2025-08-29 17:46:50 - pico-train - INFO - Step 0 -- 📊 Evaluation Results 2025-08-29 17:46:50 - pico-train - INFO - └── paloma: inf 2025-08-29 17:46:50 - pico-train - INFO - ================================================== 2025-08-29 17:46:50 - pico-train - INFO - ✨ Training Configuration 2025-08-29 17:46:50 - pico-train - INFO - ================================================== 2025-08-29 17:46:50 - pico-train - INFO - ╭─────────────────────────────────────────────────────╮ 2025-08-29 17:46:50 - pico-train - INFO - │ checkpointing: │ 2025-08-29 17:46:50 - pico-train - INFO - │ checkpoints_dir: checkpoints │ 2025-08-29 17:46:50 - pico-train - INFO - │ evaluation: │ 2025-08-29 17:46:50 - pico-train - INFO - │ eval_results_dir: eval_results │ 2025-08-29 17:46:50 - pico-train - INFO - │ fabric_checkpoint_dir: fabric_state │ 2025-08-29 17:46:50 - pico-train - INFO - │ fabric_checkpoint_filename: checkpoint.pt │ 2025-08-29 17:46:50 - pico-train - INFO - │ hf_checkpoint: │ 2025-08-29 17:46:50 - pico-train - INFO - │ collection_slug: null │ 2025-08-29 17:46:50 - pico-train - INFO - │ repo_id: ThomasTheMaker/pico-decoder-tiny │ 2025-08-29 17:46:50 - pico-train - INFO - │ learning_dynamics: │ 2025-08-29 17:46:50 - pico-train - INFO - │ batch_size: 1 │ 2025-08-29 17:46:50 - pico-train - INFO - │ eval_data: null │ 2025-08-29 17:46:50 - pico-train - INFO - │ layer_suffixes: │ 2025-08-29 17:46:50 - pico-train - INFO - │ - attention.v_proj │ 2025-08-29 17:46:50 - pico-train - INFO - │ - attention.o_proj │ 2025-08-29 17:46:50 - pico-train - INFO - │ - swiglu.w_2 │ 2025-08-29 17:46:50 - pico-train - INFO - │ sequence_idx: -1 │ 2025-08-29 17:46:50 - pico-train - INFO - │ learning_dynamics_dir: learning_dynamics │ 2025-08-29 17:46:50 - pico-train - INFO - │ logs_dir: logs │ 2025-08-29 17:46:50 - pico-train - INFO - │ run_name: pico-decoder-tiny-dolma5M-v1 │ 2025-08-29 17:46:50 - pico-train - INFO - │ runs_dir: runs │ 2025-08-29 17:46:50 - pico-train - INFO - │ save_every_n_steps: 500 │ 2025-08-29 17:46:50 - pico-train - INFO - │ save_to_hf: true │ 2025-08-29 17:46:50 - pico-train - INFO - │ training: │ 2025-08-29 17:46:50 - pico-train - INFO - │ auto_resume: true │ 2025-08-29 17:46:50 - pico-train - INFO - │ data: │ 2025-08-29 17:46:50 - pico-train - INFO - │ dataloader: │ 2025-08-29 17:46:50 - pico-train - INFO - │ batch_size: 4 │ 2025-08-29 17:46:50 - pico-train - INFO - │ dataset: │ 2025-08-29 17:46:50 - pico-train - INFO - │ name: ThomasTheMaker/pretokenized-dolma-5M │ 2025-08-29 17:46:50 - pico-train - INFO - │ tokenizer: │ 2025-08-29 17:46:50 - pico-train - INFO - │ name: allenai/OLMo-7B-0724-hf │ 2025-08-29 17:46:50 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-29 17:46:50 - pico-train - INFO - │ evaluation: │ 2025-08-29 17:46:50 - pico-train - INFO - │ metrics: │ 2025-08-29 17:46:50 - pico-train - INFO - │ - paloma │ 2025-08-29 17:46:50 - pico-train - INFO - │ paloma: │ 2025-08-29 17:46:50 - pico-train - INFO - │ batch_size: 1 │ 2025-08-29 17:46:50 - pico-train - INFO - │ dataset_name: pico-lm/pretokenized-paloma-tinsy │ 2025-08-29 17:46:50 - pico-train - INFO - │ dataset_split: val │ 2025-08-29 17:46:50 - pico-train - INFO - │ max_length: 2048 │ 2025-08-29 17:46:50 - pico-train - INFO - │ model: │ 2025-08-29 17:46:50 - pico-train - INFO - │ activation_hidden_dim: 384 │ 2025-08-29 17:46:50 - pico-train - INFO - │ attention_n_heads: 12 │ 2025-08-29 17:46:50 - pico-train - INFO - │ attention_n_kv_heads: 4 │ 2025-08-29 17:46:50 - pico-train - INFO - │ batch_size: 1024 │ 2025-08-29 17:46:50 - pico-train - INFO - │ d_model: 96 │ 2025-08-29 17:46:50 - pico-train - INFO - │ max_seq_len: 2048 │ 2025-08-29 17:46:50 - pico-train - INFO - │ model_type: pico_decoder │ 2025-08-29 17:46:50 - pico-train - INFO - │ n_layers: 12 │ 2025-08-29 17:46:50 - pico-train - INFO - │ norm_eps: 1.0e-06 │ 2025-08-29 17:46:50 - pico-train - INFO - │ position_emb_theta: 10000.0 │ 2025-08-29 17:46:50 - pico-train - INFO - │ vocab_size: 50304 │ 2025-08-29 17:46:50 - pico-train - INFO - │ monitoring: │ 2025-08-29 17:46:50 - pico-train - INFO - │ logging: │ 2025-08-29 17:46:50 - pico-train - INFO - │ log_every_n_steps: 25 │ 2025-08-29 17:46:50 - pico-train - INFO - │ log_level: INFO │ 2025-08-29 17:46:50 - pico-train - INFO - │ save_to_wandb: false │ 2025-08-29 17:46:50 - pico-train - INFO - │ wandb: │ 2025-08-29 17:46:50 - pico-train - INFO - │ entity: boymyc │ 2025-08-29 17:46:50 - pico-train - INFO - │ project: pico-decoder-tiny │ 2025-08-29 17:46:50 - pico-train - INFO - │ training: │ 2025-08-29 17:46:50 - pico-train - INFO - │ fabric: │ 2025-08-29 17:46:50 - pico-train - INFO - │ accelerator: cuda │ 2025-08-29 17:46:50 - pico-train - INFO - │ num_devices: 1 │ 2025-08-29 17:46:50 - pico-train - INFO - │ num_nodes: 1 │ 2025-08-29 17:46:50 - pico-train - INFO - │ precision: bf16-mixed │ 2025-08-29 17:46:50 - pico-train - INFO - │ max_steps: 20000 │ 2025-08-29 17:46:50 - pico-train - INFO - │ optimization: │ 2025-08-29 17:46:50 - pico-train - INFO - │ gradient_accumulation_steps: 4 │ 2025-08-29 17:46:50 - pico-train - INFO - │ lr: 5.0e-05 │ 2025-08-29 17:46:50 - pico-train - INFO - │ lr_scheduler: cosine │ 2025-08-29 17:46:50 - pico-train - INFO - │ lr_warmup_steps: 8000 │ 2025-08-29 17:46:50 - pico-train - INFO - │ optimizer: adamw │ 2025-08-29 17:46:50 - pico-train - INFO - │ │ 2025-08-29 17:46:50 - pico-train - INFO - ╰─────────────────────────────────────────────────────╯ 2025-08-29 17:46:50 - pico-train - INFO - ================================================== 2025-08-29 17:46:50 - pico-train - INFO - ⛭ Runtime Summary: 2025-08-29 17:46:50 - pico-train - INFO - ================================================== 2025-08-29 17:46:50 - pico-train - INFO - Starting from step: 0 2025-08-29 17:46:50 - pico-train - INFO - Model Setup: 2025-08-29 17:46:50 - pico-train - INFO - └─ Total Parameters: 11,282,784 2025-08-29 17:46:50 - pico-train - INFO - └─ Trainable Parameters: 11,282,784 2025-08-29 17:46:50 - pico-train - INFO - Distributed Setup: 2025-08-29 17:46:50 - pico-train - INFO - └─ Number of Devices: 1 2025-08-29 17:46:50 - pico-train - INFO - └─ Device Type: NVIDIA GeForce RTX 5090 2025-08-29 17:46:50 - pico-train - INFO - └─ Available Memory: 33.68 GB 2025-08-29 17:46:50 - pico-train - INFO - Software Setup: 2025-08-29 17:46:50 - pico-train - INFO - └─ Python Version: 3.10.12 2025-08-29 17:46:50 - pico-train - INFO - └─ PyTorch Version: 2.8.0+cu128 2025-08-29 17:46:50 - pico-train - INFO - └─ CUDA Version: 12.8 2025-08-29 17:46:50 - pico-train - INFO - └─ Operating System: Linux 6.8.0-63-generic 2025-08-29 17:46:50 - pico-train - INFO - Batch Size Configuration: 2025-08-29 17:46:50 - pico-train - INFO - └─ Global Batch Size: 4 2025-08-29 17:46:50 - pico-train - INFO - └─ Per Device Batch Size: 1 2025-08-29 17:46:50 - pico-train - INFO - └─ Gradient Accumulation Steps: 4 2025-08-29 17:46:50 - pico-train - INFO - ================================================== 2025-08-29 17:46:52 - pico-train - INFO - Step 0 -- 🔄 Training Metrics 2025-08-29 17:46:52 - pico-train - INFO - ├── Loss: 10.9975 2025-08-29 17:46:52 - pico-train - INFO - ├── Learning Rate: 0.00e+00 2025-08-29 17:46:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:46:52 - pico-train - INFO - Step 0 -- 📈 Saving Learning Dynamics 2025-08-29 17:47:06 - pico-train - INFO - Step 25 -- 🔄 Training Metrics 2025-08-29 17:47:06 - pico-train - INFO - ├── Loss: 10.9972 2025-08-29 17:47:06 - pico-train - INFO - ├── Learning Rate: 1.56e-07 2025-08-29 17:47:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:47:18 - pico-train - INFO - Step 50 -- 🔄 Training Metrics 2025-08-29 17:47:18 - pico-train - INFO - ├── Loss: 11.0030 2025-08-29 17:47:18 - pico-train - INFO - ├── Learning Rate: 3.13e-07 2025-08-29 17:47:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:47:31 - pico-train - INFO - Step 75 -- 🔄 Training Metrics 2025-08-29 17:47:31 - pico-train - INFO - ├── Loss: 11.0034 2025-08-29 17:47:31 - pico-train - INFO - ├── Learning Rate: 4.69e-07 2025-08-29 17:47:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:47:43 - pico-train - INFO - Step 100 -- 🔄 Training Metrics 2025-08-29 17:47:43 - pico-train - INFO - ├── Loss: 10.9962 2025-08-29 17:47:43 - pico-train - INFO - ├── Learning Rate: 6.25e-07 2025-08-29 17:47:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:47:56 - pico-train - INFO - Step 125 -- 🔄 Training Metrics 2025-08-29 17:47:56 - pico-train - INFO - ├── Loss: 10.9973 2025-08-29 17:47:56 - pico-train - INFO - ├── Learning Rate: 7.81e-07 2025-08-29 17:47:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:48:08 - pico-train - INFO - Step 150 -- 🔄 Training Metrics 2025-08-29 17:48:08 - pico-train - INFO - ├── Loss: 10.9943 2025-08-29 17:48:08 - pico-train - INFO - ├── Learning Rate: 9.38e-07 2025-08-29 17:48:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:48:21 - pico-train - INFO - Step 175 -- 🔄 Training Metrics 2025-08-29 17:48:21 - pico-train - INFO - ├── Loss: 10.9860 2025-08-29 17:48:21 - pico-train - INFO - ├── Learning Rate: 1.09e-06 2025-08-29 17:48:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:48:33 - pico-train - INFO - Step 200 -- 🔄 Training Metrics 2025-08-29 17:48:33 - pico-train - INFO - ├── Loss: 10.9885 2025-08-29 17:48:33 - pico-train - INFO - ├── Learning Rate: 1.25e-06 2025-08-29 17:48:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:48:46 - pico-train - INFO - Step 225 -- 🔄 Training Metrics 2025-08-29 17:48:46 - pico-train - INFO - ├── Loss: 10.9816 2025-08-29 17:48:46 - pico-train - INFO - ├── Learning Rate: 1.41e-06 2025-08-29 17:48:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:48:59 - pico-train - INFO - Step 250 -- 🔄 Training Metrics 2025-08-29 17:48:59 - pico-train - INFO - ├── Loss: 10.9786 2025-08-29 17:48:59 - pico-train - INFO - ├── Learning Rate: 1.56e-06 2025-08-29 17:48:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:49:11 - pico-train - INFO - Step 275 -- 🔄 Training Metrics 2025-08-29 17:49:11 - pico-train - INFO - ├── Loss: 10.9707 2025-08-29 17:49:11 - pico-train - INFO - ├── Learning Rate: 1.72e-06 2025-08-29 17:49:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:49:23 - pico-train - INFO - Step 300 -- 🔄 Training Metrics 2025-08-29 17:49:23 - pico-train - INFO - ├── Loss: 10.9700 2025-08-29 17:49:23 - pico-train - INFO - ├── Learning Rate: 1.88e-06 2025-08-29 17:49:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:49:36 - pico-train - INFO - Step 325 -- 🔄 Training Metrics 2025-08-29 17:49:36 - pico-train - INFO - ├── Loss: 10.9626 2025-08-29 17:49:36 - pico-train - INFO - ├── Learning Rate: 2.03e-06 2025-08-29 17:49:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:49:48 - pico-train - INFO - Step 350 -- 🔄 Training Metrics 2025-08-29 17:49:48 - pico-train - INFO - ├── Loss: 10.9580 2025-08-29 17:49:48 - pico-train - INFO - ├── Learning Rate: 2.19e-06 2025-08-29 17:49:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:50:01 - pico-train - INFO - Step 375 -- 🔄 Training Metrics 2025-08-29 17:50:01 - pico-train - INFO - ├── Loss: 10.9486 2025-08-29 17:50:01 - pico-train - INFO - ├── Learning Rate: 2.34e-06 2025-08-29 17:50:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:50:13 - pico-train - INFO - Step 400 -- 🔄 Training Metrics 2025-08-29 17:50:13 - pico-train - INFO - ├── Loss: 10.9417 2025-08-29 17:50:13 - pico-train - INFO - ├── Learning Rate: 2.50e-06 2025-08-29 17:50:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:50:26 - pico-train - INFO - Step 425 -- 🔄 Training Metrics 2025-08-29 17:50:26 - pico-train - INFO - ├── Loss: 10.9328 2025-08-29 17:50:26 - pico-train - INFO - ├── Learning Rate: 2.66e-06 2025-08-29 17:50:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:50:39 - pico-train - INFO - Step 450 -- 🔄 Training Metrics 2025-08-29 17:50:39 - pico-train - INFO - ├── Loss: 10.9242 2025-08-29 17:50:39 - pico-train - INFO - ├── Learning Rate: 2.81e-06 2025-08-29 17:50:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:50:51 - pico-train - INFO - Step 475 -- 🔄 Training Metrics 2025-08-29 17:50:51 - pico-train - INFO - ├── Loss: 10.9170 2025-08-29 17:50:51 - pico-train - INFO - ├── Learning Rate: 2.97e-06 2025-08-29 17:50:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:51:03 - pico-train - INFO - Step 500 -- 💾 Saving Checkpoint 2025-08-29 17:52:53 - pico-train - INFO - Step 500 -- 📊 Evaluation Results 2025-08-29 17:52:53 - pico-train - INFO - └── paloma: inf 2025-08-29 17:52:55 - pico-train - INFO - Step 500 -- 🔄 Training Metrics 2025-08-29 17:52:55 - pico-train - INFO - ├── Loss: 10.8979 2025-08-29 17:52:55 - pico-train - INFO - ├── Learning Rate: 3.13e-06 2025-08-29 17:52:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:52:55 - pico-train - INFO - Step 500 -- 📈 Saving Learning Dynamics 2025-08-29 17:53:09 - pico-train - INFO - Step 525 -- 🔄 Training Metrics 2025-08-29 17:53:09 - pico-train - INFO - ├── Loss: 10.8890 2025-08-29 17:53:09 - pico-train - INFO - ├── Learning Rate: 3.28e-06 2025-08-29 17:53:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:53:22 - pico-train - INFO - Step 550 -- 🔄 Training Metrics 2025-08-29 17:53:22 - pico-train - INFO - ├── Loss: 10.8846 2025-08-29 17:53:22 - pico-train - INFO - ├── Learning Rate: 3.44e-06 2025-08-29 17:53:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:53:35 - pico-train - INFO - Step 575 -- 🔄 Training Metrics 2025-08-29 17:53:35 - pico-train - INFO - ├── Loss: 10.8657 2025-08-29 17:53:35 - pico-train - INFO - ├── Learning Rate: 3.59e-06 2025-08-29 17:53:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:53:47 - pico-train - INFO - Step 600 -- 🔄 Training Metrics 2025-08-29 17:53:47 - pico-train - INFO - ├── Loss: 10.8590 2025-08-29 17:53:47 - pico-train - INFO - ├── Learning Rate: 3.75e-06 2025-08-29 17:53:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:54:00 - pico-train - INFO - Step 625 -- 🔄 Training Metrics 2025-08-29 17:54:00 - pico-train - INFO - ├── Loss: 10.8328 2025-08-29 17:54:00 - pico-train - INFO - ├── Learning Rate: 3.91e-06 2025-08-29 17:54:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:54:12 - pico-train - INFO - Step 650 -- 🔄 Training Metrics 2025-08-29 17:54:12 - pico-train - INFO - ├── Loss: 10.8166 2025-08-29 17:54:12 - pico-train - INFO - ├── Learning Rate: 4.06e-06 2025-08-29 17:54:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:54:25 - pico-train - INFO - Step 675 -- 🔄 Training Metrics 2025-08-29 17:54:25 - pico-train - INFO - ├── Loss: 10.7913 2025-08-29 17:54:25 - pico-train - INFO - ├── Learning Rate: 4.22e-06 2025-08-29 17:54:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:54:38 - pico-train - INFO - Step 700 -- 🔄 Training Metrics 2025-08-29 17:54:38 - pico-train - INFO - ├── Loss: 10.7609 2025-08-29 17:54:38 - pico-train - INFO - ├── Learning Rate: 4.37e-06 2025-08-29 17:54:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:54:50 - pico-train - INFO - Step 725 -- 🔄 Training Metrics 2025-08-29 17:54:50 - pico-train - INFO - ├── Loss: 10.7322 2025-08-29 17:54:50 - pico-train - INFO - ├── Learning Rate: 4.53e-06 2025-08-29 17:54:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:55:03 - pico-train - INFO - Step 750 -- 🔄 Training Metrics 2025-08-29 17:55:03 - pico-train - INFO - ├── Loss: 10.7121 2025-08-29 17:55:03 - pico-train - INFO - ├── Learning Rate: 4.69e-06 2025-08-29 17:55:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:55:15 - pico-train - INFO - Step 775 -- 🔄 Training Metrics 2025-08-29 17:55:15 - pico-train - INFO - ├── Loss: 10.6877 2025-08-29 17:55:15 - pico-train - INFO - ├── Learning Rate: 4.84e-06 2025-08-29 17:55:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:55:28 - pico-train - INFO - Step 800 -- 🔄 Training Metrics 2025-08-29 17:55:28 - pico-train - INFO - ├── Loss: 10.6436 2025-08-29 17:55:28 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 17:55:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:55:41 - pico-train - INFO - Step 825 -- 🔄 Training Metrics 2025-08-29 17:55:41 - pico-train - INFO - ├── Loss: 10.6256 2025-08-29 17:55:41 - pico-train - INFO - ├── Learning Rate: 5.16e-06 2025-08-29 17:55:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:55:53 - pico-train - INFO - Step 850 -- 🔄 Training Metrics 2025-08-29 17:55:53 - pico-train - INFO - ├── Loss: 10.5961 2025-08-29 17:55:53 - pico-train - INFO - ├── Learning Rate: 5.31e-06 2025-08-29 17:55:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:56:06 - pico-train - INFO - Step 875 -- 🔄 Training Metrics 2025-08-29 17:56:06 - pico-train - INFO - ├── Loss: 10.5443 2025-08-29 17:56:06 - pico-train - INFO - ├── Learning Rate: 5.47e-06 2025-08-29 17:56:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:56:18 - pico-train - INFO - Step 900 -- 🔄 Training Metrics 2025-08-29 17:56:18 - pico-train - INFO - ├── Loss: 10.5197 2025-08-29 17:56:18 - pico-train - INFO - ├── Learning Rate: 5.63e-06 2025-08-29 17:56:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:56:31 - pico-train - INFO - Step 925 -- 🔄 Training Metrics 2025-08-29 17:56:31 - pico-train - INFO - ├── Loss: 10.4854 2025-08-29 17:56:31 - pico-train - INFO - ├── Learning Rate: 5.78e-06 2025-08-29 17:56:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:56:44 - pico-train - INFO - Step 950 -- 🔄 Training Metrics 2025-08-29 17:56:44 - pico-train - INFO - ├── Loss: 10.4826 2025-08-29 17:56:44 - pico-train - INFO - ├── Learning Rate: 5.94e-06 2025-08-29 17:56:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:56:56 - pico-train - INFO - Step 975 -- 🔄 Training Metrics 2025-08-29 17:56:56 - pico-train - INFO - ├── Loss: 10.4557 2025-08-29 17:56:56 - pico-train - INFO - ├── Learning Rate: 6.09e-06 2025-08-29 17:56:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:57:09 - pico-train - INFO - Step 1000 -- 💾 Saving Checkpoint 2025-08-29 17:59:05 - pico-train - INFO - Step 1000 -- 📊 Evaluation Results 2025-08-29 17:59:05 - pico-train - INFO - └── paloma: 7.125172406420199e+27 2025-08-29 17:59:08 - pico-train - INFO - Step 1000 -- 🔄 Training Metrics 2025-08-29 17:59:08 - pico-train - INFO - ├── Loss: 10.4142 2025-08-29 17:59:08 - pico-train - INFO - ├── Learning Rate: 6.25e-06 2025-08-29 17:59:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:59:08 - pico-train - INFO - Step 1000 -- 📈 Saving Learning Dynamics 2025-08-29 17:59:22 - pico-train - INFO - Step 1025 -- 🔄 Training Metrics 2025-08-29 17:59:22 - pico-train - INFO - ├── Loss: 10.3885 2025-08-29 17:59:22 - pico-train - INFO - ├── Learning Rate: 6.41e-06 2025-08-29 17:59:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:59:35 - pico-train - INFO - Step 1050 -- 🔄 Training Metrics 2025-08-29 17:59:35 - pico-train - INFO - ├── Loss: 10.3737 2025-08-29 17:59:35 - pico-train - INFO - ├── Learning Rate: 6.56e-06 2025-08-29 17:59:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 17:59:47 - pico-train - INFO - Step 1075 -- 🔄 Training Metrics 2025-08-29 17:59:47 - pico-train - INFO - ├── Loss: 10.3534 2025-08-29 17:59:47 - pico-train - INFO - ├── Learning Rate: 6.72e-06 2025-08-29 17:59:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:00:00 - pico-train - INFO - Step 1100 -- 🔄 Training Metrics 2025-08-29 18:00:00 - pico-train - INFO - ├── Loss: 10.3219 2025-08-29 18:00:00 - pico-train - INFO - ├── Learning Rate: 6.88e-06 2025-08-29 18:00:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:00:13 - pico-train - INFO - Step 1125 -- 🔄 Training Metrics 2025-08-29 18:00:13 - pico-train - INFO - ├── Loss: 10.3064 2025-08-29 18:00:13 - pico-train - INFO - ├── Learning Rate: 7.03e-06 2025-08-29 18:00:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:00:25 - pico-train - INFO - Step 1150 -- 🔄 Training Metrics 2025-08-29 18:00:25 - pico-train - INFO - ├── Loss: 10.2761 2025-08-29 18:00:25 - pico-train - INFO - ├── Learning Rate: 7.19e-06 2025-08-29 18:00:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:00:38 - pico-train - INFO - Step 1175 -- 🔄 Training Metrics 2025-08-29 18:00:38 - pico-train - INFO - ├── Loss: 10.2592 2025-08-29 18:00:38 - pico-train - INFO - ├── Learning Rate: 7.34e-06 2025-08-29 18:00:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:00:50 - pico-train - INFO - Step 1200 -- 🔄 Training Metrics 2025-08-29 18:00:50 - pico-train - INFO - ├── Loss: 10.2420 2025-08-29 18:00:50 - pico-train - INFO - ├── Learning Rate: 7.50e-06 2025-08-29 18:00:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:01:03 - pico-train - INFO - Step 1225 -- 🔄 Training Metrics 2025-08-29 18:01:03 - pico-train - INFO - ├── Loss: 10.2141 2025-08-29 18:01:03 - pico-train - INFO - ├── Learning Rate: 7.66e-06 2025-08-29 18:01:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:01:15 - pico-train - INFO - Step 1250 -- 🔄 Training Metrics 2025-08-29 18:01:15 - pico-train - INFO - ├── Loss: 10.1882 2025-08-29 18:01:15 - pico-train - INFO - ├── Learning Rate: 7.81e-06 2025-08-29 18:01:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:01:28 - pico-train - INFO - Step 1275 -- 🔄 Training Metrics 2025-08-29 18:01:28 - pico-train - INFO - ├── Loss: 10.1608 