pico-train - INFO - ├── Loss: 6.1306 2025-08-30 03:40:36 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:40:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:40:49 - pico-train - INFO - Step 36775 -- 🔄 Training Metrics 2025-08-30 03:40:49 - pico-train - INFO - ├── Loss: 6.1677 2025-08-30 03:40:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:40:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:41:01 - pico-train - INFO - Step 36800 -- 🔄 Training Metrics 2025-08-30 03:41:01 - pico-train - INFO - ├── Loss: 6.1384 2025-08-30 03:41:01 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:41:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:41:14 - pico-train - INFO - Step 36825 -- 🔄 Training Metrics 2025-08-30 03:41:14 - pico-train - INFO - ├── Loss: 6.1046 2025-08-30 03:41:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:41:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:41:27 - pico-train - INFO - Step 36850 -- 🔄 Training Metrics 2025-08-30 03:41:27 - pico-train - INFO - ├── Loss: 6.1113 2025-08-30 03:41:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:41:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:41:39 - pico-train - INFO - Step 36875 -- 🔄 Training Metrics 2025-08-30 03:41:39 - pico-train - INFO - ├── Loss: 6.0820 2025-08-30 03:41:39 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:41:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:41:52 - pico-train - INFO - Step 36900 -- 🔄 Training Metrics 2025-08-30 03:41:52 - pico-train - INFO - ├── Loss: 6.1183 2025-08-30 03:41:52 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:41:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:42:04 - pico-train - INFO - Step 36925 -- 🔄 Training Metrics 2025-08-30 03:42:04 - pico-train - INFO - ├── Loss: 6.2381 2025-08-30 03:42:04 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:42:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:42:17 - pico-train - INFO - Step 36950 -- 🔄 Training Metrics 2025-08-30 03:42:17 - pico-train - INFO - ├── Loss: 6.1110 2025-08-30 03:42:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:42:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:42:29 - pico-train - INFO - Step 36975 -- 🔄 Training Metrics 2025-08-30 03:42:29 - pico-train - INFO - ├── Loss: 6.1691 2025-08-30 03:42:29 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:42:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:42:41 - pico-train - INFO - Step 37000 -- 💾 Saving Checkpoint 2025-08-30 03:44:57 - pico-train - INFO - Step 37000 -- 📊 Evaluation Results 2025-08-30 03:44:57 - pico-train - INFO - └── paloma: 5.5391129624917924e+26 2025-08-30 03:44:59 - pico-train - INFO - Step 37000 -- 🔄 Training Metrics 2025-08-30 03:44:59 - pico-train - INFO - ├── Loss: 6.1885 2025-08-30 03:44:59 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:44:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:44:59 - pico-train - INFO - Step 37000 -- 📈 Saving Learning Dynamics 2025-08-30 03:45:14 - pico-train - INFO - Step 37025 -- 🔄 Training Metrics 2025-08-30 03:45:14 - pico-train - INFO - ├── Loss: 6.1579 2025-08-30 03:45:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:45:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:45:27 - pico-train - INFO - Step 37050 -- 🔄 Training Metrics 2025-08-30 03:45:27 - pico-train - INFO - ├── Loss: 6.1313 2025-08-30 03:45:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:45:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:45:39 - pico-train - INFO - Step 37075 -- 🔄 Training Metrics 2025-08-30 03:45:39 - pico-train - INFO - ├── Loss: 6.0942 2025-08-30 03:45:39 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:45:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:45:52 - pico-train - INFO - Step 37100 -- 🔄 Training Metrics 2025-08-30 03:45:52 - pico-train - INFO - ├── Loss: 6.1327 2025-08-30 03:45:52 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:45:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:46:05 - pico-train - INFO - Step 37125 -- 🔄 Training Metrics 2025-08-30 03:46:05 - pico-train - INFO - ├── Loss: 6.1410 2025-08-30 03:46:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:46:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:46:17 - pico-train - INFO - Step 37150 -- 🔄 Training Metrics 2025-08-30 03:46:17 - pico-train - INFO - ├── Loss: 6.0944 2025-08-30 03:46:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:46:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:46:30 - pico-train - INFO - Step 37175 -- 🔄 Training Metrics 2025-08-30 03:46:30 - pico-train - INFO - ├── Loss: 6.0974 2025-08-30 03:46:30 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:46:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:46:42 - pico-train - INFO - Step 37200 -- 🔄 Training Metrics 2025-08-30 03:46:42 - pico-train - INFO - ├── Loss: 6.1735 2025-08-30 03:46:42 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:46:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:46:55 - pico-train - INFO - Step 37225 -- 🔄 Training Metrics 2025-08-30 03:46:55 - pico-train - INFO - ├── Loss: 6.1205 2025-08-30 03:46:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:46:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:47:08 - pico-train - INFO - Step 37250 -- 🔄 Training Metrics 2025-08-30 03:47:08 - pico-train - INFO - ├── Loss: 6.1602 2025-08-30 03:47:08 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:47:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:47:21 - pico-train - INFO - Step 37275 -- 🔄 Training Metrics 2025-08-30 03:47:21 - pico-train - INFO - ├── Loss: 6.1855 2025-08-30 03:47:21 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:47:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:47:33 - pico-train - INFO - Step 37300 -- 🔄 Training Metrics 2025-08-30 03:47:33 - pico-train - INFO - ├── Loss: 6.1308 2025-08-30 03:47:33 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:47:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:47:46 - pico-train - INFO - Step 37325 -- 🔄 Training Metrics 2025-08-30 03:47:46 - pico-train - INFO - ├── Loss: 6.1135 2025-08-30 03:47:46 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:47:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:47:58 - pico-train - INFO - Step 37350 -- 🔄 Training Metrics 2025-08-30 03:47:58 - pico-train - INFO - ├── Loss: 6.0931 2025-08-30 03:47:58 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:47:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:48:11 - pico-train - INFO - Step 37375 -- 🔄 Training Metrics 2025-08-30 03:48:11 - pico-train - INFO - ├── Loss: 6.1745 2025-08-30 03:48:11 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:48:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:48:23 - pico-train - INFO - Step 37400 -- 🔄 Training Metrics 2025-08-30 03:48:23 - pico-train - INFO - ├── Loss: 6.1609 2025-08-30 03:48:23 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:48:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:48:36 - pico-train - INFO - Step 37425 -- 🔄 Training Metrics 2025-08-30 03:48:36 - pico-train - INFO - ├── Loss: 6.1909 2025-08-30 03:48:36 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:48:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:48:48 - pico-train - INFO - Step 37450 -- 🔄 Training Metrics 2025-08-30 03:48:48 - pico-train - INFO - ├── Loss: 6.1441 2025-08-30 03:48:48 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:48:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:49:01 - pico-train - INFO - Step 37475 -- 🔄 Training Metrics 2025-08-30 03:49:01 - pico-train - INFO - ├── Loss: 6.1467 2025-08-30 03:49:01 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:49:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:49:13 - pico-train - INFO - Step 37500 -- 💾 Saving Checkpoint 2025-08-30 03:51:13 - pico-train - INFO - Step 37500 -- 📊 Evaluation Results 2025-08-30 03:51:13 - pico-train - INFO - └── paloma: 5.823151093085719e+26 2025-08-30 03:51:15 - pico-train - INFO - Step 37500 -- 🔄 Training Metrics 2025-08-30 03:51:15 - pico-train - INFO - ├── Loss: 6.1800 2025-08-30 03:51:15 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:51:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:51:15 - pico-train - INFO - Step 37500 -- 📈 Saving Learning Dynamics 2025-08-30 03:51:30 - pico-train - INFO - Step 37525 -- 🔄 Training Metrics 2025-08-30 03:51:30 - pico-train - INFO - ├── Loss: 6.1196 2025-08-30 03:51:30 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:51:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:51:43 - pico-train - INFO - Step 37550 -- 🔄 Training Metrics 2025-08-30 03:51:43 - pico-train - INFO - ├── Loss: 