2025-08-29 18:01:28 - pico-train - INFO - ├── Learning Rate: 7.97e-06 2025-08-29 18:01:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:01:40 - pico-train - INFO - Step 1300 -- 🔄 Training Metrics 2025-08-29 18:01:40 - pico-train - INFO - ├── Loss: 10.1460 2025-08-29 18:01:40 - pico-train - INFO - ├── Learning Rate: 8.13e-06 2025-08-29 18:01:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:01:53 - pico-train - INFO - Step 1325 -- 🔄 Training Metrics 2025-08-29 18:01:53 - pico-train - INFO - ├── Loss: 10.0944 2025-08-29 18:01:53 - pico-train - INFO - ├── Learning Rate: 8.28e-06 2025-08-29 18:01:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:02:05 - pico-train - INFO - Step 1350 -- 🔄 Training Metrics 2025-08-29 18:02:05 - pico-train - INFO - ├── Loss: 10.0885 2025-08-29 18:02:05 - pico-train - INFO - ├── Learning Rate: 8.44e-06 2025-08-29 18:02:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:02:18 - pico-train - INFO - Step 1375 -- 🔄 Training Metrics 2025-08-29 18:02:18 - pico-train - INFO - ├── Loss: 10.0748 2025-08-29 18:02:18 - pico-train - INFO - ├── Learning Rate: 8.59e-06 2025-08-29 18:02:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:02:31 - pico-train - INFO - Step 1400 -- 🔄 Training Metrics 2025-08-29 18:02:31 - pico-train - INFO - ├── Loss: 10.0425 2025-08-29 18:02:31 - pico-train - INFO - ├── Learning Rate: 8.75e-06 2025-08-29 18:02:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:02:43 - pico-train - INFO - Step 1425 -- 🔄 Training Metrics 2025-08-29 18:02:43 - pico-train - INFO - ├── Loss: 10.0422 2025-08-29 18:02:43 - pico-train - INFO - ├── Learning Rate: 8.91e-06 2025-08-29 18:02:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:02:56 - pico-train - INFO - Step 1450 -- 🔄 Training Metrics 2025-08-29 18:02:56 - pico-train - INFO - ├── Loss: 10.0039 2025-08-29 18:02:56 - pico-train - INFO - ├── Learning Rate: 9.06e-06 2025-08-29 18:02:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:03:08 - pico-train - INFO - Step 1475 -- 🔄 Training Metrics 2025-08-29 18:03:08 - pico-train - INFO - ├── Loss: 9.9736 2025-08-29 18:03:08 - pico-train - INFO - ├── Learning Rate: 9.22e-06 2025-08-29 18:03:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:03:20 - pico-train - INFO - Step 1500 -- 💾 Saving Checkpoint 2025-08-29 18:05:15 - pico-train - INFO - Step 1500 -- 📊 Evaluation Results 2025-08-29 18:05:15 - pico-train - INFO - └── paloma: 6.5469212698356e+18 2025-08-29 18:05:17 - pico-train - INFO - Step 1500 -- 🔄 Training Metrics 2025-08-29 18:05:17 - pico-train - INFO - ├── Loss: 9.9729 2025-08-29 18:05:17 - pico-train - INFO - ├── Learning Rate: 9.38e-06 2025-08-29 18:05:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:05:17 - pico-train - INFO - Step 1500 -- 📈 Saving Learning Dynamics 2025-08-29 18:05:32 - pico-train - INFO - Step 1525 -- 🔄 Training Metrics 2025-08-29 18:05:32 - pico-train - INFO - ├── Loss: 9.9379 2025-08-29 18:05:32 - pico-train - INFO - ├── Learning Rate: 9.53e-06 2025-08-29 18:05:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:05:45 - pico-train - INFO - Step 1550 -- 🔄 Training Metrics 2025-08-29 18:05:45 - pico-train - INFO - ├── Loss: 9.8819 2025-08-29 18:05:45 - pico-train - INFO - ├── Learning Rate: 9.69e-06 2025-08-29 18:05:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:05:57 - pico-train - INFO - Step 1575 -- 🔄 Training Metrics 2025-08-29 18:05:57 - pico-train - INFO - ├── Loss: 9.8702 2025-08-29 18:05:57 - pico-train - INFO - ├── Learning Rate: 9.84e-06 2025-08-29 18:05:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:06:10 - pico-train - INFO - Step 1600 -- 🔄 Training Metrics 2025-08-29 18:06:10 - pico-train - INFO - ├── Loss: 9.8571 2025-08-29 18:06:10 - pico-train - INFO - ├── Learning Rate: 1.00e-05 2025-08-29 18:06:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:06:23 - pico-train - INFO - Step 1625 -- 🔄 Training Metrics 2025-08-29 18:06:23 - pico-train - INFO - ├── Loss: 9.8356 2025-08-29 18:06:23 - pico-train - INFO - ├── Learning Rate: 1.02e-05 2025-08-29 18:06:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:06:35 - pico-train - INFO - Step 1650 -- 🔄 Training Metrics 2025-08-29 18:06:35 - pico-train - INFO - ├── Loss: 9.7973 2025-08-29 18:06:35 - pico-train - INFO - ├── Learning Rate: 1.03e-05 2025-08-29 18:06:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:06:48 - pico-train - INFO - Step 1675 -- 🔄 Training Metrics 2025-08-29 18:06:48 - pico-train - INFO - ├── Loss: 9.7745 2025-08-29 18:06:48 - pico-train - INFO - ├── Learning Rate: 1.05e-05 2025-08-29 18:06:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:07:01 - pico-train - INFO - Step 1700 -- 🔄 Training Metrics 2025-08-29 18:07:01 - pico-train - INFO - ├── Loss: 9.7673 2025-08-29 18:07:01 - pico-train - INFO - ├── Learning Rate: 1.06e-05 2025-08-29 18:07:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:07:14 - pico-train - INFO - Step 1725 -- 🔄 Training Metrics 2025-08-29 18:07:14 - pico-train - INFO - ├── Loss: 9.7406 2025-08-29 18:07:14 - pico-train - INFO - ├── Learning Rate: 1.08e-05 2025-08-29 18:07:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:07:26 - pico-train - INFO - Step 1750 -- 🔄 Training Metrics 2025-08-29 18:07:26 - pico-train - INFO - ├── Loss: 9.7312 2025-08-29 18:07:26 - pico-train - INFO - ├── Learning Rate: 1.09e-05 2025-08-29 18:07:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:07:39 - pico-train - INFO - Step 1775 -- 🔄 Training Metrics 2025-08-29 18:07:39 - pico-train - INFO - ├── Loss: 9.6563 2025-08-29 18:07:39 - pico-train - INFO - ├── Learning Rate: 1.11e-05 2025-08-29 18:07:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:07:51 - pico-train - INFO - Step 1800 -- 🔄 Training Metrics 2025-08-29 18:07:51 - pico-train - INFO - ├── Loss: 9.6515 2025-08-29 18:07:51 - pico-train - INFO - ├── Learning Rate: 1.13e-05 2025-08-29 18:07:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:08:04 - pico-train - INFO - Step 1825 -- 🔄 Training Metrics 2025-08-29 18:08:04 - pico-train - INFO - ├── Loss: 9.6241 2025-08-29 18:08:04 - pico-train - INFO - ├── Learning Rate: 1.14e-05 2025-08-29 18:08:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:08:17 - pico-train - INFO - Step 1850 -- 🔄 Training Metrics 2025-08-29 18:08:17 - pico-train - INFO - ├── Loss: 9.6015 2025-08-29 18:08:17 - pico-train - INFO - ├── Learning Rate: 1.16e-05 2025-08-29 18:08:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:08:29 - pico-train - INFO - Step 1875 -- 🔄 Training Metrics 2025-08-29 18:08:29 - pico-train - INFO - ├── Loss: 9.5933 2025-08-29 18:08:29 - pico-train - INFO - ├── Learning Rate: 1.17e-05 2025-08-29 18:08:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:08:42 - pico-train - INFO - Step 1900 -- 🔄 Training Metrics 2025-08-29 18:08:42 - pico-train - INFO - ├── Loss: 9.5544 2025-08-29 18:08:42 - pico-train - INFO - ├── Learning Rate: 1.19e-05 2025-08-29 18:08:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:08:54 - pico-train - INFO - Step 1925 -- 🔄 Training Metrics 2025-08-29 18:08:54 - pico-train - INFO - ├── Loss: 9.5407 2025-08-29 18:08:54 - pico-train - INFO - ├── Learning Rate: 1.20e-05 2025-08-29 18:08:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:09:07 - pico-train - INFO - Step 1950 -- 🔄 Training Metrics 2025-08-29 18:09:07 - pico-train - INFO - ├── Loss: 9.5431 2025-08-29 18:09:07 - pico-train - INFO - ├── Learning Rate: 1.22e-05 2025-08-29 18:09:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:09:19 - pico-train - INFO - Step 1975 -- 🔄 Training Metrics 2025-08-29 18:09:19 - pico-train - INFO - ├── Loss: 9.4853 2025-08-29 18:09:19 - pico-train - INFO - ├── Learning Rate: 1.23e-05 2025-08-29 18:09:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:09:31 - pico-train - INFO - Step 2000 -- 💾 Saving Checkpoint 2025-08-29 18:11:25 - pico-train - INFO - Step 2000 -- 📊 Evaluation Results 2025-08-29 18:11:25 - pico-train - INFO - └── paloma: 5.118641309912889e+18 2025-08-29 18:11:29 - pico-train - INFO - Step 2000 -- 🔄 Training Metrics 2025-08-29 18:11:29 - pico-train - INFO - ├── Loss: 9.4665 2025-08-29 18:11:29 - pico-train - INFO - ├── Learning Rate: 1.25e-05 2025-08-29 18:11:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:11:29 - pico-train - INFO - Step 2000 -- 📈 Saving Learning Dynamics 2025-08-29 18:11:43 - pico-train - INFO - Step 2025 -- 🔄 Training Metrics 2025-08-29 18:11:43 - pico-train - INFO - ├── Loss: 9.4621 2025-08-29 18:11:43 - pico-train - INFO - ├── Learning Rate: 1.27e-05 2025-08-29 18:11:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:11:56 - pico-train - INFO - Step 2050 -- 🔄 Training Metrics 2025-08-29 18:11:56 - pico-train - INFO - ├── Loss: 9.4031 2025-08-29 18:11:56 - pico-train - INFO - ├── Learning Rate: 1.28e-05 2025-08-29 18:11:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:12:08 - pico-train - INFO - Step 2075 -- 🔄 Training Metrics 2025-08-29 18:12:08 - pico-train - INFO - ├── Loss: 9.3699 2025-08-29 18:12:08 - pico-train - INFO - ├── Learning Rate: 1.30e-05 2025-08-29 18:12:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:12:21 - pico-train - INFO - Step 2100 -- 🔄 Training Metrics 2025-08-29 18:12:21 - pico-train - INFO - ├── Loss: 9.3422 2025-08-29 18:12:21 - pico-train - INFO - ├── Learning Rate: 1.31e-05 2025-08-29 18:12:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:12:33 - pico-train - INFO - Step 2125 -- 🔄 Training Metrics 2025-08-29 18:12:33 - pico-train - INFO - ├── Loss: 9.3129 2025-08-29 18:12:33 - pico-train - INFO - ├── Learning Rate: 1.33e-05 2025-08-29 18:12:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:12:46 - pico-train - INFO - Step 2150 -- 🔄 Training Metrics 2025-08-29 18:12:46 - pico-train - INFO - ├── Loss: 9.2917 2025-08-29 18:12:46 - pico-train - INFO - ├── Learning Rate: 1.34e-05 2025-08-29 18:12:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:12:58 - pico-train - INFO - Step 2175 -- 🔄 Training Metrics 2025-08-29 18:12:58 - pico-train - INFO - ├── Loss: 9.2670 2025-08-29 18:12:58 - pico-train - INFO - ├── Learning Rate: 1.36e-05 2025-08-29 18:12:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:13:11 - pico-train - INFO - Step 2200 -- 🔄 Training Metrics 2025-08-29 18:13:11 - pico-train - INFO - ├── Loss: 9.2512 2025-08-29 18:13:11 - pico-train - INFO - ├── Learning Rate: 1.38e-05 2025-08-29 18:13:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:13:23 - pico-train - INFO - Step 2225 -- 🔄 Training Metrics 2025-08-29 18:13:23 - pico-train - INFO - ├── Loss: 9.2737 2025-08-29 18:13:23 - pico-train - INFO - ├── Learning Rate: 1.39e-05 2025-08-29 18:13:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:13:36 - pico-train - INFO - Step 2250 -- 🔄 Training Metrics 2025-08-29 18:13:36 - pico-train - INFO - ├── Loss: 9.2357 2025-08-29 18:13:36 - pico-train - INFO - ├── Learning Rate: 1.41e-05 2025-08-29 18:13:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:13:49 - pico-train - INFO - Step 2275 -- 🔄 Training Metrics 2025-08-29 18:13:49 - pico-train - INFO - ├── Loss: 9.1471 2025-08-29 18:13:49 - pico-train - INFO - ├── Learning Rate: 1.42e-05 2025-08-29 18:13:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:14:01 - pico-train - INFO - Step 2300 -- 🔄 Training Metrics 2025-08-29 18:14:01 - pico-train - INFO - ├── Loss: 9.1305 2025-08-29 18:14:01 - pico-train - INFO - ├── Learning Rate: 1.44e-05 2025-08-29 18:14:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:14:14 - pico-train - INFO - Step 2325 -- 🔄 Training Metrics 2025-08-29 18:14:14 - pico-train - INFO - ├── Loss: 9.1430 2025-08-29 18:14:14 - pico-train - INFO - ├── Learning Rate: 1.45e-05 2025-08-29 18:14:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:14:26 - pico-train - INFO - Step 2350 -- 🔄 Training Metrics 2025-08-29 18:14:26 - pico-train - INFO - ├── Loss: 9.0948 2025-08-29 18:14:26 - pico-train - INFO - ├── Learning Rate: 1.47e-05 2025-08-29 18:14:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:14:39 - pico-train - INFO - Step 2375 -- 🔄 Training Metrics 2025-08-29 18:14:39 - pico-train - INFO - ├── Loss: 9.0256 2025-08-29 18:14:39 - pico-train - INFO - ├── Learning Rate: 1.48e-05 2025-08-29 18:14:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:14:52 - pico-train - INFO - Step 2400 -- 🔄 Training Metrics 2025-08-29 18:14:52 - pico-train - INFO - ├── Loss: 9.0664 2025-08-29 18:14:52 - pico-train - INFO - ├── Learning Rate: 1.50e-05 2025-08-29 18:14:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:15:04 - pico-train - INFO - Step 2425 -- 🔄 Training Metrics 2025-08-29 18:15:04 - pico-train - INFO - ├── Loss: 9.0020 2025-08-29 18:15:04 - pico-train - INFO - ├── Learning Rate: 1.52e-05 2025-08-29 18:15:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:15:17 - pico-train - INFO - Step 2450 -- 🔄 Training Metrics 2025-08-29 18:15:17 - pico-train - INFO - ├── Loss: 8.9518 2025-08-29 18:15:17 - pico-train - INFO - ├── Learning Rate: 1.53e-05 2025-08-29 18:15:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:15:29 - pico-train - INFO - Step 2475 -- 🔄 Training Metrics 2025-08-29 18:15:29 - pico-train - INFO - ├── Loss: 8.9717 2025-08-29 18:15:29 - pico-train - INFO - ├── Learning Rate: 1.55e-05 2025-08-29 18:15:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:15:41 - pico-train - INFO - Step 2500 -- 💾 Saving Checkpoint 2025-08-29 18:17:36 - pico-train - INFO - Step 2500 -- 📊 Evaluation Results 2025-08-29 18:17:36 - pico-train - INFO - └── paloma: 3.37924315167126e+18 2025-08-29 18:17:38 - pico-train - INFO - Step 2500 -- 🔄 Training Metrics 2025-08-29 18:17:38 - pico-train - INFO - ├── Loss: 8.9536 2025-08-29 18:17:38 - pico-train - INFO - ├── Learning Rate: 1.56e-05 2025-08-29 18:17:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:17:38 - pico-train - INFO - Step 2500 -- 📈 Saving Learning Dynamics 2025-08-29 18:17:52 - pico-train - INFO - Step 2525 -- 🔄 Training Metrics 2025-08-29 18:17:52 - pico-train - INFO - ├── Loss: 8.8812 2025-08-29 18:17:52 - pico-train - INFO - ├── Learning Rate: 1.58e-05 2025-08-29 18:17:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:18:05 - pico-train - INFO - Step 2550 -- 🔄 Training Metrics 2025-08-29 18:18:05 - pico-train - INFO - ├── Loss: 8.8824 2025-08-29 18:18:05 - pico-train - INFO - ├── Learning Rate: 1.59e-05 2025-08-29 18:18:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:18:17 - pico-train - INFO - Step 2575 -- 🔄 Training Metrics 2025-08-29 18:18:17 - pico-train - INFO - ├── Loss: 8.8564 2025-08-29 18:18:17 - pico-train - INFO - ├── Learning Rate: 1.61e-05 2025-08-29 18:18:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:18:30 - pico-train - INFO - Step 2600 -- 🔄 Training Metrics 2025-08-29 18:18:30 - pico-train - INFO - ├── Loss: 8.8419 2025-08-29 18:18:30 - pico-train - INFO - ├── Learning Rate: 1.63e-05 2025-08-29 18:18:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:18:43 - pico-train - INFO - Step 2625 -- 🔄 Training Metrics 2025-08-29 18:18:43 - pico-train - INFO - ├── Loss: 8.7865 2025-08-29 18:18:43 - pico-train - INFO - ├── Learning Rate: 1.64e-05 2025-08-29 18:18:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:18:55 - pico-train - INFO - Step 2650 -- 🔄 Training Metrics 2025-08-29 18:18:55 - pico-train - INFO - ├── Loss: 8.7493 2025-08-29 18:18:55 - pico-train - INFO - ├── Learning Rate: 1.66e-05 2025-08-29 18:18:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:19:08 - pico-train - INFO - Step 2675 -- 🔄 Training Metrics 2025-08-29 18:19:08 - pico-train - INFO - ├── Loss: 8.7255 2025-08-29 18:19:08 - pico-train - INFO - ├── Learning Rate: 1.67e-05 2025-08-29 18:19:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:19:20 - pico-train - INFO - Step 2700 -- 🔄 Training Metrics 2025-08-29 18:19:20 - pico-train - INFO - ├── Loss: 8.6469 2025-08-29 18:19:20 - pico-train - INFO - ├── Learning Rate: 1.69e-05 2025-08-29 18:19:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:19:33 - pico-train - INFO - Step 2725 -- 🔄 Training Metrics 2025-08-29 18:19:33 - pico-train - INFO - ├── Loss: 8.6799 2025-08-29 18:19:33 - pico-train - INFO - ├── Learning Rate: 1.70e-05 2025-08-29 18:19:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:19:45 - pico-train - INFO - Step 2750 -- 🔄 Training Metrics 2025-08-29 18:19:45 - pico-train - INFO - ├── Loss: 8.6974 2025-08-29 18:19:45 - pico-train - INFO - ├── Learning Rate: 1.72e-05 2025-08-29 18:19:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:19:58 - pico-train - INFO - Step 2775 -- 🔄 Training Metrics 2025-08-29 18:19:58 - pico-train - INFO - ├── Loss: 8.6441 2025-08-29 18:19:58 - pico-train - INFO - ├── Learning Rate: 1.73e-05 2025-08-29 18:19:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:20:10 - pico-train - INFO - Step 2800 -- 🔄 Training Metrics 2025-08-29 18:20:10 - pico-train - INFO - ├── Loss: 8.6689 2025-08-29 18:20:10 - pico-train - INFO - ├── Learning Rate: 1.75e-05 2025-08-29 18:20:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:20:23 - pico-train - INFO - Step 2825 -- 🔄 Training Metrics 2025-08-29 18:20:23 - pico-train - INFO - ├── Loss: 8.5732 2025-08-29 18:20:23 - pico-train - INFO - ├── Learning Rate: 1.77e-05 2025-08-29 18:20:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:20:35 - pico-train - INFO - Step 2850 -- 🔄 Training Metrics 2025-08-29 18:20:35 - pico-train - INFO - ├── Loss: 8.5955 2025-08-29 18:20:35 - pico-train - INFO - ├── Learning Rate: 1.78e-05 2025-08-29 18:20:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:20:48 - pico-train - INFO - Step 2875 -- 🔄 Training Metrics 2025-08-29 18:20:48 - pico-train - INFO - ├── Loss: 8.5823 2025-08-29 18:20:48 - pico-train - INFO - ├── Learning Rate: 1.80e-05 2025-08-29 18:20:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:21:00 - pico-train - INFO - Step 2900 -- 🔄 Training Metrics 2025-08-29 18:21:00 - pico-train - INFO - ├── Loss: 8.5968 2025-08-29 18:21:00 - pico-train - INFO - ├── Learning Rate: 1.81e-05 2025-08-29 18:21:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:21:13 - pico-train - INFO - Step 2925 -- 🔄 Training Metrics 2025-08-29 18:21:13 - pico-train - INFO - ├── Loss: 8.4721 2025-08-29 18:21:13 - pico-train - INFO - ├── Learning Rate: 1.83e-05 2025-08-29 18:21:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:21:26 - pico-train - INFO - Step 2950 -- 🔄 Training Metrics 2025-08-29 18:21:26 - pico-train - INFO - ├── Loss: 8.4672 2025-08-29 18:21:26 - pico-train - INFO - ├── Learning Rate: 1.84e-05 2025-08-29 18:21:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:21:38 - pico-train - INFO - Step 2975 -- 🔄 Training Metrics 2025-08-29 18:21:38 - pico-train - INFO - ├── Loss: 8.4033 2025-08-29 18:21:38 - pico-train - INFO - ├── Learning Rate: 1.86e-05 2025-08-29 18:21:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:21:50 - pico-train - INFO - Step 3000 -- 💾 Saving Checkpoint 2025-08-29 18:24:11 - pico-train - INFO - Step 3000 -- 📊 Evaluation Results 2025-08-29 18:24:11 - pico-train - INFO - └── paloma: 6.892747900243237e+18 2025-08-29 18:24:14 - pico-train - INFO - Step 3000 -- 🔄 Training Metrics 2025-08-29 18:24:14 - pico-train - INFO - ├── Loss: 8.4947 2025-08-29 18:24:14 - pico-train - INFO - ├── Learning Rate: 1.88e-05 2025-08-29 18:24:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:24:14 - pico-train - INFO - Step 3000 -- 📈 Saving Learning Dynamics 2025-08-29 18:24:28 - pico-train - INFO - Step 3025 -- 🔄 Training Metrics 2025-08-29 18:24:28 - pico-train - INFO - ├── Loss: 8.3780 2025-08-29 18:24:28 - pico-train - INFO - ├── Learning Rate: 1.89e-05 2025-08-29 18:24:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:24:41 - pico-train - INFO - Step 3050 -- 🔄 Training Metrics 2025-08-29 18:24:41 - pico-train - INFO - ├── Loss: 8.3581 2025-08-29 18:24:41 - pico-train - INFO - ├── Learning Rate: 1.91e-05 2025-08-29 18:24:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:24:54 - pico-train - INFO - Step 3075 -- 🔄 Training Metrics 2025-08-29 18:24:54 - pico-train - INFO - ├── Loss: 8.3341 2025-08-29 18:24:54 - pico-train - INFO - ├── Learning Rate: 1.92e-05 2025-08-29 18:24:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:25:06 - pico-train - INFO - Step 3100 -- 🔄 Training Metrics 2025-08-29 18:25:06 - pico-train - INFO - ├── Loss: 8.3391 2025-08-29 18:25:06 - pico-train - INFO - ├── Learning Rate: 1.94e-05 2025-08-29 18:25:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:25:19 - pico-train - INFO - Step 3125 -- 🔄 Training Metrics 2025-08-29 18:25:19 - pico-train - INFO - ├── Loss: 8.3670 2025-08-29 18:25:19 - pico-train - INFO - ├── Learning Rate: 1.95e-05 2025-08-29 18:25:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:25:32 - pico-train - INFO - Step 3150 -- 🔄 Training Metrics 2025-08-29 18:25:32 - pico-train - INFO - ├── Loss: 8.2370 2025-08-29 18:25:32 - pico-train - INFO - ├── Learning Rate: 1.97e-05 2025-08-29 18:25:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:25:44 - pico-train - INFO - Step 3175 -- 🔄 Training Metrics 2025-08-29 18:25:44 - pico-train - INFO - ├── Loss: 8.2879 2025-08-29 18:25:44 - pico-train - INFO - ├── Learning Rate: 1.98e-05 2025-08-29 18:25:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:25:57 - pico-train - INFO - Step 3200 -- 🔄 Training Metrics 2025-08-29 18:25:57 - pico-train - INFO - ├── Loss: 8.2706 2025-08-29 18:25:57 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-29 18:25:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:26:09 - pico-train - INFO - Step 3225 -- 🔄 Training Metrics 2025-08-29 18:26:09 - pico-train - INFO - ├── Loss: 8.1983 2025-08-29 18:26:09 - pico-train - INFO - ├── Learning Rate: 2.02e-05 2025-08-29 18:26:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:26:22 - pico-train - INFO - Step 3250 -- 🔄 Training Metrics 2025-08-29 18:26:22 - pico-train - INFO - ├── Loss: 8.2174 2025-08-29 18:26:22 - pico-train - INFO - ├── Learning Rate: 2.03e-05 2025-08-29 18:26:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:26:34 - pico-train - INFO - Step 3275 -- 🔄 Training Metrics 2025-08-29 18:26:34 - pico-train - INFO - ├── Loss: 8.2229 2025-08-29 18:26:34 - pico-train - INFO - ├── Learning Rate: 2.05e-05 2025-08-29 18:26:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:26:47 - pico-train - INFO - Step 3300 -- 🔄 Training Metrics 2025-08-29 18:26:47 - pico-train - INFO - ├── Loss: 8.1398 2025-08-29 18:26:47 - pico-train - INFO - ├── Learning Rate: 2.06e-05 2025-08-29 18:26:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:26:59 - pico-train - INFO - Step 3325 -- 🔄 Training Metrics 2025-08-29 18:26:59 - pico-train - INFO - ├── Loss: 8.1430 2025-08-29 18:26:59 - pico-train - INFO - ├── Learning Rate: 2.08e-05 2025-08-29 18:26:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:27:12 - pico-train - INFO - Step 3350 -- 🔄 Training Metrics 2025-08-29 18:27:12 - pico-train - INFO - ├── Loss: 8.1471 2025-08-29 18:27:12 - pico-train - INFO - ├── Learning Rate: 2.09e-05 2025-08-29 18:27:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:27:25 - pico-train - INFO - Step 3375 -- 🔄 Training Metrics 2025-08-29 18:27:25 - pico-train - INFO - ├── Loss: 8.0908 2025-08-29 18:27:25 - pico-train - INFO - ├── Learning Rate: 2.11e-05 2025-08-29 18:27:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:27:37 - pico-train - INFO - Step 3400 -- 🔄 Training Metrics 2025-08-29 18:27:37 - pico-train - INFO - ├── Loss: 8.1165 2025-08-29 18:27:37 - pico-train - INFO - ├── Learning Rate: 2.13e-05 2025-08-29 18:27:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:27:50 - pico-train - INFO - Step 3425 -- 🔄 Training Metrics 2025-08-29 18:27:50 - pico-train - INFO - ├── Loss: 8.0957 2025-08-29 18:27:50 - pico-train - INFO - ├── Learning Rate: 2.14e-05 2025-08-29 18:27:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:28:02 - pico-train - INFO - Step 3450 -- 🔄 Training Metrics 2025-08-29 18:28:02 - pico-train - INFO - ├── Loss: 8.1115 2025-08-29 18:28:02 - pico-train - INFO - ├── Learning Rate: 2.16e-05 2025-08-29 18:28:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:28:15 - pico-train - INFO - Step 3475 -- 🔄 Training Metrics 2025-08-29 18:28:15 - pico-train - INFO - ├── Loss: 8.0623 2025-08-29 18:28:15 - pico-train - INFO - ├── Learning Rate: 2.17e-05 2025-08-29 18:28:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:28:27 - pico-train - INFO - Step 3500 -- 💾 Saving Checkpoint 2025-08-29 18:30:20 - pico-train - INFO - Step 3500 -- 📊 Evaluation Results 2025-08-29 18:30:20 - pico-train - INFO - └── paloma: 2.0436832271954907e+19 2025-08-29 18:30:23 - pico-train - INFO - Step 3500 -- 🔄 Training Metrics 2025-08-29 18:30:23 - pico-train - INFO - ├── Loss: 8.0527 2025-08-29 18:30:23 - pico-train - INFO - ├── Learning Rate: 2.19e-05 2025-08-29 18:30:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:30:23 - pico-train - INFO - Step 3500 -- 📈 Saving Learning Dynamics 2025-08-29 18:30:37 - pico-train - INFO - Step 3525 -- 🔄 Training Metrics 2025-08-29 18:30:37 - pico-train - INFO - ├── Loss: 7.9975 2025-08-29 18:30:37 - pico-train - INFO - ├── Learning Rate: 2.20e-05 2025-08-29 18:30:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:30:50 - pico-train - INFO - Step 3550 -- 🔄 Training Metrics 2025-08-29 18:30:50 - pico-train - INFO - ├── Loss: 7.9881 2025-08-29 18:30:50 - pico-train - INFO - ├── Learning Rate: 2.22e-05 2025-08-29 18:30:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:31:03 - pico-train - INFO - Step 3575 -- 🔄 Training Metrics 2025-08-29 18:31:03 - pico-train - INFO - ├── Loss: 8.0060 2025-08-29 18:31:03 - pico-train - INFO - ├── Learning Rate: 2.23e-05 2025-08-29 18:31:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:31:15 - pico-train - INFO - Step 3600 -- 🔄 Training Metrics 2025-08-29 18:31:15 - pico-train - INFO - ├── Loss: 7.9366 2025-08-29 18:31:15 - pico-train - INFO - ├── Learning Rate: 2.25e-05 2025-08-29 18:31:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:31:28 - pico-train - INFO - Step 3625 -- 🔄 Training Metrics 2025-08-29 18:31:28 - pico-train - INFO - ├── Loss: 8.0252 2025-08-29 18:31:28 - pico-train - INFO - ├── Learning Rate: 2.27e-05 2025-08-29 18:31:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:31:40 - pico-train - INFO - Step 3650 -- 🔄 Training Metrics 2025-08-29 18:31:40 - pico-train - INFO - ├── Loss: 7.9160 2025-08-29 18:31:40 - pico-train - INFO - ├── Learning Rate: 2.28e-05 2025-08-29 18:31:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:31:53 - pico-train - INFO - Step 3675 -- 🔄 Training Metrics 2025-08-29 18:31:53 - pico-train - INFO - ├── Loss: 7.9470 2025-08-29 18:31:53 - pico-train - INFO - ├── Learning Rate: 2.30e-05 2025-08-29 18:31:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:32:05 - pico-train - INFO - Step 3700 -- 🔄 Training Metrics 2025-08-29 18:32:05 - pico-train - INFO - ├── Loss: 7.8943 2025-08-29 18:32:05 - pico-train - INFO - ├── Learning Rate: 2.31e-05 2025-08-29 18:32:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:32:18 - pico-train - INFO - Step 3725 -- 🔄 Training Metrics 2025-08-29 18:32:18 - pico-train - INFO - ├── Loss: 7.8951 2025-08-29 18:32:18 - pico-train - INFO - ├── Learning Rate: 2.33e-05 2025-08-29 18:32:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:32:31 - pico-train - INFO - Step 3750 -- 🔄 Training Metrics 2025-08-29 18:32:31 - pico-train - INFO - ├── Loss: 7.9316 2025-08-29 18:32:31 - pico-train - INFO - ├── Learning Rate: 2.34e-05 2025-08-29 18:32:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:32:43 - pico-train - INFO - Step 3775 -- 🔄 Training Metrics 2025-08-29 18:32:43 - pico-train - INFO - ├── Loss: 7.9407 2025-08-29 18:32:43 - pico-train - INFO - ├── Learning Rate: 2.36e-05 2025-08-29 18:32:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:32:56 - pico-train - INFO - Step 3800 -- 🔄 Training Metrics 2025-08-29 18:32:56 - pico-train - INFO - ├── Loss: 7.9385 2025-08-29 18:32:56 - pico-train - INFO - ├── Learning Rate: 2.38e-05 2025-08-29 18:32:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:33:08 - pico-train - INFO - Step 3825 -- 🔄 Training Metrics 2025-08-29 18:33:08 - pico-train - INFO - ├── Loss: 7.8800 2025-08-29 18:33:08 - pico-train - INFO - ├── Learning Rate: 2.39e-05 2025-08-29 18:33:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:33:21 - pico-train - INFO - Step 3850 -- 🔄 Training Metrics 2025-08-29 18:33:21 - pico-train - INFO - ├── Loss: 7.9207 2025-08-29 18:33:21 - pico-train - INFO - ├── Learning Rate: 2.41e-05 2025-08-29 18:33:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:33:33 - pico-train - INFO - Step 3875 -- 🔄 Training Metrics 2025-08-29 18:33:33 - pico-train - INFO - ├── Loss: 7.8258 2025-08-29 18:33:33 - pico-train - INFO - ├── Learning Rate: 2.42e-05 2025-08-29 18:33:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:33:46 - pico-train - INFO - Step 3900 -- 🔄 Training Metrics 2025-08-29 18:33:46 - pico-train - INFO - ├── Loss: 7.9005 2025-08-29 18:33:46 - pico-train - INFO - ├── Learning Rate: 2.44e-05 2025-08-29 18:33:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:33:59 - pico-train - INFO - Step 3925 -- 🔄 Training Metrics 2025-08-29 18:33:59 - pico-train - INFO - ├── Loss: 7.8232 2025-08-29 18:33:59 - pico-train - INFO - ├── Learning Rate: 2.45e-05 2025-08-29 18:33:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:34:11 - pico-train - INFO - Step 3950 -- 🔄 Training Metrics 2025-08-29 18:34:11 - pico-train - INFO - ├── Loss: 7.7847 2025-08-29 18:34:11 - pico-train - INFO - ├── Learning Rate: 2.47e-05 2025-08-29 18:34:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:34:24 - pico-train - INFO - Step 3975 -- 🔄 Training Metrics 2025-08-29 18:34:24 - pico-train - INFO - ├── Loss: 7.7909 2025-08-29 18:34:24 - pico-train - INFO - ├── Learning Rate: 2.48e-05 2025-08-29 18:34:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:34:36 - pico-train - INFO - Step 4000 -- 💾 Saving Checkpoint 2025-08-29 18:36:31 - pico-train - INFO - Step 4000 -- 📊 Evaluation Results 2025-08-29 18:36:31 - pico-train - INFO - └── paloma: 4.1410268232311005e+19 2025-08-29 18:36:34 - pico-train - INFO - Step 4000 -- 🔄 Training Metrics 2025-08-29 18:36:34 - pico-train - INFO - ├── Loss: 7.7419 2025-08-29 18:36:34 - pico-train - INFO - ├── Learning Rate: 2.50e-05 2025-08-29 18:36:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:36:34 - pico-train - INFO - Step 4000 -- 📈 Saving Learning Dynamics 2025-08-29 18:36:48 - pico-train - INFO - Step 4025 -- 🔄 Training Metrics 2025-08-29 18:36:48 - pico-train - INFO - ├── Loss: 7.8031 2025-08-29 18:36:48 - pico-train - INFO - ├── Learning Rate: 2.52e-05 2025-08-29 18:36:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:37:01 - pico-train - INFO - Step 4050 -- 🔄 Training Metrics 2025-08-29 18:37:01 - pico-train - INFO - ├── Loss: 7.7948 2025-08-29 18:37:01 - pico-train - INFO - ├── Learning Rate: 2.53e-05 2025-08-29 18:37:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:37:14 - pico-train - INFO - Step 4075 -- 🔄 Training Metrics 2025-08-29 18:37:14 - pico-train - INFO - ├── Loss: 7.7259 2025-08-29 18:37:14 - pico-train - INFO - ├── Learning Rate: 2.55e-05 2025-08-29 18:37:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:37:26 - pico-train - INFO - Step 4100 -- 🔄 Training Metrics 2025-08-29 18:37:26 - pico-train - INFO - ├── Loss: 7.8406 2025-08-29 18:37:26 - pico-train - INFO - ├── Learning Rate: 2.56e-05 2025-08-29 18:37:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:37:39 - pico-train - INFO - Step 4125 -- 🔄 Training Metrics 2025-08-29 18:37:39 - pico-train - INFO - ├── Loss: 7.7938 2025-08-29 18:37:39 - pico-train - INFO - ├── Learning Rate: 2.58e-05 2025-08-29 18:37:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:37:51 - pico-train - INFO - Step 4150 -- 🔄 Training Metrics 2025-08-29 18:37:51 - pico-train - INFO - ├── Loss: 7.7101 2025-08-29 18:37:51 - pico-train - INFO - ├── Learning Rate: 2.59e-05 2025-08-29 18:37:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:38:04 - pico-train - INFO - Step 4175 -- 🔄 Training Metrics 2025-08-29 18:38:04 - pico-train - INFO - ├── Loss: 7.6633 2025-08-29 18:38:04 - pico-train - INFO - ├── Learning Rate: 2.61e-05 2025-08-29 18:38:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:38:17 - pico-train - INFO - Step 4200 -- 🔄 Training Metrics 2025-08-29 18:38:17 - pico-train - INFO - ├── Loss: 7.6830 2025-08-29 18:38:17 - pico-train - INFO - ├── Learning Rate: 2.63e-05 2025-08-29 18:38:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:38:29 - pico-train - INFO - Step 4225 -- 🔄 Training Metrics 2025-08-29 18:38:29 - pico-train - INFO - ├── Loss: 7.7106 2025-08-29 18:38:29 - pico-train - INFO - ├── Learning Rate: 2.64e-05 2025-08-29 18:38:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:38:42 - pico-train - INFO - Step 4250 -- 🔄 Training Metrics 2025-08-29 18:38:42 - pico-train - INFO - ├── Loss: 7.7174 2025-08-29 18:38:42 - pico-train - INFO - ├── Learning Rate: 2.66e-05 2025-08-29 18:38:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:38:54 - pico-train - INFO - Step 4275 -- 🔄 Training Metrics 2025-08-29 18:38:54 - pico-train - INFO - ├── Loss: 7.7508 2025-08-29 18:38:54 - pico-train - INFO - ├── Learning Rate: 2.67e-05 2025-08-29 18:38:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:39:07 - pico-train - INFO - Step 4300 -- 🔄 Training Metrics 2025-08-29 18:39:07 - pico-train - INFO - ├── Loss: 7.6831 2025-08-29 18:39:07 - pico-train - INFO - ├── Learning Rate: 2.69e-05 2025-08-29 18:39:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:39:19 - pico-train - INFO - Step 4325 -- 🔄 Training Metrics 2025-08-29 18:39:19 - pico-train - INFO - ├── Loss: 7.6498 2025-08-29 18:39:19 - pico-train - INFO - ├── Learning Rate: 2.70e-05 2025-08-29 18:39:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:39:32 - pico-train - INFO - Step 4350 -- 🔄 Training Metrics 2025-08-29 18:39:32 - pico-train - INFO - ├── Loss: 7.6668 2025-08-29 18:39:32 - pico-train - INFO - ├── Learning Rate: 2.72e-05 2025-08-29 18:39:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:39:45 - pico-train - INFO - Step 4375 -- 🔄 Training Metrics 2025-08-29 18:39:45 - pico-train - INFO - ├── Loss: 7.6852 2025-08-29 18:39:45 - pico-train - INFO - ├── Learning Rate: 2.73e-05 2025-08-29 18:39:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:39:57 - pico-train - INFO - Step 4400 -- 🔄 Training Metrics 2025-08-29 18:39:57 - pico-train - INFO - ├── Loss: 7.6469 2025-08-29 18:39:57 - pico-train - INFO - ├── Learning Rate: 2.75e-05 2025-08-29 18:39:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:40:10 - pico-train - INFO - Step 4425 -- 🔄 Training Metrics 2025-08-29 18:40:10 - pico-train - INFO - ├── Loss: 7.7448 2025-08-29 18:40:10 - pico-train - INFO - ├── Learning Rate: 2.77e-05 2025-08-29 18:40:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:40:22 - pico-train - INFO - Step 4450 -- 🔄 Training Metrics 2025-08-29 18:40:22 - pico-train - INFO - ├── Loss: 7.7422 2025-08-29 18:40:22 - pico-train - INFO - ├── Learning Rate: 2.78e-05 2025-08-29 18:40:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:40:35 - pico-train - INFO - Step 4475 -- 🔄 Training Metrics 2025-08-29 18:40:35 - pico-train - INFO - ├── Loss: 7.6918 2025-08-29 18:40:35 - pico-train - INFO - ├── Learning Rate: 2.80e-05 2025-08-29 18:40:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:40:47 - pico-train - INFO - Step 4500 -- 💾 Saving Checkpoint 2025-08-29 18:42:40 - pico-train - INFO - Step 4500 -- 📊 Evaluation Results 2025-08-29 18:42:40 - pico-train - INFO - └── paloma: 3.4524340411684053e+19 2025-08-29 18:42:43 - pico-train - INFO - Step 4500 -- 🔄 Training Metrics 2025-08-29 18:42:43 - pico-train - INFO - ├── Loss: 7.7084 2025-08-29 18:42:43 - pico-train - INFO - ├── Learning Rate: 2.81e-05 2025-08-29 18:42:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:42:43 - pico-train - INFO - Step 4500 -- 📈 Saving Learning Dynamics 2025-08-29 18:42:57 - pico-train - INFO - Step 4525 -- 🔄 Training Metrics 2025-08-29 18:42:57 - pico-train - INFO - ├── Loss: 7.7220 2025-08-29 18:42:57 - pico-train - INFO - ├── Learning Rate: 2.83e-05 2025-08-29 18:42:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:43:10 - pico-train - INFO - Step 4550 -- 🔄 Training Metrics 2025-08-29 18:43:10 - pico-train - INFO - ├── Loss: 7.6893 2025-08-29 18:43:10 - pico-train - INFO - ├── Learning Rate: 2.84e-05 2025-08-29 18:43:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:43:22 - pico-train - INFO - Step 4575 -- 🔄 Training Metrics 2025-08-29 18:43:22 - pico-train - INFO - ├── Loss: 7.6454 2025-08-29 18:43:22 - pico-train - INFO - ├── Learning Rate: 2.86e-05 2025-08-29 18:43:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:43:35 - pico-train - INFO - Step 4600 -- 🔄 Training Metrics 2025-08-29 18:43:35 - pico-train - INFO - ├── Loss: 7.6298 2025-08-29 18:43:35 - pico-train - INFO - ├── Learning Rate: 2.87e-05 2025-08-29 18:43:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:43:48 - pico-train - INFO - Step 4625 -- 🔄 Training Metrics 2025-08-29 18:43:48 - pico-train - INFO - ├── Loss: 7.6420 2025-08-29 18:43:48 - pico-train - INFO - ├── Learning Rate: 2.89e-05 2025-08-29 18:43:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:44:00 - pico-train - INFO - Step 4650 -- 🔄 Training Metrics 2025-08-29 18:44:00 - pico-train - INFO - ├── Loss: 7.6247 2025-08-29 18:44:00 - pico-train - INFO - ├── Learning Rate: 2.91e-05 2025-08-29 18:44:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:44:13 - pico-train - INFO - Step 4675 -- 🔄 Training Metrics 2025-08-29 18:44:13 - pico-train - INFO - ├── Loss: 7.6448 2025-08-29 18:44:13 - pico-train - INFO - ├── Learning Rate: 2.92e-05 2025-08-29 18:44:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:44:25 - pico-train - INFO - Step 4700 -- 🔄 Training Metrics 2025-08-29 18:44:25 - pico-train - INFO - ├── Loss: 7.6506 2025-08-29 18:44:25 - pico-train - INFO - ├── Learning Rate: 2.94e-05 2025-08-29 18:44:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:44:38 - pico-train - INFO - Step 4725 -- 🔄 Training Metrics 2025-08-29 18:44:38 - pico-train - INFO - ├── Loss: 7.6356 2025-08-29 18:44:38 - pico-train - INFO - ├── Learning Rate: 2.95e-05 2025-08-29 18:44:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:44:51 - pico-train - INFO - Step 4750 -- 🔄 Training Metrics 2025-08-29 18:44:51 - pico-train - INFO - ├── Loss: 7.6426 2025-08-29 18:44:51 - pico-train - INFO - ├── Learning Rate: 2.97e-05 2025-08-29 18:44:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:45:03 - pico-train - INFO - Step 4775 -- 🔄 Training Metrics 2025-08-29 18:45:03 - pico-train - INFO - ├── Loss: 7.6388 2025-08-29 18:45:03 - pico-train - INFO - ├── Learning Rate: 2.98e-05 2025-08-29 18:45:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:45:16 - pico-train - INFO - Step 4800 -- 🔄 Training Metrics 2025-08-29 18:45:16 - pico-train - INFO - ├── Loss: 7.5216 2025-08-29 18:45:16 - pico-train - INFO - ├── Learning Rate: 3.00e-05 2025-08-29 18:45:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:45:28 - pico-train - INFO - Step 4825 -- 🔄 Training Metrics 2025-08-29 18:45:28 - pico-train - INFO - ├── Loss: 7.5367 2025-08-29 18:45:28 - pico-train - INFO - ├── Learning Rate: 3.02e-05 2025-08-29 18:45:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:45:41 - pico-train - INFO - Step 4850 -- 🔄 Training Metrics 2025-08-29 18:45:41 - pico-train - INFO - ├── Loss: 7.5084 2025-08-29 18:45:41 - pico-train - INFO - ├── Learning Rate: 3.03e-05 2025-08-29 18:45:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:45:54 - pico-train - INFO - Step 4875 -- 🔄 Training Metrics 2025-08-29 18:45:54 - pico-train - INFO - ├── Loss: 7.6092 2025-08-29 18:45:54 - pico-train - INFO - ├── Learning Rate: 3.05e-05 2025-08-29 18:45:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:46:06 - pico-train - INFO - Step 4900 -- 🔄 Training Metrics 2025-08-29 18:46:06 - pico-train - INFO - ├── Loss: 7.5760 2025-08-29 18:46:06 - pico-train - INFO - ├── Learning Rate: 3.06e-05 2025-08-29 18:46:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:46:19 - pico-train - INFO - Step 4925 -- 🔄 Training Metrics 2025-08-29 18:46:19 - pico-train - INFO - ├── Loss: 7.5686 2025-08-29 18:46:19 - pico-train - INFO - ├── Learning Rate: 3.08e-05 2025-08-29 18:46:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:46:31 - pico-train - INFO - Step 4950 -- 🔄 Training Metrics 2025-08-29 18:46:31 - pico-train - INFO - ├── Loss: 7.5583 2025-08-29 18:46:31 - pico-train - INFO - ├── Learning Rate: 3.09e-05 2025-08-29 18:46:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:46:44 - pico-train - INFO - Step 4975 -- 🔄 Training Metrics 2025-08-29 18:46:44 - pico-train - INFO - ├── Loss: 7.5818 2025-08-29 18:46:44 - pico-train - INFO - ├── Learning Rate: 3.11e-05 2025-08-29 18:46:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:46:56 - pico-train - INFO - Step 5000 -- 💾 Saving Checkpoint 2025-08-29 18:49:02 - pico-train - INFO - Step 5000 -- 📊 Evaluation Results 2025-08-29 18:49:02 - pico-train - INFO - └── paloma: 2.320698426399461e+19 2025-08-29 18:49:04 - pico-train - INFO - Step 5000 -- 🔄 Training Metrics 2025-08-29 18:49:04 - pico-train - INFO - ├── Loss: 7.6004 2025-08-29 18:49:04 - pico-train - INFO - ├── Learning Rate: 3.13e-05 2025-08-29 18:49:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:49:04 - pico-train - INFO - Step 5000 -- 📈 Saving Learning Dynamics 2025-08-29 18:49:18 - pico-train - INFO - Step 5025 -- 🔄 Training Metrics 2025-08-29 18:49:18 - pico-train - INFO - ├── Loss: 7.5371 2025-08-29 18:49:18 - pico-train - INFO - ├── Learning Rate: 3.14e-05 2025-08-29 18:49:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:49:31 - pico-train - INFO - Step 5050 -- 🔄 Training Metrics 2025-08-29 18:49:31 - pico-train - INFO - ├── Loss: 7.5179 2025-08-29 18:49:31 - pico-train - INFO - ├── Learning Rate: 3.16e-05 2025-08-29 18:49:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:49:44 - pico-train - INFO - Step 5075 -- 🔄 Training Metrics 2025-08-29 18:49:44 - pico-train - INFO - ├── Loss: 7.5255 2025-08-29 18:49:44 - pico-train - INFO - ├── Learning Rate: 3.17e-05 2025-08-29 18:49:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:49:56 - pico-train - INFO - Step 5100 -- 🔄 Training Metrics 2025-08-29 18:49:56 - pico-train - INFO - ├── Loss: 7.5155 2025-08-29 18:49:56 - pico-train - INFO - ├── Learning Rate: 3.19e-05 2025-08-29 18:49:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:50:10 - pico-train - INFO - Step 5125 -- 🔄 Training Metrics 2025-08-29 18:50:10 - pico-train - INFO - ├── Loss: 7.5660 2025-08-29 18:50:10 - pico-train - INFO - ├── Learning Rate: 3.20e-05 2025-08-29 18:50:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:50:22 - pico-train - INFO - Step 5150 -- 🔄 Training Metrics 2025-08-29 18:50:22 - pico-train - INFO - ├── Loss: 7.4797 2025-08-29 18:50:22 - pico-train - INFO - ├── Learning Rate: 3.22e-05 2025-08-29 18:50:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:50:35 - pico-train - INFO - Step 5175 -- 🔄 Training Metrics 2025-08-29 18:50:35 - pico-train - INFO - ├── Loss: 7.6224 2025-08-29 18:50:35 - pico-train - INFO - ├── Learning Rate: 3.23e-05 2025-08-29 18:50:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:50:48 - pico-train - INFO - Step 5200 -- 🔄 Training Metrics 2025-08-29 18:50:48 - pico-train - INFO - ├── Loss: 7.4821 2025-08-29 18:50:48 - pico-train - INFO - ├── Learning Rate: 3.25e-05 2025-08-29 18:50:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:51:00 - pico-train - INFO - Step 5225 -- 🔄 Training Metrics 2025-08-29 18:51:00 - pico-train - INFO - ├── Loss: 7.4765 2025-08-29 18:51:00 - pico-train - INFO - ├── Learning Rate: 3.27e-05 2025-08-29 18:51:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:51:13 - pico-train - INFO - Step 5250 -- 🔄 Training Metrics 2025-08-29 18:51:13 - pico-train - INFO - ├── Loss: 7.4680 2025-08-29 18:51:13 - pico-train - INFO - ├── Learning Rate: 3.28e-05 2025-08-29 18:51:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:51:26 - pico-train - INFO - Step 5275 -- 🔄 Training Metrics 2025-08-29 18:51:26 - pico-train - INFO - ├── Loss: 7.5165 2025-08-29 18:51:26 - pico-train - INFO - ├── Learning Rate: 3.30e-05 2025-08-29 18:51:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:51:38 - pico-train - INFO - Step 5300 -- 🔄 Training Metrics 2025-08-29 18:51:38 - pico-train - INFO - ├── Loss: 7.5334 2025-08-29 18:51:38 - pico-train - INFO - ├── Learning Rate: 3.31e-05 2025-08-29 18:51:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:51:51 - pico-train - INFO - Step 5325 -- 🔄 Training Metrics 2025-08-29 18:51:51 - pico-train - INFO - ├── Loss: 7.5053 2025-08-29 18:51:51 - pico-train - INFO - ├── Learning Rate: 3.33e-05 2025-08-29 18:51:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:52:04 - pico-train - INFO - Step 5350 -- 🔄 Training Metrics 2025-08-29 18:52:04 - pico-train - INFO - ├── Loss: 7.5115 2025-08-29 18:52:04 - pico-train - INFO - ├── Learning Rate: 3.34e-05 2025-08-29 18:52:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:52:16 - pico-train - INFO - Step 5375 -- 🔄 Training Metrics 2025-08-29 18:52:16 - pico-train - INFO - ├── Loss: 7.4736 2025-08-29 18:52:16 - pico-train - INFO - ├── Learning Rate: 3.36e-05 2025-08-29 18:52:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:52:29 - pico-train - INFO - Step 5400 -- 🔄 Training Metrics 2025-08-29 18:52:29 - pico-train - INFO - ├── Loss: 7.4520 2025-08-29 18:52:29 - pico-train - INFO - ├── Learning Rate: 3.38e-05 2025-08-29 18:52:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:52:41 - pico-train - INFO - Step 5425 -- 🔄 Training Metrics 2025-08-29 18:52:41 - pico-train - INFO - ├── Loss: 7.4596 2025-08-29 18:52:41 - pico-train - INFO - ├── Learning Rate: 3.39e-05 2025-08-29 18:52:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:52:54 - pico-train - INFO - Step 5450 -- 🔄 Training Metrics 2025-08-29 18:52:54 - pico-train - INFO - ├── Loss: 7.4518 2025-08-29 18:52:54 - pico-train - INFO - ├── Learning Rate: 3.41e-05 2025-08-29 18:52:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:53:06 - pico-train - INFO - Step 5475 -- 🔄 Training Metrics 2025-08-29 18:53:06 - pico-train - INFO - ├── Loss: 7.4308 2025-08-29 18:53:06 - pico-train - INFO - ├── Learning Rate: 3.42e-05 2025-08-29 18:53:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:53:18 - pico-train - INFO - Step 5500 -- 💾 Saving Checkpoint 2025-08-29 18:55:23 - pico-train - INFO - Step 5500 -- 📊 Evaluation Results 2025-08-29 18:55:23 - pico-train - INFO - └── paloma: 3.1834097890526753e+19 2025-08-29 18:55:25 - pico-train - INFO - Step 5500 -- 🔄 Training Metrics 2025-08-29 18:55:25 - pico-train - INFO - ├── Loss: 7.4627 2025-08-29 18:55:25 - pico-train - INFO - ├── Learning Rate: 3.44e-05 2025-08-29 18:55:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:55:25 - pico-train - INFO - Step 5500 -- 📈 Saving Learning Dynamics 2025-08-29 18:55:39 - pico-train - INFO - Step 5525 -- 🔄 Training Metrics 2025-08-29 18:55:39 - pico-train - INFO - ├── Loss: 7.4095 2025-08-29 18:55:39 - pico-train - INFO - ├── Learning Rate: 3.45e-05 2025-08-29 18:55:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:55:52 - pico-train - INFO - Step 5550 -- 🔄 Training Metrics 2025-08-29 18:55:52 - pico-train - INFO - ├── Loss: 7.4423 2025-08-29 18:55:52 - pico-train - INFO - ├── Learning Rate: 3.47e-05 2025-08-29 18:55:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:56:04 - pico-train - INFO - Step 5575 -- 🔄 Training Metrics 2025-08-29 18:56:04 - pico-train - INFO - ├── Loss: 7.4600 2025-08-29 18:56:04 - pico-train - INFO - ├── Learning Rate: 3.48e-05 2025-08-29 18:56:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:56:17 - pico-train - INFO - Step 5600 -- 🔄 Training Metrics 2025-08-29 18:56:17 - pico-train - INFO - ├── Loss: 7.3457 2025-08-29 18:56:17 - pico-train - INFO - ├── Learning Rate: 3.50e-05 2025-08-29 18:56:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:56:31 - pico-train - INFO - Step 5625 -- 🔄 Training Metrics 2025-08-29 18:56:31 - pico-train - INFO - ├── Loss: 7.4838 2025-08-29 18:56:31 - pico-train - INFO - ├── Learning Rate: 3.52e-05 2025-08-29 18:56:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:56:43 - pico-train - INFO - Step 5650 -- 🔄 Training Metrics 2025-08-29 18:56:43 - pico-train - INFO - ├── Loss: 7.4556 2025-08-29 18:56:43 - pico-train - INFO - ├── Learning Rate: 3.53e-05 2025-08-29 18:56:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:56:56 - pico-train - INFO - Step 5675 -- 🔄 Training Metrics 2025-08-29 18:56:56 - pico-train - INFO - ├── Loss: 7.4220 2025-08-29 18:56:56 - pico-train - INFO - ├── Learning Rate: 3.55e-05 2025-08-29 18:56:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:57:09 - pico-train - INFO - Step 5700 -- 🔄 Training Metrics 2025-08-29 18:57:09 - pico-train - INFO - ├── Loss: 7.4307 2025-08-29 18:57:09 - pico-train - INFO - ├── Learning Rate: 3.56e-05 2025-08-29 18:57:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:57:21 - pico-train - INFO - Step 5725 -- 🔄 Training Metrics 2025-08-29 18:57:21 - pico-train - INFO - ├── Loss: 7.3795 2025-08-29 18:57:21 - pico-train - INFO - ├── Learning Rate: 3.58e-05 2025-08-29 18:57:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:57:34 - pico-train - INFO - Step 5750 -- 🔄 Training Metrics 2025-08-29 18:57:34 - pico-train - INFO - ├── Loss: 7.3855 2025-08-29 18:57:34 - pico-train - INFO - ├── Learning Rate: 3.59e-05 2025-08-29 18:57:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:57:47 - pico-train - INFO - Step 5775 -- 🔄 Training Metrics 2025-08-29 18:57:47 - pico-train - INFO - ├── Loss: 7.3518 2025-08-29 18:57:47 - pico-train - INFO - ├── Learning Rate: 3.61e-05 2025-08-29 18:57:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:57:59 - pico-train - INFO - Step 5800 -- 🔄 Training Metrics 2025-08-29 18:57:59 - pico-train - INFO - ├── Loss: 7.3794 2025-08-29 18:57:59 - pico-train - INFO - ├── Learning Rate: 3.63e-05 2025-08-29 18:57:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:58:12 - pico-train - INFO - Step 5825 -- 🔄 Training Metrics 2025-08-29 18:58:12 - pico-train - INFO - ├── Loss: 7.3591 2025-08-29 18:58:12 - pico-train - INFO - ├── Learning Rate: 3.64e-05 2025-08-29 18:58:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:58:24 - pico-train - INFO - Step 5850 -- 🔄 Training Metrics 2025-08-29 18:58:24 - pico-train - INFO - ├── Loss: 7.3489 2025-08-29 18:58:24 - pico-train - INFO - ├── Learning Rate: 3.66e-05 2025-08-29 18:58:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:58:37 - pico-train - INFO - Step 5875 -- 🔄 Training Metrics 2025-08-29 18:58:37 - pico-train - INFO - ├── Loss: 7.4108 2025-08-29 18:58:37 - pico-train - INFO - ├── Learning Rate: 3.67e-05 2025-08-29 18:58:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:58:50 - pico-train - INFO - Step 5900 -- 🔄 Training Metrics 2025-08-29 18:58:50 - pico-train - INFO - ├── Loss: 7.3580 2025-08-29 18:58:50 - pico-train - INFO - ├── Learning Rate: 3.69e-05 2025-08-29 18:58:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:59:02 - pico-train - INFO - Step 5925 -- 🔄 Training Metrics 2025-08-29 18:59:02 - pico-train - INFO - ├── Loss: 7.3131 2025-08-29 18:59:02 - pico-train - INFO - ├── Learning Rate: 3.70e-05 2025-08-29 18:59:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:59:15 - pico-train - INFO - Step 5950 -- 🔄 Training Metrics 2025-08-29 18:59:15 - pico-train - INFO - ├── Loss: 7.2905 2025-08-29 18:59:15 - pico-train - INFO - ├── Learning Rate: 3.72e-05 2025-08-29 18:59:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:59:27 - pico-train - INFO - Step 5975 -- 🔄 Training Metrics 2025-08-29 18:59:27 - pico-train - INFO - ├── Loss: 7.3466 2025-08-29 18:59:27 - pico-train - INFO - ├── Learning Rate: 3.73e-05 2025-08-29 18:59:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 18:59:40 - pico-train - INFO - Step 6000 -- 💾 Saving Checkpoint 2025-08-29 19:01:34 - pico-train - INFO - Step 6000 -- 📊 Evaluation Results 2025-08-29 19:01:34 - pico-train - INFO - └── paloma: 4.457139025979801e+19 2025-08-29 19:01:35 - pico-train - INFO - Step 6000 -- 🔄 Training Metrics 2025-08-29 19:01:35 - pico-train - INFO - ├── Loss: 7.3765 2025-08-29 19:01:35 - pico-train - INFO - ├── Learning Rate: 3.75e-05 2025-08-29 19:01:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:01:35 - pico-train - INFO - Step 6000 -- 📈 Saving Learning Dynamics 2025-08-29 19:01:49 - pico-train - INFO - Step 6025 -- 🔄 Training Metrics 2025-08-29 19:01:49 - pico-train - INFO - ├── Loss: 7.2870 2025-08-29 19:01:49 - pico-train - INFO - ├── Learning Rate: 3.77e-05 2025-08-29 19:01:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:02:02 - pico-train - INFO - Step 6050 -- 🔄 Training Metrics 2025-08-29 19:02:02 - pico-train - INFO - ├── Loss: 7.3333 2025-08-29 19:02:02 - pico-train - INFO - ├── Learning Rate: 3.78e-05 2025-08-29 19:02:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:02:14 - pico-train - INFO - Step 6075 -- 🔄 Training Metrics 2025-08-29 19:02:14 - pico-train - INFO - ├── Loss: 7.3098 2025-08-29 19:02:14 - pico-train - INFO - ├── Learning Rate: 3.80e-05 2025-08-29 19:02:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:02:27 - pico-train - INFO - Step 6100 -- 🔄 Training Metrics 2025-08-29 19:02:27 - pico-train - INFO - ├── Loss: 7.2594 2025-08-29 19:02:27 - pico-train - INFO - ├── Learning Rate: 3.81e-05 2025-08-29 19:02:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:02:40 - pico-train - INFO - Step 6125 -- 🔄 Training Metrics 2025-08-29 19:02:40 - pico-train - INFO - ├── Loss: 7.3327 2025-08-29 19:02:40 - pico-train - INFO - ├── Learning Rate: 3.83e-05 2025-08-29 19:02:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:02:53 - pico-train - INFO - Step 6150 -- 🔄 Training Metrics 2025-08-29 19:02:53 - pico-train - INFO - ├── Loss: 7.3030 2025-08-29 19:02:53 - pico-train - INFO - ├── Learning Rate: 3.84e-05 2025-08-29 19:02:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:03:05 - pico-train - INFO - Step 6175 -- 🔄 Training Metrics 2025-08-29 19:03:05 - pico-train - INFO - ├── Loss: 7.2523 2025-08-29 19:03:05 - pico-train - INFO - ├── Learning Rate: 3.86e-05 2025-08-29 19:03:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:03:18 - pico-train - INFO - Step 6200 -- 🔄 Training Metrics 2025-08-29 19:03:18 - pico-train - INFO - ├── Loss: 7.2546 2025-08-29 19:03:18 - pico-train - INFO - ├── Learning Rate: 3.87e-05 2025-08-29 19:03:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:03:30 - pico-train - INFO - Step 6225 -- 🔄 Training Metrics 2025-08-29 19:03:30 - pico-train - INFO - ├── Loss: 7.3242 2025-08-29 19:03:30 - pico-train - INFO - ├── Learning Rate: 3.89e-05 2025-08-29 19:03:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:03:43 - pico-train - INFO - Step 6250 -- 🔄 Training Metrics 2025-08-29 19:03:43 - pico-train - INFO - ├── Loss: 7.2035 2025-08-29 19:03:43 - pico-train - INFO - ├── Learning Rate: 3.91e-05 2025-08-29 19:03:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:03:56 - pico-train - INFO - Step 6275 -- 🔄 Training Metrics 2025-08-29 19:03:56 - pico-train - INFO - ├── Loss: 7.2334 2025-08-29 19:03:56 - pico-train - INFO - ├── Learning Rate: 3.92e-05 2025-08-29 19:03:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:04:08 - pico-train - INFO - Step 6300 -- 🔄 Training Metrics 2025-08-29 19:04:08 - pico-train - INFO - ├── Loss: 7.2295 2025-08-29 19:04:08 - pico-train - INFO - ├── Learning Rate: 3.94e-05 2025-08-29 19:04:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:04:21 - pico-train - INFO - Step 6325 -- 🔄 Training Metrics 2025-08-29 19:04:21 - pico-train - INFO - ├── Loss: 7.3051 2025-08-29 19:04:21 - pico-train - INFO - ├── Learning Rate: 3.95e-05 2025-08-29 19:04:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:04:34 - pico-train - INFO - Step 6350 -- 🔄 Training Metrics 2025-08-29 19:04:34 - pico-train - INFO - ├── Loss: 7.3188 2025-08-29 19:04:34 - pico-train - INFO - ├── Learning Rate: 3.97e-05 2025-08-29 19:04:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:04:46 - pico-train - INFO - Step 6375 -- 🔄 Training Metrics 2025-08-29 19:04:46 - pico-train - INFO - ├── Loss: 7.3212 2025-08-29 19:04:46 - pico-train - INFO - ├── Learning Rate: 3.98e-05 2025-08-29 19:04:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:04:59 - pico-train - INFO - Step 6400 -- 🔄 Training Metrics 2025-08-29 19:04:59 - pico-train - INFO - ├── Loss: 7.2465 2025-08-29 19:04:59 - pico-train - INFO - ├── Learning Rate: 4.00e-05 2025-08-29 19:04:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:05:12 - pico-train - INFO - Step 6425 -- 🔄 Training Metrics 2025-08-29 19:05:12 - pico-train - INFO - ├── Loss: 7.2081 2025-08-29 19:05:12 - pico-train - INFO - ├── Learning Rate: 4.02e-05 2025-08-29 19:05:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:05:24 - pico-train - INFO - Step 6450 -- 🔄 Training Metrics 2025-08-29 19:05:24 - pico-train - INFO - ├── Loss: 7.2852 2025-08-29 19:05:24 - pico-train - INFO - ├── Learning Rate: 4.03e-05 2025-08-29 19:05:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:05:37 - pico-train - INFO - Step 6475 -- 🔄 Training Metrics 2025-08-29 19:05:37 - pico-train - INFO - ├── Loss: 7.2074 2025-08-29 19:05:37 - pico-train - INFO - ├── Learning Rate: 4.05e-05 2025-08-29 19:05:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:05:49 - pico-train - INFO - Step 6500 -- 💾 Saving Checkpoint 2025-08-29 19:07:49 - pico-train - INFO - Step 6500 -- 📊 Evaluation Results 2025-08-29 19:07:49 - pico-train - INFO - └── paloma: 7.3062353841856406e+19 2025-08-29 19:07:50 - pico-train - INFO - Step 6500 -- 🔄 Training Metrics 2025-08-29 19:07:50 - pico-train - INFO - ├── Loss: 7.2520 2025-08-29 19:07:50 - pico-train - INFO - ├── Learning Rate: 4.06e-05 2025-08-29 19:07:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:07:50 - pico-train - INFO - Step 6500 -- 📈 Saving Learning Dynamics 2025-08-29 19:08:05 - pico-train - INFO - Step 6525 -- 🔄 Training Metrics 2025-08-29 19:08:05 - pico-train - INFO - ├── Loss: 7.2115 2025-08-29 19:08:05 - pico-train - INFO - ├── Learning Rate: 4.08e-05 2025-08-29 19:08:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:08:18 - pico-train - INFO - Step 6550 -- 🔄 Training Metrics 2025-08-29 19:08:18 - pico-train - INFO - ├── Loss: 7.2435 2025-08-29 19:08:18 - pico-train - INFO - ├── Learning Rate: 4.09e-05 2025-08-29 19:08:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:08:30 - pico-train - INFO - Step 6575 -- 🔄 Training Metrics 2025-08-29 19:08:30 - pico-train - INFO - ├── Loss: 7.1962 2025-08-29 19:08:30 - pico-train - INFO - ├── Learning Rate: 4.11e-05 2025-08-29 19:08:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:08:43 - pico-train - INFO - Step 6600 -- 🔄 Training Metrics 2025-08-29 19:08:43 - pico-train - INFO - ├── Loss: 7.1631 2025-08-29 19:08:43 - pico-train - INFO - ├── Learning Rate: 4.12e-05 2025-08-29 19:08:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:08:56 - pico-train - INFO - Step 6625 -- 🔄 Training Metrics 2025-08-29 19:08:56 - pico-train - INFO - ├── Loss: 7.2525 2025-08-29 19:08:56 - pico-train - INFO - ├── Learning Rate: 4.14e-05 2025-08-29 19:08:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:09:09 - pico-train - INFO - Step 6650 -- 🔄 Training Metrics 2025-08-29 19:09:09 - pico-train - INFO - ├── Loss: 7.2133 2025-08-29 19:09:09 - pico-train - INFO - ├── Learning Rate: 4.16e-05 2025-08-29 19:09:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:09:21 - pico-train - INFO - Step 6675 -- 🔄 Training Metrics 2025-08-29 19:09:21 - pico-train - INFO - ├── Loss: 7.2248 2025-08-29 19:09:21 - pico-train - INFO - ├── Learning Rate: 4.17e-05 2025-08-29 19:09:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:09:34 - pico-train - INFO - Step 6700 -- 🔄 Training Metrics 2025-08-29 19:09:34 - pico-train - INFO - ├── Loss: 7.1928 2025-08-29 19:09:34 - pico-train - INFO - ├── Learning Rate: 4.19e-05 2025-08-29 19:09:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:09:46 - pico-train - INFO - Step 6725 -- 🔄 Training Metrics 2025-08-29 19:09:46 - pico-train - INFO - ├── Loss: 7.1698 2025-08-29 19:09:46 - pico-train - INFO - ├── Learning Rate: 4.20e-05 2025-08-29 19:09:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:09:59 - pico-train - INFO - Step 6750 -- 🔄 Training Metrics 2025-08-29 19:09:59 - pico-train - INFO - ├── Loss: 7.3037 2025-08-29 19:09:59 - pico-train - INFO - ├── Learning Rate: 4.22e-05 2025-08-29 19:09:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:10:11 - pico-train - INFO - Step 6775 -- 🔄 Training Metrics 2025-08-29 19:10:11 - pico-train - INFO - ├── Loss: 7.2451 2025-08-29 19:10:11 - pico-train - INFO - ├── Learning Rate: 4.23e-05 2025-08-29 19:10:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:10:24 - pico-train - INFO - Step 6800 -- 🔄 Training Metrics 2025-08-29 19:10:24 - pico-train - INFO - ├── Loss: 7.1373 2025-08-29 19:10:24 - pico-train - INFO - ├── Learning Rate: 4.25e-05 2025-08-29 19:10:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:10:37 - pico-train - INFO - Step 6825 -- 🔄 Training Metrics 2025-08-29 19:10:37 - pico-train - INFO - ├── Loss: 7.1390 2025-08-29 19:10:37 - pico-train - INFO - ├── Learning Rate: 4.27e-05 2025-08-29 19:10:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:10:49 - pico-train - INFO - Step 6850 -- 🔄 Training Metrics 2025-08-29 19:10:49 - pico-train - INFO - ├── Loss: 7.1296 2025-08-29 19:10:49 - pico-train - INFO - ├── Learning Rate: 4.28e-05 2025-08-29 19:10:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:11:02 - pico-train - INFO - Step 6875 -- 🔄 Training Metrics 2025-08-29 19:11:02 - pico-train - INFO - ├── Loss: 7.0961 2025-08-29 19:11:02 - pico-train - INFO - ├── Learning Rate: 4.30e-05 2025-08-29 19:11:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:11:14 - pico-train - INFO - Step 6900 -- 🔄 Training Metrics 2025-08-29 19:11:14 - pico-train - INFO - ├── Loss: 7.1408 2025-08-29 19:11:14 - pico-train - INFO - ├── Learning Rate: 4.31e-05 2025-08-29 19:11:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:11:27 - pico-train - INFO - Step 6925 -- 🔄 Training Metrics 2025-08-29 19:11:27 - pico-train - INFO - ├── Loss: 7.1852 2025-08-29 19:11:27 - pico-train - INFO - ├── Learning Rate: 4.33e-05 2025-08-29 19:11:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:11:39 - pico-train - INFO - Step 6950 -- 🔄 Training Metrics 2025-08-29 19:11:39 - pico-train - INFO - ├── Loss: 7.2067 2025-08-29 19:11:39 - pico-train - INFO - ├── Learning Rate: 4.34e-05 2025-08-29 19:11:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:11:52 - pico-train - INFO - Step 6975 -- 🔄 Training Metrics 2025-08-29 19:11:52 - pico-train - INFO - ├── Loss: 7.0681 2025-08-29 19:11:52 - pico-train - INFO - ├── Learning Rate: 4.36e-05 2025-08-29 19:11:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:12:04 - pico-train - INFO - Step 7000 -- 💾 Saving Checkpoint 2025-08-29 19:14:06 - pico-train - INFO - Step 7000 -- 📊 Evaluation Results 2025-08-29 19:14:06 - pico-train - INFO - └── paloma: 1.2357969480287024e+20 2025-08-29 19:14:08 - pico-train - INFO - Step 7000 -- 🔄 Training Metrics 