6.1254 2025-08-30 03:51:43 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:51:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:51:56 - pico-train - INFO - Step 37575 -- 🔄 Training Metrics 2025-08-30 03:51:56 - pico-train - INFO - ├── Loss: 6.1453 2025-08-30 03:51:56 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:51:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:52:08 - pico-train - INFO - Step 37600 -- 🔄 Training Metrics 2025-08-30 03:52:08 - pico-train - INFO - ├── Loss: 6.1073 2025-08-30 03:52:08 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:52:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:52:21 - pico-train - INFO - Step 37625 -- 🔄 Training Metrics 2025-08-30 03:52:21 - pico-train - INFO - ├── Loss: 6.1739 2025-08-30 03:52:21 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:52:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:52:34 - pico-train - INFO - Step 37650 -- 🔄 Training Metrics 2025-08-30 03:52:34 - pico-train - INFO - ├── Loss: 6.1204 2025-08-30 03:52:34 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:52:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:52:46 - pico-train - INFO - Step 37675 -- 🔄 Training Metrics 2025-08-30 03:52:46 - pico-train - INFO - ├── Loss: 6.2738 2025-08-30 03:52:46 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:52:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:52:59 - pico-train - INFO - Step 37700 -- 🔄 Training Metrics 2025-08-30 03:52:59 - pico-train - INFO - ├── Loss: 6.1134 2025-08-30 03:52:59 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:52:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:53:11 - pico-train - INFO - Step 37725 -- 🔄 Training Metrics 2025-08-30 03:53:11 - pico-train - INFO - ├── Loss: 6.1197 2025-08-30 03:53:11 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:53:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:53:24 - pico-train - INFO - Step 37750 -- 🔄 Training Metrics 2025-08-30 03:53:24 - pico-train - INFO - ├── Loss: 6.1062 2025-08-30 03:53:24 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:53:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:53:37 - pico-train - INFO - Step 37775 -- 🔄 Training Metrics 2025-08-30 03:53:37 - pico-train - INFO - ├── Loss: 6.2604 2025-08-30 03:53:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:53:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:53:50 - pico-train - INFO - Step 37800 -- 🔄 Training Metrics 2025-08-30 03:53:50 - pico-train - INFO - ├── Loss: 6.1548 2025-08-30 03:53:50 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:53:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:54:02 - pico-train - INFO - Step 37825 -- 🔄 Training Metrics 2025-08-30 03:54:02 - pico-train - INFO - ├── Loss: 6.0781 2025-08-30 03:54:02 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:54:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:54:15 - pico-train - INFO - Step 37850 -- 🔄 Training Metrics 2025-08-30 03:54:15 - pico-train - INFO - ├── Loss: 6.1886 2025-08-30 03:54:15 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:54:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:54:28 - pico-train - INFO - Step 37875 -- 🔄 Training Metrics 2025-08-30 03:54:28 - pico-train - INFO - ├── Loss: 6.1364 2025-08-30 03:54:28 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:54:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:54:40 - pico-train - INFO - Step 37900 -- 🔄 Training Metrics 2025-08-30 03:54:40 - pico-train - INFO - ├── Loss: 6.1419 2025-08-30 03:54:40 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:54:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:54:53 - pico-train - INFO - Step 37925 -- 🔄 Training Metrics 2025-08-30 03:54:53 - pico-train - INFO - ├── Loss: 6.0992 2025-08-30 03:54:53 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:54:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:55:05 - pico-train - INFO - Step 37950 -- 🔄 Training Metrics 2025-08-30 03:55:05 - pico-train - INFO - ├── Loss: 6.0952 2025-08-30 03:55:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:55:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:55:18 - pico-train - INFO - Step 37975 -- 🔄 Training Metrics 2025-08-30 03:55:18 - pico-train - INFO - ├── Loss: 6.0819 2025-08-30 03:55:18 