2025-08-29 19:14:08 - pico-train - INFO - ├── Loss: 7.1813 2025-08-29 19:14:08 - pico-train - INFO - ├── Learning Rate: 4.37e-05 2025-08-29 19:14:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:14:08 - pico-train - INFO - Step 7000 -- 📈 Saving Learning Dynamics 2025-08-29 19:14:22 - pico-train - INFO - Step 7025 -- 🔄 Training Metrics 2025-08-29 19:14:22 - pico-train - INFO - ├── Loss: 7.1992 2025-08-29 19:14:22 - pico-train - INFO - ├── Learning Rate: 4.39e-05 2025-08-29 19:14:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:14:34 - pico-train - INFO - Step 7050 -- 🔄 Training Metrics 2025-08-29 19:14:34 - pico-train - INFO - ├── Loss: 7.1409 2025-08-29 19:14:34 - pico-train - INFO - ├── Learning Rate: 4.41e-05 2025-08-29 19:14:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:14:47 - pico-train - INFO - Step 7075 -- 🔄 Training Metrics 2025-08-29 19:14:47 - pico-train - INFO - ├── Loss: 7.1271 2025-08-29 19:14:47 - pico-train - INFO - ├── Learning Rate: 4.42e-05 2025-08-29 19:14:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:15:00 - pico-train - INFO - Step 7100 -- 🔄 Training Metrics 2025-08-29 19:15:00 - pico-train - INFO - ├── Loss: 7.1720 2025-08-29 19:15:00 - pico-train - INFO - ├── Learning Rate: 4.44e-05 2025-08-29 19:15:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:15:17 - pico-train - INFO - Step 7125 -- 🔄 Training Metrics 2025-08-29 19:15:17 - pico-train - INFO - ├── Loss: 7.1515 2025-08-29 19:15:17 - pico-train - INFO - ├── Learning Rate: 4.45e-05 2025-08-29 19:15:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:15:30 - pico-train - INFO - Step 7150 -- 🔄 Training Metrics 2025-08-29 19:15:30 - pico-train - INFO - ├── Loss: 7.0898 2025-08-29 19:15:30 - pico-train - INFO - ├── Learning Rate: 4.47e-05 2025-08-29 19:15:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:15:42 - pico-train - INFO - Step 7175 -- 🔄 Training Metrics 2025-08-29 19:15:42 - pico-train - INFO - ├── Loss: 7.0996 2025-08-29 19:15:42 - pico-train - INFO - ├── Learning Rate: 4.48e-05 2025-08-29 19:15:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:15:55 - pico-train - INFO - Step 7200 -- 🔄 Training Metrics 2025-08-29 19:15:55 - pico-train - INFO - ├── Loss: 7.0610 2025-08-29 19:15:55 - pico-train - INFO - ├── Learning Rate: 4.50e-05 2025-08-29 19:15:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:16:07 - pico-train - INFO - Step 7225 -- 🔄 Training Metrics 2025-08-29 19:16:07 - pico-train - INFO - ├── Loss: 7.1939 2025-08-29 19:16:07 - pico-train - INFO - ├── Learning Rate: 4.52e-05 2025-08-29 19:16:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:16:20 - pico-train - INFO - Step 7250 -- 🔄 Training Metrics 2025-08-29 19:16:20 - pico-train - INFO - ├── Loss: 7.0355 2025-08-29 19:16:20 - pico-train - INFO - ├── Learning Rate: 4.53e-05 2025-08-29 19:16:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:16:32 - pico-train - INFO - Step 7275 -- 🔄 Training Metrics 2025-08-29 19:16:32 - pico-train - INFO - ├── Loss: 7.0935 2025-08-29 19:16:32 - pico-train - INFO - ├── Learning Rate: 4.55e-05 2025-08-29 19:16:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:16:45 - pico-train - INFO - Step 7300 -- 🔄 Training Metrics 2025-08-29 19:16:45 - pico-train - INFO - ├── Loss: 7.0689 2025-08-29 19:16:45 - pico-train - INFO - ├── Learning Rate: 4.56e-05 2025-08-29 19:16:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:16:57 - pico-train - INFO - Step 7325 -- 🔄 Training Metrics 2025-08-29 19:16:57 - pico-train - INFO - ├── Loss: 7.0265 2025-08-29 19:16:57 - pico-train - INFO - ├── Learning Rate: 4.58e-05 2025-08-29 19:16:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:17:10 - pico-train - INFO - Step 7350 -- 🔄 Training Metrics 2025-08-29 19:17:10 - pico-train - INFO - ├── Loss: 7.0963 2025-08-29 19:17:10 - pico-train - INFO - ├── Learning Rate: 4.59e-05 2025-08-29 19:17:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:17:23 - pico-train - INFO - Step 7375 -- 🔄 Training Metrics 2025-08-29 19:17:23 - pico-train - INFO - ├── Loss: 7.1138 2025-08-29 19:17:23 - pico-train - INFO - ├── Learning Rate: 4.61e-05 2025-08-29 19:17:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:17:35 - pico-train - INFO - Step 7400 -- 🔄 Training Metrics 2025-08-29 19:17:35 - pico-train - INFO - ├── Loss: 7.0414 2025-08-29 19:17:35 - pico-train - INFO - ├── Learning Rate: 4.63e-05 2025-08-29 19:17:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:17:48 - pico-train - INFO - Step 7425 -- 🔄 Training Metrics 2025-08-29 19:17:48 - pico-train - INFO - ├── Loss: 7.0753 2025-08-29 19:17:48 - pico-train - INFO - ├── Learning Rate: 4.64e-05 2025-08-29 19:17:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:18:00 - pico-train - INFO - Step 7450 -- 🔄 Training Metrics 2025-08-29 19:18:00 - pico-train - INFO - ├── Loss: 7.0603 2025-08-29 19:18:00 - pico-train - INFO - ├── Learning Rate: 4.66e-05 2025-08-29 19:18:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:18:13 - pico-train - INFO - Step 7475 -- 🔄 Training Metrics 2025-08-29 19:18:13 - pico-train - INFO - ├── Loss: 7.0818 2025-08-29 19:18:13 - pico-train - INFO - ├── Learning Rate: 4.67e-05 2025-08-29 19:18:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:18:25 - pico-train - INFO - Step 7500 -- 💾 Saving Checkpoint 2025-08-29 19:21:05 - pico-train - INFO - Step 7500 -- 📊 Evaluation Results 2025-08-29 19:21:05 - pico-train - INFO - └── paloma: 2.7199371732053928e+20 2025-08-29 19:21:07 - pico-train - INFO - Step 7500 -- 🔄 Training Metrics 2025-08-29 19:21:07 - pico-train - INFO - ├── Loss: 7.0788 2025-08-29 19:21:07 - pico-train - INFO - ├── Learning Rate: 4.69e-05 2025-08-29 19:21:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:21:07 - pico-train - INFO - Step 7500 -- 📈 Saving Learning Dynamics 2025-08-29 19:21:42 - pico-train - INFO - Step 7525 -- 🔄 Training Metrics 2025-08-29 19:21:42 - pico-train - INFO - ├── Loss: 6.9952 2025-08-29 19:21:42 - pico-train - INFO - ├── Learning Rate: 4.70e-05 2025-08-29 19:21:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:22:00 - pico-train - INFO - Step 7550 -- 🔄 Training Metrics 2025-08-29 19:22:00 - pico-train - INFO - ├── Loss: 7.0114 2025-08-29 19:22:00 - pico-train - INFO - ├── Learning Rate: 4.72e-05 2025-08-29 19:22:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:22:12 - pico-train - INFO - Step 7575 -- 🔄 Training Metrics 2025-08-29 19:22:12 - pico-train - INFO - ├── Loss: 7.0611 2025-08-29 19:22:12 - pico-train - INFO - ├── Learning Rate: 4.73e-05 2025-08-29 19:22:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:22:25 - pico-train - INFO - Step 7600 -- 🔄 Training Metrics 2025-08-29 19:22:25 - pico-train - INFO - ├── Loss: 7.0057 2025-08-29 19:22:25 - pico-train - INFO - ├── Learning Rate: 4.75e-05 2025-08-29 19:22:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:22:38 - pico-train - INFO - Step 7625 -- 🔄 Training Metrics 2025-08-29 19:22:38 - pico-train - INFO - ├── Loss: 7.0182 2025-08-29 19:22:38 - pico-train - INFO - ├── Learning Rate: 4.77e-05 2025-08-29 19:22:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:22:51 - pico-train - INFO - Step 7650 -- 🔄 Training Metrics 2025-08-29 19:22:51 - pico-train - INFO - ├── Loss: 7.0271 2025-08-29 19:22:51 - pico-train - INFO - ├── Learning Rate: 4.78e-05 2025-08-29 19:22:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:23:03 - pico-train - INFO - Step 7675 -- 🔄 Training Metrics 2025-08-29 19:23:03 - pico-train - INFO - ├── Loss: 7.0817 2025-08-29 19:23:03 - pico-train - INFO - ├── Learning Rate: 4.80e-05 2025-08-29 19:23:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:23:16 - pico-train - INFO - Step 7700 -- 🔄 Training Metrics 2025-08-29 19:23:16 - pico-train - INFO - ├── Loss: 7.0859 2025-08-29 19:23:16 - pico-train - INFO - ├── Learning Rate: 4.81e-05 2025-08-29 19:23:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:23:28 - pico-train - INFO - Step 7725 -- 🔄 Training Metrics 2025-08-29 19:23:28 - pico-train - INFO - ├── Loss: 6.9859 2025-08-29 19:23:28 - pico-train - INFO - ├── Learning Rate: 4.83e-05 2025-08-29 19:23:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:23:41 - pico-train - INFO - Step 7750 -- 🔄 Training Metrics 2025-08-29 19:23:41 - pico-train - INFO - ├── Loss: 7.0380 2025-08-29 19:23:41 - pico-train - INFO - ├── Learning Rate: 4.84e-05 2025-08-29 19:23:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:23:54 - pico-train - INFO - Step 7775 -- 🔄 Training Metrics 2025-08-29 19:23:54 - pico-train - INFO - ├── Loss: 6.9784 2025-08-29 19:23:54 - pico-train - INFO - ├── Learning Rate: 4.86e-05 2025-08-29 19:23:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:24:06 - pico-train - INFO - Step 7800 -- 🔄 Training Metrics 2025-08-29 19:24:06 - pico-train - INFO - ├── Loss: 7.0304 2025-08-29 19:24:06 - pico-train - INFO - ├── Learning Rate: 4.87e-05 2025-08-29 19:24:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:24:19 - pico-train - INFO - Step 7825 -- 🔄 Training Metrics 2025-08-29 19:24:19 - pico-train - INFO - ├── Loss: 7.0000 2025-08-29 19:24:19 - pico-train - INFO - ├── Learning Rate: 4.89e-05 2025-08-29 19:24:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:24:31 - pico-train - INFO - Step 7850 -- 🔄 Training Metrics 2025-08-29 19:24:31 - pico-train - INFO - ├── Loss: 7.0159 2025-08-29 19:24:31 - pico-train - INFO - ├── Learning Rate: 4.91e-05 2025-08-29 19:24:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:24:44 - pico-train - INFO - Step 7875 -- 🔄 Training Metrics 2025-08-29 19:24:44 - pico-train - INFO - ├── Loss: 6.9859 2025-08-29 19:24:44 - pico-train - INFO - ├── Learning Rate: 4.92e-05 2025-08-29 19:24:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:24:56 - pico-train - INFO - Step 7900 -- 🔄 Training Metrics 2025-08-29 19:24:56 - pico-train - INFO - ├── Loss: 6.9348 2025-08-29 19:24:56 - pico-train - INFO - ├── Learning Rate: 4.94e-05 2025-08-29 19:24:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:25:09 - pico-train - INFO - Step 7925 -- 🔄 Training Metrics 2025-08-29 19:25:09 - pico-train - INFO - ├── Loss: 6.9541 2025-08-29 19:25:09 - pico-train - INFO - ├── Learning Rate: 4.95e-05 2025-08-29 19:25:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:25:22 - pico-train - INFO - Step 7950 -- 🔄 Training Metrics 2025-08-29 19:25:22 - pico-train - INFO - ├── Loss: 6.9342 2025-08-29 19:25:22 - pico-train - INFO - ├── Learning Rate: 4.97e-05 2025-08-29 19:25:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:25:34 - pico-train - INFO - Step 7975 -- 🔄 Training Metrics 2025-08-29 19:25:34 - pico-train - INFO - ├── Loss: 7.0294 2025-08-29 19:25:34 - pico-train - INFO - ├── Learning Rate: 4.98e-05 2025-08-29 19:25:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:25:46 - pico-train - INFO - Step 8000 -- 💾 Saving Checkpoint 2025-08-29 19:29:05 - pico-train - INFO - Step 8000 -- 📊 Evaluation Results 2025-08-29 19:29:05 - pico-train - INFO - └── paloma: 7.181862506006892e+20 2025-08-29 19:29:08 - pico-train - INFO - Step 8000 -- 🔄 Training Metrics 2025-08-29 19:29:08 - pico-train - INFO - ├── Loss: 7.0412 2025-08-29 19:29:08 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:29:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:29:08 - pico-train - INFO - Step 8000 -- 📈 Saving Learning Dynamics 2025-08-29 19:29:25 - pico-train - INFO - Step 8025 -- 🔄 Training Metrics 2025-08-29 19:29:25 - pico-train - INFO - ├── Loss: 6.9111 2025-08-29 19:29:25 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:29:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:29:54 - pico-train - INFO - Step 8050 -- 🔄 Training Metrics 2025-08-29 19:29:54 - pico-train - INFO - ├── Loss: 7.0142 2025-08-29 19:29:54 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:29:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:30:26 - pico-train - INFO - Step 8075 -- 🔄 Training Metrics 2025-08-29 19:30:26 - pico-train - INFO - ├── Loss: 6.9201 2025-08-29 19:30:26 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:30:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:30:56 - pico-train - INFO - Step 8100 -- 🔄 Training Metrics 2025-08-29 19:30:56 - pico-train - INFO - ├── Loss: 6.9100 2025-08-29 19:30:56 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:30:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:31:32 - pico-train - INFO - Step 8125 -- 🔄 Training Metrics 2025-08-29 19:31:32 - pico-train - INFO - ├── Loss: 6.9728 2025-08-29 19:31:32 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:31:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:32:06 - pico-train - INFO - Step 8150 -- 🔄 Training Metrics 2025-08-29 19:32:06 - pico-train - INFO - ├── Loss: 6.9962 2025-08-29 19:32:06 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:32:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:32:40 - pico-train - INFO - Step 8175 -- 🔄 Training Metrics 2025-08-29 19:32:40 - pico-train - INFO - ├── Loss: 7.0076 2025-08-29 19:32:40 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:32:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:33:12 - pico-train - INFO - Step 8200 -- 🔄 Training Metrics 2025-08-29 19:33:12 - pico-train - INFO - ├── Loss: 6.8807 2025-08-29 19:33:12 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:33:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:33:46 - pico-train - INFO - Step 8225 -- 🔄 Training Metrics 2025-08-29 19:33:46 - pico-train - INFO - ├── Loss: 6.8498 2025-08-29 19:33:46 - pico-train - INFO - ├── Learning Rate: 5.00e-05 2025-08-29 19:33:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:34:19 - pico-train - INFO - Step 8250 -- 🔄 Training Metrics 2025-08-29 19:34:19 - pico-train - INFO - ├── Loss: 6.9326 2025-08-29 19:34:19 - pico-train - INFO - ├── Learning Rate: 4.99e-05 2025-08-29 19:34:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:34:52 - pico-train - INFO - Step 8275 -- 🔄 Training Metrics 2025-08-29 19:34:52 - pico-train - INFO - ├── Loss: 6.8967 2025-08-29 19:34:52 - pico-train - INFO - ├── Learning Rate: 4.99e-05 2025-08-29 19:34:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:35:25 - pico-train - INFO - Step 8300 -- 🔄 Training Metrics 2025-08-29 19:35:25 - pico-train - INFO - ├── Loss: 6.9631 2025-08-29 19:35:25 - pico-train - INFO - ├── Learning Rate: 4.99e-05 2025-08-29 19:35:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:35:57 - pico-train - INFO - Step 8325 -- 🔄 Training Metrics 2025-08-29 19:35:57 - pico-train - INFO - ├── Loss: 6.8934 2025-08-29 19:35:57 - pico-train - INFO - ├── Learning Rate: 4.99e-05 2025-08-29 19:35:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:36:10 - pico-train - INFO - Step 8350 -- 🔄 Training Metrics 2025-08-29 19:36:10 - pico-train - INFO - ├── Loss: 6.8573 2025-08-29 19:36:10 - pico-train - INFO - ├── Learning Rate: 4.99e-05 2025-08-29 19:36:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:36:23 - pico-train - INFO - Step 8375 -- 🔄 Training Metrics 2025-08-29 19:36:23 - pico-train - INFO - ├── Loss: 6.9487 2025-08-29 19:36:23 - pico-train - INFO - ├── Learning Rate: 4.99e-05 2025-08-29 19:36:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:36:35 - pico-train - INFO - Step 8400 -- 🔄 Training Metrics 2025-08-29 19:36:35 - pico-train - INFO - ├── Loss: 6.8890 2025-08-29 19:36:35 - pico-train - INFO - ├── Learning Rate: 4.99e-05 2025-08-29 19:36:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:36:53 - pico-train - INFO - Step 8425 -- 🔄 Training Metrics 2025-08-29 19:36:53 - pico-train - INFO - ├── Loss: 6.9669 2025-08-29 19:36:53 - pico-train - INFO - ├── Learning Rate: 4.98e-05 2025-08-29 19:36:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:37:06 - pico-train - INFO - Step 8450 -- 🔄 Training Metrics 2025-08-29 19:37:06 - pico-train - INFO - ├── Loss: 6.9062 2025-08-29 19:37:06 - pico-train - INFO - ├── Learning Rate: 4.98e-05 2025-08-29 19:37:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:37:18 - pico-train - INFO - Step 8475 -- 🔄 Training Metrics 2025-08-29 19:37:18 - pico-train - INFO - ├── Loss: 6.8962 2025-08-29 19:37:18 - pico-train - INFO - ├── Learning Rate: 4.98e-05 2025-08-29 19:37:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:37:31 - pico-train - INFO - Step 8500 -- 💾 Saving Checkpoint 2025-08-29 19:39:47 - pico-train - INFO - Step 8500 -- 📊 Evaluation Results 2025-08-29 19:39:47 - pico-train - INFO - └── paloma: 1.544414097062705e+21 2025-08-29 19:39:48 - pico-train - INFO - Step 8500 -- 🔄 Training Metrics 2025-08-29 19:39:48 - pico-train - INFO - ├── Loss: 6.9129 2025-08-29 19:39:48 - pico-train - INFO - ├── Learning Rate: 4.98e-05 2025-08-29 19:39:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:39:48 - pico-train - INFO - Step 8500 -- 📈 Saving Learning Dynamics 2025-08-29 19:40:04 - pico-train - INFO - Step 8525 -- 🔄 Training Metrics 2025-08-29 19:40:04 - pico-train - INFO - ├── Loss: 6.8971 2025-08-29 19:40:04 - pico-train - INFO - ├── Learning Rate: 4.98e-05 2025-08-29 19:40:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:40:17 - pico-train - INFO - Step 8550 -- 🔄 Training Metrics 2025-08-29 19:40:17 - pico-train - INFO - ├── Loss: 6.8434 2025-08-29 19:40:17 - pico-train - INFO - ├── Learning Rate: 4.97e-05 2025-08-29 19:40:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:40:29 - pico-train - INFO - Step 8575 -- 🔄 Training Metrics 2025-08-29 19:40:29 - pico-train - INFO - ├── Loss: 6.8232 2025-08-29 19:40:29 - pico-train - INFO - ├── Learning Rate: 4.97e-05 2025-08-29 19:40:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:40:43 - pico-train - INFO - Step 8600 -- 🔄 Training Metrics 2025-08-29 19:40:43 - pico-train - INFO - ├── Loss: 6.9620 2025-08-29 19:40:43 - pico-train - INFO - ├── Learning Rate: 4.97e-05 2025-08-29 19:40:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:40:57 - pico-train - INFO - Step 8625 -- 🔄 Training Metrics 2025-08-29 19:40:57 - pico-train - INFO - ├── Loss: 6.8810 2025-08-29 19:40:57 - pico-train - INFO - ├── Learning Rate: 4.97e-05 2025-08-29 19:40:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:41:09 - pico-train - INFO - Step 8650 -- 🔄 Training Metrics 2025-08-29 19:41:09 - pico-train - INFO - ├── Loss: 6.8215 2025-08-29 19:41:09 - pico-train - INFO - ├── Learning Rate: 4.96e-05 2025-08-29 19:41:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:41:22 - pico-train - INFO - Step 8675 -- 🔄 Training Metrics 2025-08-29 19:41:22 - pico-train - INFO - ├── Loss: 6.8250 2025-08-29 19:41:22 - pico-train - INFO - ├── Learning Rate: 4.96e-05 2025-08-29 19:41:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:41:35 - pico-train - INFO - Step 8700 -- 🔄 Training Metrics 2025-08-29 19:41:35 - pico-train - INFO - ├── Loss: 6.9534 2025-08-29 19:41:35 - pico-train - INFO - ├── Learning Rate: 4.96e-05 2025-08-29 19:41:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:41:48 - pico-train - INFO - Step 8725 -- 🔄 Training Metrics 2025-08-29 19:41:48 - pico-train - INFO - ├── Loss: 6.8382 2025-08-29 19:41:48 - pico-train - INFO - ├── Learning Rate: 4.96e-05 2025-08-29 19:41:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:42:00 - pico-train - INFO - Step 8750 -- 🔄 Training Metrics 2025-08-29 19:42:00 - pico-train - INFO - ├── Loss: 6.8307 2025-08-29 19:42:00 - pico-train - INFO - ├── Learning Rate: 4.95e-05 2025-08-29 19:42:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:42:13 - pico-train - INFO - Step 8775 -- 🔄 Training Metrics 2025-08-29 19:42:13 - pico-train - INFO - ├── Loss: 6.8339 2025-08-29 19:42:13 - pico-train - INFO - ├── Learning Rate: 4.95e-05 2025-08-29 19:42:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:42:26 - pico-train - INFO - Step 8800 -- 🔄 Training Metrics 2025-08-29 19:42:26 - pico-train - INFO - ├── Loss: 6.8389 2025-08-29 19:42:26 - pico-train - INFO - ├── Learning Rate: 4.95e-05 2025-08-29 19:42:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:42:38 - pico-train - INFO - Step 8825 -- 🔄 Training Metrics 2025-08-29 19:42:38 - pico-train - INFO - ├── Loss: 6.8220 2025-08-29 19:42:38 - pico-train - INFO - ├── Learning Rate: 4.94e-05 2025-08-29 19:42:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:42:51 - pico-train - INFO - Step 8850 -- 🔄 Training Metrics 2025-08-29 19:42:51 - pico-train - INFO - ├── Loss: 6.7964 2025-08-29 19:42:51 - pico-train - INFO - ├── Learning Rate: 4.94e-05 2025-08-29 19:42:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:43:04 - pico-train - INFO - Step 8875 -- 🔄 Training Metrics 2025-08-29 19:43:04 - pico-train - INFO - ├── Loss: 6.7773 2025-08-29 19:43:04 - pico-train - INFO - ├── Learning Rate: 4.93e-05 2025-08-29 19:43:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:43:16 - pico-train - INFO - Step 8900 -- 🔄 Training Metrics 2025-08-29 19:43:16 - pico-train - INFO - ├── Loss: 6.8768 2025-08-29 19:43:16 - pico-train - INFO - ├── Learning Rate: 4.93e-05 2025-08-29 19:43:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:43:29 - pico-train - INFO - Step 8925 -- 🔄 Training Metrics 2025-08-29 19:43:29 - pico-train - INFO - ├── Loss: 6.8547 2025-08-29 19:43:29 - pico-train - INFO - ├── Learning Rate: 4.93e-05 2025-08-29 19:43:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:43:42 - pico-train - INFO - Step 8950 -- 🔄 Training Metrics 2025-08-29 19:43:42 - pico-train - INFO - ├── Loss: 6.8451 2025-08-29 19:43:42 - pico-train - INFO - ├── Learning Rate: 4.92e-05 2025-08-29 19:43:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:43:55 - pico-train - INFO - Step 8975 -- 🔄 Training Metrics 2025-08-29 19:43:55 - pico-train - INFO - ├── Loss: 6.8555 2025-08-29 19:43:55 - pico-train - INFO - ├── Learning Rate: 4.92e-05 2025-08-29 19:43:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:44:07 - pico-train - INFO - Step 9000 -- 💾 Saving Checkpoint 2025-08-29 19:46:25 - pico-train - INFO - Step 9000 -- 📊 Evaluation Results 2025-08-29 19:46:25 - pico-train - INFO - └── paloma: 3.7651081241501e+21 2025-08-29 19:46:27 - pico-train - INFO - Step 9000 -- 🔄 Training Metrics 2025-08-29 19:46:27 - pico-train - INFO - ├── Loss: 6.8261 2025-08-29 19:46:27 - pico-train - INFO - ├── Learning Rate: 4.91e-05 2025-08-29 19:46:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:46:27 - pico-train - INFO - Step 9000 -- 📈 Saving Learning Dynamics 2025-08-29 19:46:43 - pico-train - INFO - Step 9025 -- 🔄 Training Metrics 2025-08-29 19:46:43 - pico-train - INFO - ├── Loss: 6.8269 2025-08-29 19:46:43 - pico-train - INFO - ├── Learning Rate: 4.91e-05 2025-08-29 19:46:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:46:55 - pico-train - INFO - Step 9050 -- 🔄 Training Metrics 2025-08-29 19:46:55 - pico-train - INFO - ├── Loss: 6.7945 2025-08-29 19:46:55 - pico-train - INFO - ├── Learning Rate: 4.91e-05 2025-08-29 19:46:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:47:08 - pico-train - INFO - Step 9075 -- 🔄 Training Metrics 2025-08-29 19:47:08 - pico-train - INFO - ├── Loss: 6.8263 2025-08-29 19:47:08 - pico-train - INFO - ├── Learning Rate: 4.90e-05 2025-08-29 19:47:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:47:21 - pico-train - INFO - Step 9100 -- 🔄 Training Metrics 2025-08-29 19:47:21 - pico-train - INFO - ├── Loss: 6.7599 2025-08-29 19:47:21 - pico-train - INFO - ├── Learning Rate: 4.90e-05 2025-08-29 19:47:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:47:35 - pico-train - INFO - Step 9125 -- 🔄 Training Metrics 2025-08-29 19:47:35 - pico-train - INFO - ├── Loss: 6.8176 2025-08-29 19:47:35 - pico-train - INFO - ├── Learning Rate: 4.89e-05 2025-08-29 19:47:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:47:47 - pico-train - INFO - Step 9150 -- 🔄 Training Metrics 2025-08-29 19:47:47 - pico-train - INFO - ├── Loss: 6.7519 2025-08-29 19:47:47 - pico-train - INFO - ├── Learning Rate: 4.89e-05 2025-08-29 19:47:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:48:00 - pico-train - INFO - Step 9175 -- 🔄 Training Metrics 2025-08-29 19:48:00 - pico-train - INFO - ├── Loss: 6.8001 2025-08-29 19:48:00 - pico-train - INFO - ├── Learning Rate: 4.88e-05 2025-08-29 19:48:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:48:12 - pico-train - INFO - Step 9200 -- 🔄 Training Metrics 2025-08-29 19:48:12 - pico-train - INFO - ├── Loss: 6.8289 2025-08-29 19:48:12 - pico-train - INFO - ├── Learning Rate: 4.88e-05 2025-08-29 19:48:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:48:25 - pico-train - INFO - Step 9225 -- 🔄 Training Metrics 2025-08-29 19:48:25 - pico-train - INFO - ├── Loss: 6.9078 2025-08-29 19:48:25 - pico-train - INFO - ├── Learning Rate: 4.87e-05 2025-08-29 19:48:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:48:37 - pico-train - INFO - Step 9250 -- 🔄 Training Metrics 2025-08-29 19:48:37 - pico-train - INFO - ├── Loss: 6.7747 2025-08-29 19:48:37 - pico-train - INFO - ├── Learning Rate: 4.87e-05 2025-08-29 19:48:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:48:50 - pico-train - INFO - Step 9275 -- 🔄 Training Metrics 2025-08-29 19:48:50 - pico-train - INFO - ├── Loss: 6.7717 2025-08-29 19:48:50 - pico-train - INFO - ├── Learning Rate: 4.86e-05 2025-08-29 19:48:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:49:02 - pico-train - INFO - Step 9300 -- 🔄 Training Metrics 2025-08-29 19:49:02 - pico-train - INFO - ├── Loss: 6.7096 2025-08-29 19:49:02 - pico-train - INFO - ├── Learning Rate: 4.86e-05 2025-08-29 19:49:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:49:15 - pico-train - INFO - Step 9325 -- 🔄 Training Metrics 2025-08-29 19:49:15 - pico-train - INFO - ├── Loss: 6.8895 2025-08-29 19:49:15 - pico-train - INFO - ├── Learning Rate: 4.85e-05 2025-08-29 19:49:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:49:28 - pico-train - INFO - Step 9350 -- 🔄 Training Metrics 2025-08-29 19:49:28 - pico-train - INFO - ├── Loss: 6.8665 2025-08-29 19:49:28 - pico-train - INFO - ├── Learning Rate: 4.85e-05 2025-08-29 19:49:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:49:40 - pico-train - INFO - Step 9375 -- 🔄 Training Metrics 2025-08-29 19:49:40 - pico-train - INFO - ├── Loss: 6.7131 2025-08-29 19:49:40 - pico-train - INFO - ├── Learning Rate: 4.84e-05 2025-08-29 19:49:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:49:53 - pico-train - INFO - Step 9400 -- 🔄 Training Metrics 2025-08-29 19:49:53 - pico-train - INFO - ├── Loss: 6.7064 2025-08-29 19:49:53 - pico-train - INFO - ├── Learning Rate: 4.83e-05 2025-08-29 19:49:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:50:06 - pico-train - INFO - Step 9425 -- 🔄 Training Metrics 2025-08-29 19:50:06 - pico-train - INFO - ├── Loss: 6.8320 2025-08-29 19:50:06 - pico-train - INFO - ├── Learning Rate: 4.83e-05 2025-08-29 19:50:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:50:18 - pico-train - INFO - Step 9450 -- 🔄 Training Metrics 2025-08-29 19:50:18 - pico-train - INFO - ├── Loss: 6.7871 2025-08-29 19:50:18 - pico-train - INFO - ├── Learning Rate: 4.82e-05 2025-08-29 19:50:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:50:31 - pico-train - INFO - Step 9475 -- 🔄 Training Metrics 2025-08-29 19:50:31 - pico-train - INFO - ├── Loss: 6.7753 2025-08-29 19:50:31 - pico-train - INFO - ├── Learning Rate: 4.82e-05 2025-08-29 19:50:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:50:43 - pico-train - INFO - Step 9500 -- 💾 Saving Checkpoint 2025-08-29 19:52:47 - pico-train - INFO - Step 9500 -- 📊 Evaluation Results 2025-08-29 19:52:47 - pico-train - INFO - └── paloma: 8.42703670029247e+21 2025-08-29 19:52:48 - pico-train - INFO - Step 9500 -- 🔄 Training Metrics 2025-08-29 19:52:48 - pico-train - INFO - ├── Loss: 6.7261 2025-08-29 19:52:48 - pico-train - INFO - ├── Learning Rate: 4.81e-05 2025-08-29 19:52:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:52:48 - pico-train - INFO - Step 9500 -- 📈 Saving Learning Dynamics 2025-08-29 19:53:04 - pico-train - INFO - Step 9525 -- 🔄 Training Metrics 2025-08-29 19:53:04 - pico-train - INFO - ├── Loss: 6.7447 2025-08-29 19:53:04 - pico-train - INFO - ├── Learning Rate: 4.80e-05 2025-08-29 19:53:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:53:16 - pico-train - INFO - Step 9550 -- 🔄 Training Metrics 2025-08-29 19:53:16 - pico-train - INFO - ├── Loss: 6.6755 2025-08-29 19:53:16 - pico-train - INFO - ├── Learning Rate: 4.80e-05 2025-08-29 19:53:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:53:29 - pico-train - INFO - Step 9575 -- 🔄 Training Metrics 2025-08-29 19:53:29 - pico-train - INFO - ├── Loss: 6.7466 2025-08-29 19:53:29 - pico-train - INFO - ├── Learning Rate: 4.79e-05 2025-08-29 19:53:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:53:42 - pico-train - INFO - Step 9600 -- 🔄 Training Metrics 2025-08-29 19:53:42 - pico-train - INFO - ├── Loss: 6.8755 2025-08-29 19:53:42 - pico-train - INFO - ├── Learning Rate: 4.78e-05 2025-08-29 19:53:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:53:55 - pico-train - INFO - Step 9625 -- 🔄 Training Metrics 2025-08-29 19:53:55 - pico-train - INFO - ├── Loss: 6.8187 2025-08-29 19:53:55 - pico-train - INFO - ├── Learning Rate: 4.78e-05 2025-08-29 19:53:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:54:08 - pico-train - INFO - Step 9650 -- 🔄 Training Metrics 2025-08-29 19:54:08 - pico-train - INFO - ├── Loss: 6.7354 2025-08-29 19:54:08 - pico-train - INFO - ├── Learning Rate: 4.77e-05 2025-08-29 19:54:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:54:21 - pico-train - INFO - Step 9675 -- 🔄 Training Metrics 2025-08-29 19:54:21 - pico-train - INFO - ├── Loss: 6.6726 2025-08-29 19:54:21 - pico-train - INFO - ├── Learning Rate: 4.76e-05 2025-08-29 19:54:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:54:34 - pico-train - INFO - Step 9700 -- 🔄 Training Metrics 2025-08-29 19:54:34 - pico-train - INFO - ├── Loss: 6.7547 2025-08-29 19:54:34 - pico-train - INFO - ├── Learning Rate: 4.76e-05 2025-08-29 19:54:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:54:46 - pico-train - INFO - Step 9725 -- 🔄 Training Metrics 2025-08-29 19:54:46 - pico-train - INFO - ├── Loss: 6.6679 2025-08-29 19:54:46 - pico-train - INFO - ├── Learning Rate: 4.75e-05 2025-08-29 19:54:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:54:59 - pico-train - INFO - Step 9750 -- 🔄 Training Metrics 2025-08-29 19:54:59 - pico-train - INFO - ├── Loss: 6.7332 2025-08-29 19:54:59 - pico-train - INFO - ├── Learning Rate: 4.74e-05 2025-08-29 19:54:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:55:12 - pico-train - INFO - Step 9775 -- 🔄 Training Metrics 2025-08-29 19:55:12 - pico-train - INFO - ├── Loss: 6.7595 2025-08-29 19:55:12 - pico-train - INFO - ├── Learning Rate: 4.73e-05 2025-08-29 19:55:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:55:25 - pico-train - INFO - Step 9800 -- 🔄 Training Metrics 2025-08-29 19:55:25 - pico-train - INFO - ├── Loss: 6.7183 2025-08-29 19:55:25 - pico-train - INFO - ├── Learning Rate: 4.73e-05 2025-08-29 19:55:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:55:38 - pico-train - INFO - Step 9825 -- 🔄 Training Metrics 2025-08-29 19:55:38 - pico-train - INFO - ├── Loss: 6.7211 2025-08-29 19:55:38 - pico-train - INFO - ├── Learning Rate: 4.72e-05 2025-08-29 19:55:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:55:51 - pico-train - INFO - Step 9850 -- 🔄 Training Metrics 2025-08-29 19:55:51 - pico-train - INFO - ├── Loss: 6.7175 2025-08-29 19:55:51 - pico-train - INFO - ├── Learning Rate: 4.71e-05 2025-08-29 19:55:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:56:04 - pico-train - INFO - Step 9875 -- 🔄 Training Metrics 2025-08-29 19:56:04 - pico-train - INFO - ├── Loss: 6.8444 2025-08-29 19:56:04 - pico-train - INFO - ├── Learning Rate: 4.70e-05 2025-08-29 19:56:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:56:17 - pico-train - INFO - Step 9900 -- 🔄 Training Metrics 2025-08-29 19:56:17 - pico-train - INFO - ├── Loss: 6.7806 2025-08-29 19:56:17 - pico-train - INFO - ├── Learning Rate: 4.70e-05 2025-08-29 19:56:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:56:30 - pico-train - INFO - Step 9925 -- 🔄 Training Metrics 2025-08-29 19:56:30 - pico-train - INFO - ├── Loss: 6.7188 2025-08-29 19:56:30 - pico-train - INFO - ├── Learning Rate: 4.69e-05 2025-08-29 19:56:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:56:43 - pico-train - INFO - Step 9950 -- 🔄 Training Metrics 2025-08-29 19:56:43 - pico-train - INFO - ├── Loss: 6.7352 2025-08-29 19:56:43 - pico-train - INFO - ├── Learning Rate: 4.68e-05 2025-08-29 19:56:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:56:56 - pico-train - INFO - Step 9975 -- 🔄 Training Metrics 2025-08-29 19:56:56 - pico-train - INFO - ├── Loss: 6.6457 2025-08-29 19:56:56 - pico-train - INFO - ├── Learning Rate: 4.67e-05 2025-08-29 19:56:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:57:08 - pico-train - INFO - Step 10000 -- 💾 Saving Checkpoint 2025-08-29 19:59:31 - pico-train - INFO - Step 10000 -- 📊 Evaluation Results 2025-08-29 19:59:31 - pico-train - INFO - └── paloma: 1.2602927078762317e+22 2025-08-29 19:59:32 - pico-train - INFO - Step 10000 -- 🔄 Training Metrics 2025-08-29 19:59:32 - pico-train - INFO - ├── Loss: 6.6998 2025-08-29 19:59:32 - pico-train - INFO - ├── Learning Rate: 4.67e-05 2025-08-29 19:59:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 19:59:32 - pico-train - INFO - Step 10000 -- 📈 Saving Learning Dynamics 2025-08-29 19:59:47 - pico-train - INFO - Step 10025 -- 🔄 Training Metrics 2025-08-29 19:59:47 - pico-train - INFO - ├── Loss: 6.7628 2025-08-29 19:59:47 - pico-train - INFO - ├── Learning Rate: 4.66e-05 2025-08-29 19:59:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:00:00 - pico-train - INFO - Step 10050 -- 🔄 Training Metrics 2025-08-29 20:00:00 - pico-train - INFO - ├── Loss: 6.6822 2025-08-29 20:00:00 - pico-train - INFO - ├── Learning Rate: 4.65e-05 2025-08-29 20:00:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:00:12 - pico-train - INFO - Step 10075 -- 🔄 Training Metrics 2025-08-29 20:00:12 - pico-train - INFO - ├── Loss: 6.6664 2025-08-29 20:00:12 - pico-train - INFO - ├── Learning Rate: 4.64e-05 2025-08-29 20:00:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:00:25 - pico-train - INFO - Step 10100 -- 🔄 Training Metrics 2025-08-29 20:00:25 - pico-train - INFO - ├── Loss: 6.6829 2025-08-29 20:00:25 - pico-train - INFO - ├── Learning Rate: 4.63e-05 2025-08-29 20:00:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:00:39 - pico-train - INFO - Step 10125 -- 🔄 Training Metrics 2025-08-29 20:00:39 - pico-train - INFO - ├── Loss: 6.6947 2025-08-29 20:00:39 - pico-train - INFO - ├── Learning Rate: 4.62e-05 2025-08-29 20:00:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:00:51 - pico-train - INFO - Step 10150 -- 🔄 Training Metrics 2025-08-29 20:00:51 - pico-train - INFO - ├── Loss: 6.7610 2025-08-29 20:00:51 - pico-train - INFO - ├── Learning Rate: 4.61e-05 2025-08-29 20:00:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:01:04 - pico-train - INFO - Step 10175 -- 🔄 Training Metrics 2025-08-29 20:01:04 - pico-train - INFO - ├── Loss: 6.7909 2025-08-29 20:01:04 - pico-train - INFO - ├── Learning Rate: 4.61e-05 2025-08-29 20:01:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:01:17 - pico-train - INFO - Step 10200 -- 🔄 Training Metrics 2025-08-29 20:01:17 - pico-train - INFO - ├── Loss: 6.7476 2025-08-29 20:01:17 - pico-train - INFO - ├── Learning Rate: 4.60e-05 2025-08-29 20:01:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:01:29 - pico-train - INFO - Step 10225 -- 🔄 Training Metrics 2025-08-29 20:01:29 - pico-train - INFO - ├── Loss: 6.6857 2025-08-29 20:01:29 - pico-train - INFO - ├── Learning Rate: 4.59e-05 2025-08-29 20:01:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:01:43 - pico-train - INFO - Step 10250 -- 🔄 Training Metrics 2025-08-29 20:01:43 - pico-train - INFO - ├── Loss: 6.6632 2025-08-29 20:01:43 - pico-train - INFO - ├── Learning Rate: 4.58e-05 2025-08-29 20:01:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:01:56 - pico-train - INFO - Step 10275 -- 🔄 Training Metrics 2025-08-29 20:01:56 - pico-train - INFO - ├── Loss: 6.7323 2025-08-29 20:01:56 - pico-train - INFO - ├── Learning Rate: 4.57e-05 2025-08-29 20:01:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:02:08 - pico-train - INFO - Step 10300 -- 🔄 Training Metrics 2025-08-29 20:02:08 - pico-train - INFO - ├── Loss: 6.6958 2025-08-29 20:02:08 - pico-train - INFO - ├── Learning Rate: 4.56e-05 2025-08-29 20:02:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:02:21 - pico-train - INFO - Step 10325 -- 🔄 Training Metrics 2025-08-29 20:02:21 - pico-train - INFO - ├── Loss: 6.6858 2025-08-29 20:02:21 - pico-train - INFO - ├── Learning Rate: 4.55e-05 2025-08-29 20:02:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:02:34 - pico-train - INFO - Step 10350 -- 🔄 Training Metrics 2025-08-29 20:02:34 - pico-train - INFO - ├── Loss: 6.7033 2025-08-29 20:02:34 - pico-train - INFO - ├── Learning Rate: 4.54e-05 2025-08-29 20:02:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:02:46 - pico-train - INFO - Step 10375 -- 🔄 Training Metrics 2025-08-29 20:02:46 - pico-train - INFO - ├── Loss: 6.6819 2025-08-29 20:02:46 - pico-train - INFO - ├── Learning Rate: 4.53e-05 2025-08-29 20:02:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:02:59 - pico-train - INFO - Step 10400 -- 🔄 Training Metrics 2025-08-29 20:02:59 - pico-train - INFO - ├── Loss: 6.7418 2025-08-29 20:02:59 - pico-train - INFO - ├── Learning Rate: 4.52e-05 2025-08-29 20:02:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:03:12 - pico-train - INFO - Step 10425 -- 🔄 Training Metrics 2025-08-29 20:03:12 - pico-train - INFO - ├── Loss: 6.7313 2025-08-29 20:03:12 - pico-train - INFO - ├── Learning Rate: 4.51e-05 2025-08-29 20:03:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:03:24 - pico-train - INFO - Step 10450 -- 🔄 Training Metrics 2025-08-29 20:03:24 - pico-train - INFO - ├── Loss: 6.6978 2025-08-29 20:03:24 - pico-train - INFO - ├── Learning Rate: 4.50e-05 2025-08-29 20:03:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:03:37 - pico-train - INFO - Step 10475 -- 🔄 Training Metrics 2025-08-29 20:03:37 - pico-train - INFO - ├── Loss: 6.6200 2025-08-29 20:03:37 - pico-train - INFO - ├── Learning Rate: 4.49e-05 2025-08-29 20:03:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:03:49 - pico-train - INFO - Step 10500 -- 💾 Saving Checkpoint 2025-08-29 20:06:30 - pico-train - INFO - Step 10500 -- 📊 Evaluation Results 2025-08-29 20:06:30 - pico-train - INFO - └── paloma: 2.548096053613213e+22 2025-08-29 20:06:32 - pico-train - INFO - Step 10500 -- 🔄 Training Metrics 2025-08-29 20:06:32 - pico-train - INFO - ├── Loss: 6.6817 2025-08-29 20:06:32 - pico-train - INFO - ├── Learning Rate: 4.48e-05 2025-08-29 20:06:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:06:32 - pico-train - INFO - Step 10500 -- 📈 Saving Learning Dynamics 2025-08-29 20:06:46 - pico-train - INFO - Step 10525 -- 🔄 Training Metrics 2025-08-29 20:06:46 - pico-train - INFO - ├── Loss: 6.6343 2025-08-29 20:06:46 - pico-train - INFO - ├── Learning Rate: 4.47e-05 2025-08-29 20:06:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:06:59 - pico-train - INFO - Step 10550 -- 🔄 Training Metrics 2025-08-29 20:06:59 - pico-train - INFO - ├── Loss: 6.5885 2025-08-29 20:06:59 - pico-train - INFO - ├── Learning Rate: 4.46e-05 2025-08-29 20:06:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:07:12 - pico-train - INFO - Step 10575 -- 🔄 Training Metrics 2025-08-29 20:07:12 - pico-train - INFO - ├── Loss: 6.6060 2025-08-29 20:07:12 - pico-train - INFO - ├── Learning Rate: 4.45e-05 2025-08-29 20:07:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:07:24 - pico-train - INFO - Step 10600 -- 🔄 Training Metrics 2025-08-29 20:07:24 - pico-train - INFO - ├── Loss: 6.6924 2025-08-29 20:07:24 - pico-train - INFO - ├── Learning Rate: 4.44e-05 2025-08-29 20:07:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:07:37 - pico-train - INFO - Step 10625 -- 🔄 Training Metrics 2025-08-29 20:07:37 - pico-train - INFO - ├── Loss: 6.6004 2025-08-29 20:07:37 - pico-train - INFO - ├── Learning Rate: 4.43e-05 2025-08-29 20:07:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:07:50 - pico-train - INFO - Step 10650 -- 🔄 Training Metrics 2025-08-29 20:07:50 - pico-train - INFO - ├── Loss: 6.6561 2025-08-29 20:07:50 - pico-train - INFO - ├── Learning Rate: 4.42e-05 2025-08-29 20:07:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:08:02 - pico-train - INFO - Step 10675 -- 🔄 Training Metrics 2025-08-29 20:08:02 - pico-train - INFO - ├── Loss: 6.6306 2025-08-29 20:08:02 - pico-train - INFO - ├── Learning Rate: 4.41e-05 2025-08-29 20:08:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:08:15 - pico-train - INFO - Step 10700 -- 🔄 Training Metrics 2025-08-29 20:08:15 - pico-train - INFO - ├── Loss: 6.6713 2025-08-29 20:08:15 - pico-train - INFO - ├── Learning Rate: 4.40e-05 2025-08-29 20:08:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:08:28 - pico-train - INFO - Step 10725 -- 🔄 Training Metrics 2025-08-29 20:08:28 - pico-train - INFO - ├── Loss: 6.5606 2025-08-29 20:08:28 - pico-train - INFO - ├── Learning Rate: 4.39e-05 2025-08-29 20:08:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:08:41 - pico-train - INFO - Step 10750 -- 🔄 Training Metrics 2025-08-29 20:08:41 - pico-train - INFO - ├── Loss: 6.6740 2025-08-29 20:08:41 - pico-train - INFO - ├── Learning Rate: 4.38e-05 2025-08-29 20:08:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:08:54 - pico-train - INFO - Step 10775 -- 🔄 Training Metrics 2025-08-29 20:08:54 - pico-train - INFO - ├── Loss: 6.6308 2025-08-29 20:08:54 - pico-train - INFO - ├── Learning Rate: 4.37e-05 2025-08-29 20:08:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:09:06 - pico-train - INFO - Step 10800 -- 🔄 Training Metrics 2025-08-29 20:09:06 - pico-train - INFO - ├── Loss: 6.7103 2025-08-29 20:09:06 - pico-train - INFO - ├── Learning Rate: 4.36e-05 2025-08-29 20:09:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:09:19 - pico-train - INFO - Step 10825 -- 🔄 Training Metrics 2025-08-29 20:09:19 - pico-train - INFO - ├── Loss: 6.6176 2025-08-29 20:09:19 - pico-train - INFO - ├── Learning Rate: 4.35e-05 2025-08-29 20:09:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:09:32 - pico-train - INFO - Step 10850 -- 🔄 Training Metrics 2025-08-29 20:09:32 - pico-train - INFO - ├── Loss: 6.6927 2025-08-29 20:09:32 - pico-train - INFO - ├── Learning Rate: 4.34e-05 2025-08-29 20:09:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:09:44 - pico-train - INFO - Step 10875 -- 🔄 Training Metrics 2025-08-29 20:09:44 - pico-train - INFO - ├── Loss: 6.7048 2025-08-29 20:09:44 - pico-train - INFO - ├── Learning Rate: 4.32e-05 2025-08-29 20:09:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:09:57 - pico-train - INFO - Step 10900 -- 🔄 Training Metrics 2025-08-29 20:09:57 - pico-train - INFO - ├── Loss: 6.6776 2025-08-29 20:09:57 - pico-train - INFO - ├── Learning Rate: 4.31e-05 2025-08-29 20:09:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:10:10 - pico-train - INFO - Step 10925 -- 🔄 Training Metrics 2025-08-29 20:10:10 - pico-train - INFO - ├── Loss: 6.6591 2025-08-29 20:10:10 - pico-train - INFO - ├── Learning Rate: 4.30e-05 2025-08-29 20:10:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:10:22 - pico-train - INFO - Step 10950 -- 🔄 Training Metrics 2025-08-29 20:10:22 - pico-train - INFO - ├── Loss: 6.6584 2025-08-29 20:10:22 - pico-train - INFO - ├── Learning Rate: 4.29e-05 2025-08-29 20:10:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:10:35 - pico-train - INFO - Step 10975 -- 🔄 Training Metrics 2025-08-29 20:10:35 - pico-train - INFO - ├── Loss: 6.6623 2025-08-29 20:10:35 - pico-train - INFO - ├── Learning Rate: 4.28e-05 2025-08-29 20:10:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:10:47 - pico-train - INFO - Step 11000 -- 💾 Saving Checkpoint 2025-08-29 20:12:49 - pico-train - INFO - Step 11000 -- 📊 Evaluation Results 2025-08-29 20:12:49 - pico-train - INFO - └── paloma: 3.4687567457405914e+22 2025-08-29 20:12:50 - pico-train - INFO - Step 11000 -- 🔄 Training Metrics 2025-08-29 20:12:50 - pico-train - INFO - ├── Loss: 6.5963 2025-08-29 20:12:50 - pico-train - INFO - ├── Learning Rate: 4.27e-05 2025-08-29 20:12:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:12:50 - pico-train - INFO - Step 11000 -- 📈 Saving Learning Dynamics 2025-08-29 20:13:05 - pico-train - INFO - Step 11025 -- 🔄 Training Metrics 2025-08-29 20:13:05 - pico-train - INFO - ├── Loss: 6.6530 2025-08-29 20:13:05 - pico-train - INFO - ├── Learning Rate: 4.26e-05 2025-08-29 20:13:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:13:17 - pico-train - INFO - Step 11050 -- 🔄 Training Metrics 2025-08-29 20:13:17 - pico-train - INFO - ├── Loss: 6.6117 2025-08-29 20:13:17 - pico-train - INFO - ├── Learning Rate: 4.24e-05 2025-08-29 20:13:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:13:30 - pico-train - INFO - Step 11075 -- 🔄 Training Metrics 2025-08-29 20:13:30 - pico-train - INFO - ├── Loss: 6.6225 2025-08-29 20:13:30 - pico-train - INFO - ├── Learning Rate: 4.23e-05 2025-08-29 20:13:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:13:43 - pico-train - INFO - Step 11100 -- 🔄 Training Metrics 2025-08-29 20:13:43 - pico-train - INFO - ├── Loss: 6.6265 2025-08-29 20:13:43 - pico-train - INFO - ├── Learning Rate: 4.22e-05 2025-08-29 20:13:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:13:55 - pico-train - INFO - Step 11125 -- 🔄 Training Metrics 2025-08-29 20:13:55 - pico-train - INFO - ├── Loss: 6.6243 2025-08-29 20:13:55 - pico-train - INFO - ├── Learning Rate: 4.21e-05 2025-08-29 20:13:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:14:08 - pico-train - INFO - Step 11150 -- 🔄 Training Metrics 2025-08-29 20:14:08 - pico-train - INFO - ├── Loss: 6.6638 2025-08-29 20:14:08 - pico-train - INFO - ├── Learning Rate: 4.20e-05 2025-08-29 20:14:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:14:21 - pico-train - INFO - Step 11175 -- 🔄 Training Metrics 2025-08-29 20:14:21 - pico-train - INFO - ├── Loss: 6.5506 2025-08-29 20:14:21 - pico-train - INFO - ├── Learning Rate: 4.18e-05 2025-08-29 20:14:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:14:33 - pico-train - INFO - Step 11200 -- 🔄 Training Metrics 2025-08-29 20:14:33 - pico-train - INFO - ├── Loss: 6.6098 2025-08-29 20:14:33 - pico-train - INFO - ├── Learning Rate: 4.17e-05 2025-08-29 20:14:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:14:46 - pico-train - INFO - Step 11225 -- 🔄 Training Metrics 2025-08-29 20:14:46 - pico-train - INFO - ├── Loss: 6.6271 2025-08-29 20:14:46 - pico-train - INFO - ├── Learning Rate: 4.16e-05 2025-08-29 20:14:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:15:02 - pico-train - INFO - Step 11250 -- 🔄 Training Metrics 2025-08-29 20:15:02 - pico-train - INFO - ├── Loss: 6.5983 2025-08-29 20:15:02 - pico-train - INFO - ├── Learning Rate: 4.15e-05 2025-08-29 20:15:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:15:14 - pico-train - INFO - Step 11275 -- 🔄 Training Metrics 2025-08-29 20:15:14 - pico-train - INFO - ├── Loss: 6.6346 2025-08-29 20:15:14 - pico-train - INFO - ├── Learning Rate: 4.14e-05 2025-08-29 20:15:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:15:27 - pico-train - INFO - Step 11300 -- 🔄 Training Metrics 2025-08-29 20:15:27 - pico-train - INFO - ├── Loss: 6.5797 2025-08-29 20:15:27 - pico-train - INFO - ├── Learning Rate: 4.12e-05 2025-08-29 20:15:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:15:40 - pico-train - INFO - Step 11325 -- 🔄 Training Metrics 2025-08-29 20:15:40 - pico-train - INFO - ├── Loss: 6.6250 2025-08-29 20:15:40 - pico-train - INFO - ├── Learning Rate: 4.11e-05 2025-08-29 20:15:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:15:52 - pico-train - INFO - Step 11350 -- 🔄 Training Metrics 2025-08-29 20:15:52 - pico-train - INFO - ├── Loss: 6.6715 2025-08-29 20:15:52 - pico-train - INFO - ├── Learning Rate: 4.10e-05 2025-08-29 20:15:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:16:05 - pico-train - INFO - Step 11375 -- 🔄 Training Metrics 2025-08-29 20:16:05 - pico-train - INFO - ├── Loss: 6.5902 2025-08-29 20:16:05 - pico-train - INFO - ├── Learning Rate: 4.09e-05 2025-08-29 20:16:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:16:18 - pico-train - INFO - Step 11400 -- 🔄 Training Metrics 2025-08-29 20:16:18 - pico-train - INFO - ├── Loss: 6.6557 2025-08-29 20:16:18 - pico-train - INFO - ├── Learning Rate: 4.07e-05 2025-08-29 20:16:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:16:30 - pico-train - INFO - Step 11425 -- 🔄 Training Metrics 2025-08-29 20:16:30 - pico-train - INFO - ├── Loss: 6.6095 2025-08-29 20:16:30 - pico-train - INFO - ├── Learning Rate: 4.06e-05 2025-08-29 20:16:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:16:43 - pico-train - INFO - Step 11450 -- 🔄 Training Metrics 2025-08-29 20:16:43 - pico-train - INFO - ├── Loss: 6.5971 2025-08-29 20:16:43 - pico-train - INFO - ├── Learning Rate: 4.05e-05 2025-08-29 20:16:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:16:56 - pico-train - INFO - Step 11475 -- 🔄 Training Metrics 2025-08-29 20:16:56 - pico-train - INFO - ├── Loss: 6.5727 2025-08-29 20:16:56 - pico-train - INFO - ├── Learning Rate: 4.03e-05 2025-08-29 20:16:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:17:08 - pico-train - INFO - Step 11500 -- 💾 Saving Checkpoint 2025-08-29 20:19:11 - pico-train - INFO - Step 11500 -- 📊 Evaluation Results 2025-08-29 20:19:11 - pico-train - INFO - └── paloma: 6.754268354433947e+22 2025-08-29 20:19:12 - pico-train - INFO - Step 11500 -- 🔄 Training Metrics 2025-08-29 20:19:12 - pico-train - INFO - ├── Loss: 6.5578 2025-08-29 20:19:12 - pico-train - INFO - ├── Learning Rate: 4.02e-05 2025-08-29 20:19:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:19:12 - pico-train - INFO - Step 11500 -- 📈 Saving Learning Dynamics 2025-08-29 20:19:27 - pico-train - INFO - Step 11525 -- 🔄 Training Metrics 2025-08-29 20:19:27 - pico-train - INFO - ├── Loss: 6.6098 2025-08-29 20:19:27 - pico-train - INFO - ├── Learning Rate: 4.01e-05 2025-08-29 20:19:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:19:40 - pico-train - INFO - Step 11550 -- 🔄 Training Metrics 2025-08-29 20:19:40 - pico-train - INFO - ├── Loss: 6.5940 2025-08-29 20:19:40 - pico-train - INFO - ├── Learning Rate: 4.00e-05 2025-08-29 20:19:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:19:52 - pico-train - INFO - Step 11575 -- 🔄 Training Metrics 2025-08-29 20:19:52 - pico-train - INFO - ├── Loss: 6.6258 2025-08-29 20:19:52 - pico-train - INFO - ├── Learning Rate: 3.98e-05 2025-08-29 20:19:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:20:05 - pico-train - INFO - Step 11600 -- 🔄 Training Metrics 2025-08-29 20:20:05 - pico-train - INFO - ├── Loss: 6.5818 2025-08-29 20:20:05 - pico-train - INFO - ├── Learning Rate: 3.97e-05 2025-08-29 20:20:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:20:18 - pico-train - INFO - Step 11625 -- 🔄 Training Metrics 2025-08-29 20:20:18 - pico-train - INFO - ├── Loss: 6.5947 2025-08-29 20:20:18 - pico-train - INFO - ├── Learning Rate: 3.96e-05 2025-08-29 20:20:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:20:30 - pico-train - INFO - Step 11650 -- 🔄 Training Metrics 2025-08-29 20:20:30 - pico-train - INFO - ├── Loss: 6.5353 2025-08-29 20:20:30 - pico-train - INFO - ├── Learning Rate: 3.94e-05 2025-08-29 20:20:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:20:43 - pico-train - INFO - Step 11675 -- 🔄 Training Metrics 2025-08-29 20:20:43 - pico-train - INFO - ├── Loss: 6.6060 2025-08-29 20:20:43 - pico-train - INFO - ├── Learning Rate: 3.93e-05 2025-08-29 20:20:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:20:56 - pico-train - INFO - Step 11700 -- 🔄 Training Metrics 2025-08-29 20:20:56 - pico-train - INFO - ├── Loss: 6.4960 2025-08-29 20:20:56 - pico-train - INFO - ├── Learning Rate: 3.92e-05 2025-08-29 20:20:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:21:08 - pico-train - INFO - Step 11725 -- 🔄 Training Metrics 2025-08-29 20:21:08 - pico-train - INFO - ├── Loss: 6.5251 2025-08-29 20:21:08 - pico-train - INFO - ├── Learning Rate: 3.90e-05 2025-08-29 20:21:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:21:24 - pico-train - INFO - Step 11750 -- 🔄 Training Metrics 2025-08-29 20:21:24 - pico-train - INFO - ├── Loss: 6.6466 2025-08-29 20:21:24 - pico-train - INFO - ├── Learning Rate: 3.89e-05 2025-08-29 20:21:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:21:37 - pico-train - INFO - Step 11775 -- 🔄 Training Metrics 2025-08-29 20:21:37 - pico-train - INFO - ├── Loss: 6.6170 2025-08-29 20:21:37 - pico-train - INFO - ├── Learning Rate: 3.88e-05 2025-08-29 20:21:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:21:50 - pico-train - INFO - Step 11800 -- 🔄 Training Metrics 2025-08-29 20:21:50 - pico-train - INFO - ├── Loss: 6.5495 2025-08-29 20:21:50 - pico-train - INFO - ├── Learning Rate: 3.86e-05 2025-08-29 20:21:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:22:02 - pico-train - INFO - Step 11825 -- 🔄 Training Metrics 2025-08-29 20:22:02 - pico-train - INFO - ├── Loss: 6.5836 2025-08-29 20:22:02 - pico-train - INFO - ├── Learning Rate: 3.85e-05 2025-08-29 20:22:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:22:15 - pico-train - INFO - Step 11850 -- 🔄 Training Metrics 2025-08-29 20:22:15 - pico-train - INFO - ├── Loss: 6.6164 2025-08-29 20:22:15 - pico-train - INFO - ├── Learning Rate: 3.83e-05 2025-08-29 20:22:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:22:27 - pico-train - INFO - Step 11875 -- 🔄 Training Metrics 2025-08-29 20:22:27 - pico-train - INFO - ├── Loss: 6.6049 2025-08-29 20:22:27 - pico-train - INFO - ├── Learning Rate: 3.82e-05 2025-08-29 20:22:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:22:40 - pico-train - INFO - Step 11900 -- 🔄 Training Metrics 2025-08-29 20:22:40 - pico-train - INFO - ├── Loss: 6.5526 2025-08-29 20:22:40 - pico-train - INFO - ├── Learning Rate: 3.81e-05 2025-08-29 20:22:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:22:53 - pico-train - INFO - Step 11925 -- 🔄 Training Metrics 2025-08-29 20:22:53 - pico-train - INFO - ├── Loss: 6.4726 2025-08-29 20:22:53 - pico-train - INFO - ├── Learning Rate: 3.79e-05 2025-08-29 20:22:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:23:05 - pico-train - INFO - Step 11950 -- 🔄 Training Metrics 2025-08-29 20:23:05 - pico-train - INFO - ├── Loss: 6.6102 2025-08-29 20:23:05 - pico-train - INFO - ├── Learning Rate: 3.78e-05 2025-08-29 20:23:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:23:18 - pico-train - INFO - Step 11975 -- 🔄 Training Metrics 2025-08-29 20:23:18 - pico-train - INFO - ├── Loss: 6.5932 2025-08-29 20:23:18 - pico-train - INFO - ├── Learning Rate: 3.76e-05 2025-08-29 20:23:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:23:30 - pico-train - INFO - Step 12000 -- 💾 Saving Checkpoint 2025-08-29 20:25:41 - pico-train - INFO - Step 12000 -- 📊 Evaluation Results 2025-08-29 20:25:41 - pico-train - INFO - └── paloma: 9.960108515700423e+22 2025-08-29 20:25:42 - pico-train - INFO - Step 12000 -- 🔄 Training Metrics 2025-08-29 20:25:42 - pico-train - INFO - ├── Loss: 6.6366 2025-08-29 20:25:42 - pico-train - INFO - ├── Learning Rate: 3.75e-05 2025-08-29 20:25:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:25:42 - pico-train - INFO - Step 12000 -- 📈 Saving Learning Dynamics 2025-08-29 20:25:57 - pico-train - INFO - Step 12025 -- 🔄 Training Metrics 2025-08-29 20:25:57 - pico-train - INFO - ├── Loss: 6.5240 2025-08-29 20:25:57 - pico-train - INFO - ├── Learning Rate: 3.74e-05 2025-08-29 20:25:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:26:09 - pico-train - INFO - Step 12050 -- 🔄 Training Metrics 2025-08-29 20:26:09 - pico-train - INFO - ├── Loss: 6.5622 2025-08-29 20:26:09 - pico-train - INFO - ├── Learning Rate: 3.72e-05 2025-08-29 20:26:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:26:22 - pico-train - INFO - Step 12075 -- 🔄 Training Metrics 2025-08-29 20:26:22 - pico-train - INFO - ├── Loss: 6.4987 2025-08-29 20:26:22 - pico-train - INFO - ├── Learning Rate: 3.71e-05 2025-08-29 20:26:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:26:35 - pico-train - INFO - Step 12100 -- 🔄 Training Metrics 2025-08-29 20:26:35 - pico-train - INFO - ├── Loss: 6.5377 2025-08-29 20:26:35 - pico-train - INFO - ├── Learning Rate: 3.69e-05 2025-08-29 20:26:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:26:48 - pico-train - INFO - Step 12125 -- 🔄 Training Metrics 2025-08-29 20:26:48 - pico-train - INFO - ├── Loss: 6.5937 2025-08-29 20:26:48 - pico-train - INFO - ├── Learning Rate: 3.68e-05 2025-08-29 20:26:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:27:00 - pico-train - INFO - Step 12150 -- 🔄 Training Metrics 2025-08-29 20:27:00 - pico-train - INFO - ├── Loss: 6.5536 2025-08-29 20:27:00 - pico-train - INFO - ├── Learning Rate: 3.66e-05 2025-08-29 20:27:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:27:13 - pico-train - INFO - Step 12175 -- 🔄 Training Metrics 2025-08-29 20:27:13 - pico-train - INFO - ├── Loss: 6.5493 2025-08-29 20:27:13 - pico-train - INFO - ├── Learning Rate: 3.65e-05 2025-08-29 20:27:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:27:26 - pico-train - INFO - Step 12200 -- 🔄 Training Metrics 2025-08-29 20:27:26 - pico-train - INFO - ├── Loss: 6.5813 2025-08-29 20:27:26 - pico-train - INFO - ├── Learning Rate: 3.63e-05 2025-08-29 20:27:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:27:38 - pico-train - INFO - Step 12225 -- 🔄 Training Metrics 2025-08-29 20:27:38 - pico-train - INFO - ├── Loss: 6.5618 2025-08-29 20:27:38 - pico-train - INFO - ├── Learning Rate: 3.62e-05 2025-08-29 20:27:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:27:52 - pico-train - INFO - Step 12250 -- 🔄 Training Metrics 2025-08-29 20:27:52 - pico-train - INFO - ├── Loss: 6.5158 2025-08-29 20:27:52 - pico-train - INFO - ├── Learning Rate: 3.61e-05 2025-08-29 20:27:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:28:05 - pico-train - INFO - Step 12275 -- 🔄 Training Metrics 2025-08-29 20:28:05 - pico-train - INFO - ├── Loss: 6.6372 2025-08-29 20:28:05 - pico-train - INFO - ├── Learning Rate: 3.59e-05 2025-08-29 20:28:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:28:17 - pico-train - INFO - Step 12300 -- 🔄 Training Metrics 2025-08-29 20:28:17 - pico-train - INFO - ├── Loss: 6.6048 2025-08-29 20:28:17 - pico-train - INFO - ├── Learning Rate: 3.58e-05 2025-08-29 20:28:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:28:30 - pico-train - INFO - Step 12325 -- 🔄 Training Metrics 2025-08-29 20:28:30 - pico-train - INFO - ├── Loss: 6.4816 2025-08-29 20:28:30 - pico-train - INFO - ├── Learning Rate: 3.56e-05 2025-08-29 20:28:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:28:43 - pico-train - INFO - Step 12350 -- 🔄 Training Metrics 2025-08-29 20:28:43 - pico-train - INFO - ├── Loss: 6.5455 2025-08-29 20:28:43 - pico-train - INFO - ├── Learning Rate: 3.55e-05 2025-08-29 20:28:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:28:55 - pico-train - INFO - Step 12375 -- 🔄 Training Metrics 2025-08-29 20:28:55 - pico-train - INFO - ├── Loss: 6.6032 2025-08-29 20:28:55 - pico-train - INFO - ├── Learning Rate: 3.53e-05 2025-08-29 20:28:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:29:08 - pico-train - INFO - Step 12400 -- 🔄 Training Metrics 2025-08-29 20:29:08 - pico-train - INFO - ├── Loss: 6.5575 2025-08-29 20:29:08 - pico-train - INFO - ├── Learning Rate: 3.52e-05 2025-08-29 20:29:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:29:21 - pico-train - INFO - Step 12425 -- 🔄 Training Metrics 2025-08-29 20:29:21 - pico-train - INFO - ├── Loss: 6.5083 2025-08-29 20:29:21 - pico-train - INFO - ├── Learning Rate: 3.50e-05 2025-08-29 20:29:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:29:33 - pico-train - INFO - Step 12450 -- 🔄 Training Metrics 2025-08-29 20:29:33 - pico-train - INFO - ├── Loss: 6.5872 2025-08-29 20:29:33 - pico-train - INFO - ├── Learning Rate: 3.49e-05 2025-08-29 20:29:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:29:46 - pico-train - INFO - Step 12475 -- 🔄 Training Metrics 2025-08-29 20:29:46 - pico-train - INFO - ├── Loss: 6.5212 2025-08-29 20:29:46 - pico-train - INFO - ├── Learning Rate: 3.47e-05 2025-08-29 20:29:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:29:58 - pico-train - INFO - Step 12500 -- 💾 Saving Checkpoint 2025-08-29 20:32:08 - pico-train - INFO - Step 12500 -- 📊 Evaluation Results 2025-08-29 20:32:08 - pico-train - INFO - └── paloma: 1.6834857831717288e+23 2025-08-29 20:32:09 - pico-train - INFO - Step 12500 -- 🔄 Training Metrics 2025-08-29 20:32:09 - pico-train - INFO - ├── Loss: 6.5582 2025-08-29 20:32:09 - pico-train - INFO - ├── Learning Rate: 3.46e-05 2025-08-29 20:32:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:32:09 - pico-train - INFO - Step 12500 -- 📈 Saving Learning Dynamics 2025-08-29 20:32:24 - pico-train - INFO - Step 12525 -- 🔄 Training Metrics 2025-08-29 20:32:24 - pico-train - INFO - ├── Loss: 6.5608 2025-08-29 20:32:24 - pico-train - INFO - ├── Learning Rate: 3.44e-05 2025-08-29 20:32:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:32:37 - pico-train - INFO - Step 12550 -- 🔄 Training Metrics 2025-08-29 20:32:37 - pico-train - INFO - ├── Loss: 6.5180 2025-08-29 20:32:37 - pico-train - INFO - ├── Learning Rate: 3.43e-05 2025-08-29 20:32:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:32:49 - pico-train - INFO - Step 12575 -- 🔄 Training Metrics 2025-08-29 20:32:49 - pico-train - INFO - ├── Loss: 6.5553 2025-08-29 20:32:49 - pico-train - INFO - ├── Learning Rate: 3.41e-05 2025-08-29 20:32:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:33:02 - pico-train - INFO - Step 12600 -- 🔄 Training Metrics 2025-08-29 20:33:02 - pico-train - INFO - ├── Loss: 6.5012 2025-08-29 20:33:02 - pico-train - INFO - ├── Learning Rate: 3.40e-05 2025-08-29 20:33:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:33:14 - pico-train - INFO - Step 12625 -- 🔄 Training Metrics 2025-08-29 20:33:14 - pico-train - INFO - ├── Loss: 6.4864 2025-08-29 20:33:14 - pico-train - INFO - ├── Learning Rate: 3.38e-05 2025-08-29 20:33:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:33:27 - pico-train - INFO - Step 12650 -- 🔄 Training Metrics 2025-08-29 20:33:27 - pico-train - INFO - ├── Loss: 6.5061 2025-08-29 20:33:27 - pico-train - INFO - ├── Learning Rate: 3.37e-05 2025-08-29 20:33:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:33:40 - pico-train - INFO - Step 12675 -- 🔄 Training Metrics 2025-08-29 20:33:40 - pico-train - INFO - ├── Loss: 6.5794 2025-08-29 20:33:40 - pico-train - INFO - ├── Learning Rate: 3.35e-05 2025-08-29 20:33:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:33:52 - pico-train - INFO - Step 12700 -- 🔄 Training Metrics 2025-08-29 20:33:52 - pico-train - INFO - ├── Loss: 6.5345 2025-08-29 20:33:52 - pico-train - INFO - ├── Learning Rate: 3.33e-05 2025-08-29 20:33:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:34:05 - pico-train - INFO - Step 12725 -- 🔄 Training Metrics 2025-08-29 20:34:05 - pico-train - INFO - ├── Loss: 6.4304 