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:55:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:55:30 - pico-train - INFO - Step 38000 -- 💾 Saving Checkpoint 2025-08-30 03:57:23 - pico-train - INFO - Step 38000 -- 📊 Evaluation Results 2025-08-30 03:57:23 - pico-train - INFO - └── paloma: 6.202568645395263e+26 2025-08-30 03:57:25 - pico-train - INFO - Step 38000 -- 🔄 Training Metrics 2025-08-30 03:57:25 - pico-train - INFO - ├── Loss: 6.1806 2025-08-30 03:57:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:57:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:57:25 - pico-train - INFO - Step 38000 -- 📈 Saving Learning Dynamics 2025-08-30 03:57:40 - pico-train - INFO - Step 38025 -- 🔄 Training Metrics 2025-08-30 03:57:40 - pico-train - INFO - ├── Loss: 6.1459 2025-08-30 03:57:40 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:57:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:57:52 - pico-train - INFO - Step 38050 -- 🔄 Training Metrics 2025-08-30 03:57:52 - pico-train - INFO - ├── Loss: 6.1239 2025-08-30 03:57:52 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:57:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:58:05 - pico-train - INFO - Step 38075 -- 🔄 Training Metrics 2025-08-30 03:58:05 - pico-train - INFO - ├── Loss: 6.1724 2025-08-30 03:58:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:58:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:58:17 - pico-train - INFO - Step 38100 -- 🔄 Training Metrics 2025-08-30 03:58:17 - pico-train - INFO - ├── Loss: 6.0446 2025-08-30 03:58:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:58:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:58:30 - pico-train - INFO - Step 38125 -- 🔄 Training Metrics 2025-08-30 03:58:30 - pico-train - INFO - ├── Loss: 6.2129 2025-08-30 03:58:30 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:58:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:58:43 - pico-train - INFO - Step 38150 -- 🔄 Training Metrics 2025-08-30 03:58:43 - pico-train - INFO - ├── Loss: 6.1901 2025-08-30 03:58:43 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:58:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:58:56 - pico-train - INFO - Step 38175 -- 🔄 Training Metrics 2025-08-30 03:58:56 - pico-train - INFO - ├── Loss: 6.1603 2025-08-30 03:58:56 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:58:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:59:08 - pico-train - INFO - Step 38200 -- 🔄 Training Metrics 2025-08-30 03:59:08 - pico-train - INFO - ├── Loss: 6.1623 2025-08-30 03:59:08 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:59:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:59:21 - pico-train - INFO - Step 38225 -- 🔄 Training Metrics 2025-08-30 03:59:21 - pico-train - INFO - ├── Loss: 6.1621 2025-08-30 03:59:21 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:59:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:59:33 - pico-train - INFO - Step 38250 -- 🔄 Training Metrics 2025-08-30 03:59:33 - pico-train - INFO - ├── Loss: 6.1762 2025-08-30 03:59:33 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:59:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:59:46 - pico-train - INFO - Step 38275 -- 🔄 Training Metrics 2025-08-30 03:59:46 - pico-train - INFO - ├── Loss: 6.1080 2025-08-30 03:59:46 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:59:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 03:59:59 - pico-train - INFO - Step 38300 -- 🔄 Training Metrics 2025-08-30 03:59:59 - pico-train - INFO - ├── Loss: 6.1721 2025-08-30 03:59:59 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 03:59:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:00:11 - pico-train - INFO - Step 38325 -- 🔄 Training Metrics 2025-08-30 04:00:11 - pico-train - INFO - ├── Loss: 6.1486 2025-08-30 04:00:11 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:00:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:00:24 - pico-train - INFO - Step 38350 -- 🔄 Training Metrics 2025-08-30 04:00:24 - pico-train - INFO - ├── Loss: 6.1230 2025-08-30 04:00:24 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:00:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:00:36 - pico-train - INFO - Step 38375 -- 🔄 Training Metrics 2025-08-30 04:00:36 - pico-train - INFO - ├── Loss: 6.1384 2025-08-30 04:00:36 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:00:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:00:49 - pico-train - INFO - Step 38400 -- 🔄 Training Metrics 2025-08-30 04:00:49 - pico-train - INFO - ├── Loss: 6.1810 2025-08-30 04:00:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:00:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:01:02 - pico-train - INFO - Step 38425 -- 🔄 Training Metrics 2025-08-30 04:01:02 - pico-train - INFO - ├── Loss: 6.1218 2025-08-30 04:01:02 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:01:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:01:14 - pico-train - INFO - Step 38450 -- 🔄 Training Metrics 2025-08-30 04:01:14 - pico-train - INFO - ├── Loss: 6.0706 2025-08-30 04:01:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:01:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:01:27 - pico-train - INFO - Step 38475 -- 🔄 Training Metrics 2025-08-30 04:01:27 - pico-train - INFO - ├── Loss: 6.1022 2025-08-30 04:01:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:01:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:01:39 - pico-train - INFO - Step 38500 -- 💾 Saving Checkpoint 2025-08-30 04:03:36 - pico-train - INFO - Step 38500 -- 📊 Evaluation Results 2025-08-30 04:03:36 - pico-train - INFO - └── paloma: 6.267698412543812e+26 2025-08-30 04:03:37 - pico-train - INFO - Step 38500 -- 🔄 Training Metrics 2025-08-30 04:03:37 - pico-train - INFO - ├── Loss: 6.2061 2025-08-30 04:03:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:03:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:03:37 - pico-train - INFO - Step 38500 -- 📈 Saving Learning Dynamics 2025-08-30 04:03:52 - pico-train - INFO - Step 38525 -- 🔄 Training Metrics 2025-08-30 04:03:52 - pico-train - INFO - ├── Loss: 6.1100 2025-08-30 04:03:52 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:03:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:04:05 - pico-train - INFO - Step 38550 -- 🔄 Training Metrics 2025-08-30 04:04:05 - pico-train - INFO - ├── Loss: 6.0985 2025-08-30 04:04:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:04:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:04:17 - pico-train - INFO - Step 38575 -- 🔄 Training Metrics 2025-08-30 04:04:17 - pico-train - INFO - ├── Loss: 6.1607 2025-08-30 04:04:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:04:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:04:30 - pico-train - INFO - Step 38600 -- 🔄 Training Metrics 2025-08-30 04:04:30 - pico-train - INFO - ├── Loss: 6.1034 2025-08-30 04:04:30 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:04:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:04:43 - pico-train - INFO - Step 38625 -- 🔄 Training Metrics 2025-08-30 04:04:43 - pico-train - INFO - ├── Loss: 6.1405 2025-08-30 04:04:43 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:04:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:04:56 - pico-train - INFO - Step 38650 -- 🔄 Training Metrics 2025-08-30 04:04:56 - pico-train - INFO - ├── Loss: 6.1453 2025-08-30 04:04:56 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:04:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:05:08 - pico-train - INFO - Step 38675 -- 🔄 Training Metrics 2025-08-30 04:05:08 - pico-train - INFO - ├── Loss: 6.0796 2025-08-30 04:05:08 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:05:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:05:21 - pico-train - INFO - Step 38700 -- 🔄 Training Metrics 2025-08-30 04:05:21 - pico-train - INFO - ├── Loss: 6.0443 2025-08-30 04:05:21 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:05:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:05:34 - pico-train - INFO - Step 38725 -- 🔄 Training Metrics 2025-08-30 04:05:34 - pico-train - INFO - ├── Loss: 6.2451 2025-08-30 04:05:34 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:05:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:05:46 - pico-train - INFO - Step 38750 -- 🔄 Training Metrics 2025-08-30 04:05:46 - pico-train - INFO - ├── Loss: 6.0574 2025-08-30 04:05:46 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:05:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:05:59 - pico-train - INFO - Step 38775 -- 🔄 Training Metrics 2025-08-30 04:05:59 - pico-train - INFO - ├── Loss: 6.1047 2025-08-30 04:05:59 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:05:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:06:12 - pico-train - INFO - Step 38800 -- 🔄 Training Metrics 2025-08-30 04:06:12 - pico-train - INFO - ├── Loss: 6.1653 2025-08-30 04:06:12 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:06:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:06:24 - pico-train - INFO - Step 38825 -- 🔄 Training Metrics 2025-08-30 04:06:24 - pico-train - INFO - ├── Loss: 6.1954 2025-08-30 04:06:24 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:06:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:06:37 - pico-train - INFO - Step 38850 -- 🔄 Training Metrics 2025-08-30 04:06:37 - pico-train - INFO - ├── Loss: 6.1769 2025-08-30 04:06:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:06:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:06:49 - pico-train - INFO - Step 38875 -- 🔄 Training Metrics 2025-08-30 04:06:49 - pico-train - INFO - ├── Loss: 6.1837 2025-08-30 04:06:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:06:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:07:02 - pico-train - INFO - Step 38900 -- 🔄 Training Metrics 2025-08-30 04:07:02 - pico-train - INFO - ├── Loss: 6.1182 2025-08-30 04:07:02 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:07:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:07:15 - pico-train - INFO - Step 38925 -- 🔄 Training Metrics 2025-08-30 04:07:15 - pico-train - INFO - ├── Loss: 6.1174 2025-08-30 04:07:15 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:07:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:07:27 - pico-train - INFO - Step 38950 -- 🔄 Training Metrics 2025-08-30 04:07:27 - pico-train - INFO - ├── Loss: 6.2171 2025-08-30 04:07:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:07:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:07:42 - pico-train - INFO - Step 38975 -- 🔄 Training Metrics 2025-08-30 04:07:42 - pico-train - INFO - ├── Loss: 6.0979 2025-08-30 04:07:42 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:07:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:07:57 - pico-train - INFO - Step 39000 -- 💾 Saving Checkpoint 2025-08-30 04:10:27 - pico-train - INFO - Step 39000 -- 📊 Evaluation Results 2025-08-30 04:10:27 - pico-train - INFO - └── paloma: 6.448910718445894e+26 2025-08-30 04:10:29 - pico-train - INFO - Step 39000 -- 🔄 Training Metrics 2025-08-30 04:10:29 - pico-train - INFO - ├── Loss: 6.1187 2025-08-30 04:10:29 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:10:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:10:29 - pico-train - INFO - Step 39000 -- 📈 Saving Learning Dynamics 2025-08-30 04:10:48 - pico-train - INFO - Step 39025 -- 🔄 Training Metrics 2025-08-30 04:10:48 - pico-train - INFO - ├── Loss: 6.0963 2025-08-30 04:10:48 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:10:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:11:04 - pico-train - INFO - Step 39050 -- 🔄 Training Metrics 2025-08-30 04:11:04 - pico-train - INFO - ├── Loss: 6.0935 2025-08-30 04:11:04 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:11:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:11:21 - pico-train - INFO - Step 39075 -- 🔄 Training Metrics 2025-08-30 04:11:21 - pico-train - INFO - ├── Loss: 6.0688 2025-08-30 04:11:21 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:11:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:11:37 - pico-train - INFO - Step 39100 -- 🔄 Training Metrics 2025-08-30 04:11:37 - pico-train - INFO - ├── Loss: 6.1405 2025-08-30 04:11:37 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:11:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:11:54 - pico-train - INFO - Step 39125 -- 🔄 Training Metrics 2025-08-30 04:11:54 - pico-train - INFO - ├── Loss: 6.1718 2025-08-30 04:11:54 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:11:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:12:10 - pico-train - INFO - Step 39150 -- 🔄 Training Metrics 2025-08-30 04:12:10 - pico-train - INFO - ├── Loss: 6.1167 2025-08-30 04:12:10 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:12:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:12:27 - pico-train - INFO - Step 39175 -- 🔄 Training Metrics 2025-08-30 04:12:27 - pico-train - INFO - ├── Loss: 6.1777 2025-08-30 04:12:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:12:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:12:43 - pico-train - INFO - Step 39200 -- 🔄 Training Metrics 2025-08-30 04:12:43 - pico-train - INFO - ├── Loss: 6.1680 2025-08-30 04:12:43 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:12:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:13:00 - pico-train - INFO - Step 39225 -- 🔄 Training Metrics 2025-08-30 04:13:00 - pico-train - INFO - ├── Loss: 6.1348 2025-08-30 04:13:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:13:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:13:16 - pico-train - INFO - Step 39250 -- 🔄 Training Metrics 2025-08-30 04:13:16 - pico-train - INFO - ├── Loss: 6.1949 2025-08-30 04:13:16 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:13:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:13:32 - pico-train - INFO - Step 39275 -- 🔄 Training Metrics 2025-08-30 04:13:32 - pico-train - INFO - ├── Loss: 6.1793 2025-08-30 04:13:32 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:13:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:13:49 - pico-train - INFO - Step 39300 -- 🔄 Training Metrics 2025-08-30 04:13:49 - pico-train - INFO - ├── Loss: 6.1331 2025-08-30 04:13:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:13:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:14:05 - pico-train - INFO - Step 39325 -- 🔄 Training Metrics 2025-08-30 04:14:05 - pico-train - INFO - ├── Loss: 6.0823 2025-08-30 04:14:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:14:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:14:22 - pico-train - INFO - Step 39350 -- 🔄 Training Metrics 2025-08-30 04:14:22 - pico-train - INFO - ├── Loss: 6.1036 2025-08-30 04:14:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:14:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:14:39 - pico-train - INFO - Step 39375 -- 🔄 Training Metrics 2025-08-30 04:14:39 - pico-train - INFO - ├── Loss: 6.0327 2025-08-30 04:14:39 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:14:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:14:55 - pico-train - INFO - Step 39400 -- 🔄 Training Metrics 2025-08-30 04:14:55 - pico-train - INFO - ├── Loss: 6.1494 2025-08-30 04:14:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:14:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:15:12 - pico-train - INFO - Step 39425 -- 🔄 Training Metrics 2025-08-30 04:15:12 - pico-train - INFO - ├── Loss: 6.1195 2025-08-30 04:15:12 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:15:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:15:25 - pico-train - INFO - Step 39450 -- 🔄 Training Metrics 2025-08-30 04:15:25 - pico-train - INFO - ├── Loss: 6.1699 2025-08-30 04:15:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:15:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:15:38 - pico-train - INFO - Step 39475 -- 🔄 Training Metrics 2025-08-30 04:15:38 - pico-train - INFO - ├── Loss: 6.1257 2025-08-30 04:15:38 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:15:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:15:50 - pico-train - INFO - Step 39500 -- 💾 Saving Checkpoint 2025-08-30 04:17:42 - pico-train - INFO - Step 39500 -- 📊 Evaluation Results 2025-08-30 04:17:42 - pico-train - INFO - └── paloma: 6.596819084881746e+26 2025-08-30 04:17:44 - pico-train - INFO - Step 39500 -- 🔄 Training Metrics 2025-08-30 04:17:44 - pico-train - INFO - ├── Loss: 6.1615 2025-08-30 04:17:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:17:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:17:44 - pico-train - INFO - Step 39500 -- 📈 Saving Learning Dynamics 2025-08-30 04:18:00 - pico-train - INFO - Step 39525 -- 🔄 Training Metrics 2025-08-30 04:18:00 - pico-train - INFO - ├── Loss: 6.1811 2025-08-30 04:18:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:18:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:18:13 - pico-train - INFO - Step 39550 -- 🔄 Training Metrics 2025-08-30 04:18:13 - pico-train - INFO - ├── Loss: 6.0980 2025-08-30 04:18:13 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:18:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:18:25 - pico-train - INFO - Step 39575 -- 🔄 Training Metrics 2025-08-30 04:18:25 - pico-train - INFO - ├── Loss: 6.1116 2025-08-30 04:18:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:18:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:18:38 - pico-train - INFO - Step 39600 -- 🔄 Training Metrics 2025-08-30 04:18:38 - pico-train - INFO - ├── Loss: 6.1743 2025-08-30 04:18:38 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:18:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:18:51 - pico-train - INFO - Step 39625 -- 🔄 Training Metrics 2025-08-30 04:18:51 - pico-train - INFO - ├── Loss: 6.1422 2025-08-30 04:18:51 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:18:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:19:03 - pico-train - INFO - Step 39650 -- 🔄 Training Metrics 2025-08-30 04:19:03 - pico-train - INFO - ├── Loss: 6.1306 2025-08-30 04:19:03 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:19:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:19:16 - pico-train - INFO - Step 39675 -- 🔄 Training Metrics 2025-08-30 04:19:16 - pico-train - INFO - ├── Loss: 6.1426 2025-08-30 04:19:16 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:19:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:19:29 - pico-train - INFO - Step 39700 -- 🔄 Training Metrics 2025-08-30 04:19:29 - pico-train - INFO - ├── Loss: 6.0568 2025-08-30 04:19:29 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:19:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:19:41 - pico-train - INFO - Step 39725 -- 🔄 Training Metrics 2025-08-30 04:19:41 - pico-train - INFO - ├── Loss: 6.2368 2025-08-30 04:19:41 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:19:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:19:54 - pico-train - INFO - Step 39750 -- 🔄 Training Metrics 2025-08-30 04:19:54 - pico-train - INFO - ├── Loss: 6.0805 2025-08-30 04:19:54 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:19:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:20:06 - pico-train - INFO - Step 39775 -- 🔄 Training Metrics 2025-08-30 04:20:06 - pico-train - INFO - ├── Loss: 6.1451 2025-08-30 04:20:06 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:20:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:20:19 - pico-train - INFO - Step 39800 -- 🔄 Training Metrics 2025-08-30 04:20:19 - pico-train - INFO - ├── Loss: 6.0792 2025-08-30 04:20:19 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:20:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:20:31 - pico-train - INFO - Step 39825 -- 🔄 Training Metrics 2025-08-30 04:20:31 - pico-train - INFO - ├── Loss: 6.0382 2025-08-30 04:20:31 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:20:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:20:44 - pico-train - INFO - Step 39850 -- 🔄 Training Metrics 2025-08-30 04:20:44 - pico-train - INFO - ├── Loss: 6.1423 2025-08-30 04:20:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:20:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:20:57 - pico-train - INFO - Step 39875 -- 🔄 Training Metrics 2025-08-30 04:20:57 - pico-train - INFO - ├── Loss: 6.1012 2025-08-30 04:20:57 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:20:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:21:09 - pico-train - INFO - Step 39900 -- 🔄 Training Metrics 2025-08-30 04:21:09 - pico-train - INFO - ├── Loss: 6.1298 2025-08-30 04:21:09 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:21:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:21:22 - pico-train - INFO - Step 39925 -- 🔄 Training Metrics 2025-08-30 04:21:22 - pico-train - INFO - ├── Loss: 6.1046 2025-08-30 04:21:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:21:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:21:34 - pico-train - INFO - Step 39950 -- 🔄 Training Metrics 2025-08-30 04:21:34 - pico-train - INFO - ├── Loss: 6.1184 2025-08-30 04:21:34 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:21:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:21:47 - pico-train - INFO - Step 39975 -- 🔄 Training Metrics 2025-08-30 04:21:47 - pico-train - INFO - ├── Loss: 6.1598 2025-08-30 04:21:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-30 04:21:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-30 04:21:59 - pico-train - INFO - Step 40000 -- 💾 Saving Checkpoint 2025-08-30 04:24:02 - pico-train - INFO - Step 40000 -- 📊 Evaluation Results 2025-08-30 04:24:02 - pico-train - INFO - └── paloma: 7.314096757540847e+26 2025-08-30 04:24:03 - pico-train - INFO - 🎉 Training complete! Final step: 40000