2025-08-29 20:34:05 - pico-train - INFO - ├── Learning Rate: 3.32e-05 2025-08-29 20:34:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:34:18 - pico-train - INFO - Step 12750 -- 🔄 Training Metrics 2025-08-29 20:34:18 - pico-train - INFO - ├── Loss: 6.5336 2025-08-29 20:34:18 - pico-train - INFO - ├── Learning Rate: 3.30e-05 2025-08-29 20:34:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:34:31 - pico-train - INFO - Step 12775 -- 🔄 Training Metrics 2025-08-29 20:34:31 - pico-train - INFO - ├── Loss: 6.4534 2025-08-29 20:34:31 - pico-train - INFO - ├── Learning Rate: 3.29e-05 2025-08-29 20:34:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:34:43 - pico-train - INFO - Step 12800 -- 🔄 Training Metrics 2025-08-29 20:34:43 - pico-train - INFO - ├── Loss: 6.5394 2025-08-29 20:34:43 - pico-train - INFO - ├── Learning Rate: 3.27e-05 2025-08-29 20:34:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:34:56 - pico-train - INFO - Step 12825 -- 🔄 Training Metrics 2025-08-29 20:34:56 - pico-train - INFO - ├── Loss: 6.5892 2025-08-29 20:34:56 - pico-train - INFO - ├── Learning Rate: 3.26e-05 2025-08-29 20:34:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:35:09 - pico-train - INFO - Step 12850 -- 🔄 Training Metrics 2025-08-29 20:35:09 - pico-train - INFO - ├── Loss: 6.5827 2025-08-29 20:35:09 - pico-train - INFO - ├── Learning Rate: 3.24e-05 2025-08-29 20:35:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:35:22 - pico-train - INFO - Step 12875 -- 🔄 Training Metrics 2025-08-29 20:35:22 - pico-train - INFO - ├── Loss: 6.4602 2025-08-29 20:35:22 - pico-train - INFO - ├── Learning Rate: 3.23e-05 2025-08-29 20:35:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:35:35 - pico-train - INFO - Step 12900 -- 🔄 Training Metrics 2025-08-29 20:35:35 - pico-train - INFO - ├── Loss: 6.4629 2025-08-29 20:35:35 - pico-train - INFO - ├── Learning Rate: 3.21e-05 2025-08-29 20:35:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:35:47 - pico-train - INFO - Step 12925 -- 🔄 Training Metrics 2025-08-29 20:35:47 - pico-train - INFO - ├── Loss: 6.5758 2025-08-29 20:35:47 - pico-train - INFO - ├── Learning Rate: 3.19e-05 2025-08-29 20:35:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:36:00 - pico-train - INFO - Step 12950 -- 🔄 Training Metrics 2025-08-29 20:36:00 - pico-train - INFO - ├── Loss: 6.5234 2025-08-29 20:36:00 - pico-train - INFO - ├── Learning Rate: 3.18e-05 2025-08-29 20:36:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:36:12 - pico-train - INFO - Step 12975 -- 🔄 Training Metrics 2025-08-29 20:36:13 - pico-train - INFO - ├── Loss: 6.5186 2025-08-29 20:36:13 - pico-train - INFO - ├── Learning Rate: 3.16e-05 2025-08-29 20:36:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:36:25 - pico-train - INFO - Step 13000 -- 💾 Saving Checkpoint 2025-08-29 20:38:32 - pico-train - INFO - Step 13000 -- 📊 Evaluation Results 2025-08-29 20:38:32 - pico-train - INFO - └── paloma: 2.530184410087534e+23 2025-08-29 20:38:34 - pico-train - INFO - Step 13000 -- 🔄 Training Metrics 2025-08-29 20:38:34 - pico-train - INFO - ├── Loss: 6.5317 2025-08-29 20:38:34 - pico-train - INFO - ├── Learning Rate: 3.15e-05 2025-08-29 20:38:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:38:34 - pico-train - INFO - Step 13000 -- 📈 Saving Learning Dynamics 2025-08-29 20:38:49 - pico-train - INFO - Step 13025 -- 🔄 Training Metrics 2025-08-29 20:38:49 - pico-train - INFO - ├── Loss: 6.5595 2025-08-29 20:38:49 - pico-train - INFO - ├── Learning Rate: 3.13e-05 2025-08-29 20:38:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:39:01 - pico-train - INFO - Step 13050 -- 🔄 Training Metrics 2025-08-29 20:39:01 - pico-train - INFO - ├── Loss: 6.5374 2025-08-29 20:39:01 - pico-train - INFO - ├── Learning Rate: 3.12e-05 2025-08-29 20:39:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:39:14 - pico-train - INFO - Step 13075 -- 🔄 Training Metrics 2025-08-29 20:39:14 - pico-train - INFO - ├── Loss: 6.4943 2025-08-29 20:39:14 - pico-train - INFO - ├── Learning Rate: 3.10e-05 2025-08-29 20:39:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:39:26 - pico-train - INFO - Step 13100 -- 🔄 Training Metrics 2025-08-29 20:39:26 - pico-train - INFO - ├── Loss: 6.4770 2025-08-29 20:39:26 - pico-train - INFO - ├── Learning Rate: 3.08e-05 2025-08-29 20:39:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:39:39 - pico-train - INFO - Step 13125 -- 🔄 Training Metrics 2025-08-29 20:39:39 - pico-train - INFO - ├── Loss: 6.6083 2025-08-29 20:39:39 - pico-train - INFO - ├── Learning Rate: 3.07e-05 2025-08-29 20:39:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:39:52 - pico-train - INFO - Step 13150 -- 🔄 Training Metrics 2025-08-29 20:39:52 - pico-train - INFO - ├── Loss: 6.4500 2025-08-29 20:39:52 - pico-train - INFO - ├── Learning Rate: 3.05e-05 2025-08-29 20:39:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:40:04 - pico-train - INFO - Step 13175 -- 🔄 Training Metrics 2025-08-29 20:40:04 - pico-train - INFO - ├── Loss: 6.5230 2025-08-29 20:40:04 - pico-train - INFO - ├── Learning Rate: 3.04e-05 2025-08-29 20:40:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:40:17 - pico-train - INFO - Step 13200 -- 🔄 Training Metrics 2025-08-29 20:40:17 - pico-train - INFO - ├── Loss: 6.5150 2025-08-29 20:40:17 - pico-train - INFO - ├── Learning Rate: 3.02e-05 2025-08-29 20:40:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:40:29 - pico-train - INFO - Step 13225 -- 🔄 Training Metrics 2025-08-29 20:40:29 - pico-train - INFO - ├── Loss: 6.4379 2025-08-29 20:40:29 - pico-train - INFO - ├── Learning Rate: 3.00e-05 2025-08-29 20:40:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:40:43 - pico-train - INFO - Step 13250 -- 🔄 Training Metrics 2025-08-29 20:40:43 - pico-train - INFO - ├── Loss: 6.5261 2025-08-29 20:40:43 - pico-train - INFO - ├── Learning Rate: 2.99e-05 2025-08-29 20:40:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:40:56 - pico-train - INFO - Step 13275 -- 🔄 Training Metrics 2025-08-29 20:40:56 - pico-train - INFO - ├── Loss: 6.4582 2025-08-29 20:40:56 - pico-train - INFO - ├── Learning Rate: 2.97e-05 2025-08-29 20:40:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:41:08 - pico-train - INFO - Step 13300 -- 🔄 Training Metrics 2025-08-29 20:41:08 - pico-train - INFO - ├── Loss: 6.4420 2025-08-29 20:41:08 - pico-train - INFO - ├── Learning Rate: 2.96e-05 2025-08-29 20:41:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:41:21 - pico-train - INFO - Step 13325 -- 🔄 Training Metrics 2025-08-29 20:41:21 - pico-train - INFO - ├── Loss: 6.5268 2025-08-29 20:41:21 - pico-train - INFO - ├── Learning Rate: 2.94e-05 2025-08-29 20:41:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:41:34 - pico-train - INFO - Step 13350 -- 🔄 Training Metrics 2025-08-29 20:41:34 - pico-train - INFO - ├── Loss: 6.4300 2025-08-29 20:41:34 - pico-train - INFO - ├── Learning Rate: 2.92e-05 2025-08-29 20:41:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:41:46 - pico-train - INFO - Step 13375 -- 🔄 Training Metrics 2025-08-29 20:41:46 - pico-train - INFO - ├── Loss: 6.4366 2025-08-29 20:41:46 - pico-train - INFO - ├── Learning Rate: 2.91e-05 2025-08-29 20:41:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:41:59 - pico-train - INFO - Step 13400 -- 🔄 Training Metrics 2025-08-29 20:41:59 - pico-train - INFO - ├── Loss: 6.5664 2025-08-29 20:41:59 - pico-train - INFO - ├── Learning Rate: 2.89e-05 2025-08-29 20:41:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:42:11 - pico-train - INFO - Step 13425 -- 🔄 Training Metrics 2025-08-29 20:42:11 - pico-train - INFO - ├── Loss: 6.5522 2025-08-29 20:42:11 - pico-train - INFO - ├── Learning Rate: 2.87e-05 2025-08-29 20:42:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:42:24 - pico-train - INFO - Step 13450 -- 🔄 Training Metrics 2025-08-29 20:42:24 - pico-train - INFO - ├── Loss: 6.4326 2025-08-29 20:42:24 - pico-train - INFO - ├── Learning Rate: 2.86e-05 2025-08-29 20:42:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:42:36 - pico-train - INFO - Step 13475 -- 🔄 Training Metrics 2025-08-29 20:42:36 - pico-train - INFO - ├── Loss: 6.4898 2025-08-29 20:42:36 - pico-train - INFO - ├── Learning Rate: 2.84e-05 2025-08-29 20:42:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:42:49 - pico-train - INFO - Step 13500 -- 💾 Saving Checkpoint 2025-08-29 20:44:58 - pico-train - INFO - Step 13500 -- 📊 Evaluation Results 2025-08-29 20:44:58 - pico-train - INFO - └── paloma: 3.495795801566584e+23 2025-08-29 20:45:00 - pico-train - INFO - Step 13500 -- 🔄 Training Metrics 2025-08-29 20:45:00 - pico-train - INFO - ├── Loss: 6.4517 2025-08-29 20:45:00 - pico-train - INFO - ├── Learning Rate: 2.83e-05 2025-08-29 20:45:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:45:00 - pico-train - INFO - Step 13500 -- 📈 Saving Learning Dynamics 2025-08-29 20:45:16 - pico-train - INFO - Step 13525 -- 🔄 Training Metrics 2025-08-29 20:45:16 - pico-train - INFO - ├── Loss: 6.4512 2025-08-29 20:45:16 - pico-train - INFO - ├── Learning Rate: 2.81e-05 2025-08-29 20:45:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:45:28 - pico-train - INFO - Step 13550 -- 🔄 Training Metrics 2025-08-29 20:45:28 - pico-train - INFO - ├── Loss: 6.4535 2025-08-29 20:45:28 - pico-train - INFO - ├── Learning Rate: 2.79e-05 2025-08-29 20:45:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:45:41 - pico-train - INFO - Step 13575 -- 🔄 Training Metrics 2025-08-29 20:45:41 - pico-train - INFO - ├── Loss: 6.5099 2025-08-29 20:45:41 - pico-train - INFO - ├── Learning Rate: 2.78e-05 2025-08-29 20:45:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:45:53 - pico-train - INFO - Step 13600 -- 🔄 Training Metrics 2025-08-29 20:45:53 - pico-train - INFO - ├── Loss: 6.4340 2025-08-29 20:45:53 - pico-train - INFO - ├── Learning Rate: 2.76e-05 2025-08-29 20:45:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:46:06 - pico-train - INFO - Step 13625 -- 🔄 Training Metrics 2025-08-29 20:46:06 - pico-train - INFO - ├── Loss: 6.4295 2025-08-29 20:46:06 - pico-train - INFO - ├── Learning Rate: 2.75e-05 2025-08-29 20:46:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:46:18 - pico-train - INFO - Step 13650 -- 🔄 Training Metrics 2025-08-29 20:46:18 - pico-train - INFO - ├── Loss: 6.3784 2025-08-29 20:46:18 - pico-train - INFO - ├── Learning Rate: 2.73e-05 2025-08-29 20:46:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:46:31 - pico-train - INFO - Step 13675 -- 🔄 Training Metrics 2025-08-29 20:46:31 - pico-train - INFO - ├── Loss: 6.5333 2025-08-29 20:46:31 - pico-train - INFO - ├── Learning Rate: 2.71e-05 2025-08-29 20:46:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:46:44 - pico-train - INFO - Step 13700 -- 🔄 Training Metrics 2025-08-29 20:46:44 - pico-train - INFO - ├── Loss: 6.5142 2025-08-29 20:46:44 - pico-train - INFO - ├── Learning Rate: 2.70e-05 2025-08-29 20:46:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:46:56 - pico-train - INFO - Step 13725 -- 🔄 Training Metrics 2025-08-29 20:46:56 - pico-train - INFO - ├── Loss: 6.4840 2025-08-29 20:46:56 - pico-train - INFO - ├── Learning Rate: 2.68e-05 2025-08-29 20:46:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:47:10 - pico-train - INFO - Step 13750 -- 🔄 Training Metrics 2025-08-29 20:47:10 - pico-train - INFO - ├── Loss: 6.4268 2025-08-29 20:47:10 - pico-train - INFO - ├── Learning Rate: 2.66e-05 2025-08-29 20:47:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:47:22 - pico-train - INFO - Step 13775 -- 🔄 Training Metrics 2025-08-29 20:47:22 - pico-train - INFO - ├── Loss: 6.4121 2025-08-29 20:47:22 - pico-train - INFO - ├── Learning Rate: 2.65e-05 2025-08-29 20:47:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:47:35 - pico-train - INFO - Step 13800 -- 🔄 Training Metrics 2025-08-29 20:47:35 - pico-train - INFO - ├── Loss: 6.4483 2025-08-29 20:47:35 - pico-train - INFO - ├── Learning Rate: 2.63e-05 2025-08-29 20:47:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:47:48 - pico-train - INFO - Step 13825 -- 🔄 Training Metrics 2025-08-29 20:47:48 - pico-train - INFO - ├── Loss: 6.4498 2025-08-29 20:47:48 - pico-train - INFO - ├── Learning Rate: 2.61e-05 2025-08-29 20:47:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:48:00 - pico-train - INFO - Step 13850 -- 🔄 Training Metrics 2025-08-29 20:48:00 - pico-train - INFO - ├── Loss: 6.4725 2025-08-29 20:48:00 - pico-train - INFO - ├── Learning Rate: 2.60e-05 2025-08-29 20:48:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:48:13 - pico-train - INFO - Step 13875 -- 🔄 Training Metrics 2025-08-29 20:48:13 - pico-train - INFO - ├── Loss: 6.4732 2025-08-29 20:48:13 - pico-train - INFO - ├── Learning Rate: 2.58e-05 2025-08-29 20:48:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:48:26 - pico-train - INFO - Step 13900 -- 🔄 Training Metrics 2025-08-29 20:48:26 - pico-train - INFO - ├── Loss: 6.3980 2025-08-29 20:48:26 - pico-train - INFO - ├── Learning Rate: 2.57e-05 2025-08-29 20:48:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:48:38 - pico-train - INFO - Step 13925 -- 🔄 Training Metrics 2025-08-29 20:48:38 - pico-train - INFO - ├── Loss: 6.4906 2025-08-29 20:48:38 - pico-train - INFO - ├── Learning Rate: 2.55e-05 2025-08-29 20:48:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:48:51 - pico-train - INFO - Step 13950 -- 🔄 Training Metrics 2025-08-29 20:48:51 - pico-train - INFO - ├── Loss: 6.4096 2025-08-29 20:48:51 - pico-train - INFO - ├── Learning Rate: 2.53e-05 2025-08-29 20:48:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:49:04 - pico-train - INFO - Step 13975 -- 🔄 Training Metrics 2025-08-29 20:49:04 - pico-train - INFO - ├── Loss: 6.4280 2025-08-29 20:49:04 - pico-train - INFO - ├── Learning Rate: 2.52e-05 2025-08-29 20:49:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:49:16 - pico-train - INFO - Step 14000 -- 💾 Saving Checkpoint 2025-08-29 20:51:14 - pico-train - INFO - Step 14000 -- 📊 Evaluation Results 2025-08-29 20:51:14 - pico-train - INFO - └── paloma: 4.7779579346961524e+23 2025-08-29 20:51:17 - pico-train - INFO - Step 14000 -- 🔄 Training Metrics 2025-08-29 20:51:17 - pico-train - INFO - ├── Loss: 6.3189 2025-08-29 20:51:17 - pico-train - INFO - ├── Learning Rate: 2.50e-05 2025-08-29 20:51:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:51:17 - pico-train - INFO - Step 14000 -- 📈 Saving Learning Dynamics 2025-08-29 20:51:33 - pico-train - INFO - Step 14025 -- 🔄 Training Metrics 2025-08-29 20:51:33 - pico-train - INFO - ├── Loss: 6.4994 2025-08-29 20:51:33 - pico-train - INFO - ├── Learning Rate: 2.48e-05 2025-08-29 20:51:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:51:45 - pico-train - INFO - Step 14050 -- 🔄 Training Metrics 2025-08-29 20:51:45 - pico-train - INFO - ├── Loss: 6.4802 2025-08-29 20:51:45 - pico-train - INFO - ├── Learning Rate: 2.47e-05 2025-08-29 20:51:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:51:58 - pico-train - INFO - Step 14075 -- 🔄 Training Metrics 2025-08-29 20:51:58 - pico-train - INFO - ├── Loss: 6.5178 2025-08-29 20:51:58 - pico-train - INFO - ├── Learning Rate: 2.45e-05 2025-08-29 20:51:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:52:11 - pico-train - INFO - Step 14100 -- 🔄 Training Metrics 2025-08-29 20:52:11 - pico-train - INFO - ├── Loss: 6.4472 2025-08-29 20:52:11 - pico-train - INFO - ├── Learning Rate: 2.43e-05 2025-08-29 20:52:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:52:23 - pico-train - INFO - Step 14125 -- 🔄 Training Metrics 2025-08-29 20:52:23 - pico-train - INFO - ├── Loss: 6.5737 2025-08-29 20:52:23 - pico-train - INFO - ├── Learning Rate: 2.42e-05 2025-08-29 20:52:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:52:36 - pico-train - INFO - Step 14150 -- 🔄 Training Metrics 2025-08-29 20:52:36 - pico-train - INFO - ├── Loss: 6.4612 2025-08-29 20:52:36 - pico-train - INFO - ├── Learning Rate: 2.40e-05 2025-08-29 20:52:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:52:48 - pico-train - INFO - Step 14175 -- 🔄 Training Metrics 2025-08-29 20:52:48 - pico-train - INFO - ├── Loss: 6.4352 2025-08-29 20:52:48 - pico-train - INFO - ├── Learning Rate: 2.39e-05 2025-08-29 20:52:48 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:53:01 - pico-train - INFO - Step 14200 -- 🔄 Training Metrics 2025-08-29 20:53:01 - pico-train - INFO - ├── Loss: 6.5225 2025-08-29 20:53:01 - pico-train - INFO - ├── Learning Rate: 2.37e-05 2025-08-29 20:53:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:53:13 - pico-train - INFO - Step 14225 -- 🔄 Training Metrics 2025-08-29 20:53:13 - pico-train - INFO - ├── Loss: 6.4075 2025-08-29 20:53:13 - pico-train - INFO - ├── Learning Rate: 2.35e-05 2025-08-29 20:53:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:53:27 - pico-train - INFO - Step 14250 -- 🔄 Training Metrics 2025-08-29 20:53:27 - pico-train - INFO - ├── Loss: 6.4283 2025-08-29 20:53:27 - pico-train - INFO - ├── Learning Rate: 2.34e-05 2025-08-29 20:53:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:53:40 - pico-train - INFO - Step 14275 -- 🔄 Training Metrics 2025-08-29 20:53:40 - pico-train - INFO - ├── Loss: 6.4336 2025-08-29 20:53:40 - pico-train - INFO - ├── Learning Rate: 2.32e-05 2025-08-29 20:53:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:53:53 - pico-train - INFO - Step 14300 -- 🔄 Training Metrics 2025-08-29 20:53:53 - pico-train - INFO - ├── Loss: 6.4139 2025-08-29 20:53:53 - pico-train - INFO - ├── Learning Rate: 2.30e-05 2025-08-29 20:53:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:54:05 - pico-train - INFO - Step 14325 -- 🔄 Training Metrics 2025-08-29 20:54:05 - pico-train - INFO - ├── Loss: 6.5305 2025-08-29 20:54:05 - pico-train - INFO - ├── Learning Rate: 2.29e-05 2025-08-29 20:54:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:54:18 - pico-train - INFO - Step 14350 -- 🔄 Training Metrics 2025-08-29 20:54:18 - pico-train - INFO - ├── Loss: 6.4196 2025-08-29 20:54:18 - pico-train - INFO - ├── Learning Rate: 2.27e-05 2025-08-29 20:54:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:54:30 - pico-train - INFO - Step 14375 -- 🔄 Training Metrics 2025-08-29 20:54:30 - pico-train - INFO - ├── Loss: 6.5622 2025-08-29 20:54:30 - pico-train - INFO - ├── Learning Rate: 2.25e-05 2025-08-29 20:54:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:54:43 - pico-train - INFO - Step 14400 -- 🔄 Training Metrics 2025-08-29 20:54:43 - pico-train - INFO - ├── Loss: 6.4562 2025-08-29 20:54:43 - pico-train - INFO - ├── Learning Rate: 2.24e-05 2025-08-29 20:54:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:54:55 - pico-train - INFO - Step 14425 -- 🔄 Training Metrics 2025-08-29 20:54:55 - pico-train - INFO - ├── Loss: 6.3897 2025-08-29 20:54:55 - pico-train - INFO - ├── Learning Rate: 2.22e-05 2025-08-29 20:54:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:55:08 - pico-train - INFO - Step 14450 -- 🔄 Training Metrics 2025-08-29 20:55:08 - pico-train - INFO - ├── Loss: 6.4705 2025-08-29 20:55:08 - pico-train - INFO - ├── Learning Rate: 2.21e-05 2025-08-29 20:55:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:55:21 - pico-train - INFO - Step 14475 -- 🔄 Training Metrics 2025-08-29 20:55:21 - pico-train - INFO - ├── Loss: 6.4615 2025-08-29 20:55:21 - pico-train - INFO - ├── Learning Rate: 2.19e-05 2025-08-29 20:55:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:55:33 - pico-train - INFO - Step 14500 -- 💾 Saving Checkpoint 2025-08-29 20:58:09 - pico-train - INFO - Step 14500 -- 📊 Evaluation Results 2025-08-29 20:58:09 - pico-train - INFO - └── paloma: 6.36811357145983e+23 2025-08-29 20:58:11 - pico-train - INFO - Step 14500 -- 🔄 Training Metrics 2025-08-29 20:58:11 - pico-train - INFO - ├── Loss: 6.4280 2025-08-29 20:58:11 - pico-train - INFO - ├── Learning Rate: 2.17e-05 2025-08-29 20:58:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:58:11 - pico-train - INFO - Step 14500 -- 📈 Saving Learning Dynamics 2025-08-29 20:58:27 - pico-train - INFO - Step 14525 -- 🔄 Training Metrics 2025-08-29 20:58:27 - pico-train - INFO - ├── Loss: 6.4418 2025-08-29 20:58:27 - pico-train - INFO - ├── Learning Rate: 2.16e-05 2025-08-29 20:58:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:58:39 - pico-train - INFO - Step 14550 -- 🔄 Training Metrics 2025-08-29 20:58:39 - pico-train - INFO - ├── Loss: 6.5223 2025-08-29 20:58:39 - pico-train - INFO - ├── Learning Rate: 2.14e-05 2025-08-29 20:58:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:58:52 - pico-train - INFO - Step 14575 -- 🔄 Training Metrics 2025-08-29 20:58:52 - pico-train - INFO - ├── Loss: 6.4231 2025-08-29 20:58:52 - pico-train - INFO - ├── Learning Rate: 2.13e-05 2025-08-29 20:58:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:59:04 - pico-train - INFO - Step 14600 -- 🔄 Training Metrics 2025-08-29 20:59:04 - pico-train - INFO - ├── Loss: 6.4879 2025-08-29 20:59:04 - pico-train - INFO - ├── Learning Rate: 2.11e-05 2025-08-29 20:59:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:59:17 - pico-train - INFO - Step 14625 -- 🔄 Training Metrics 2025-08-29 20:59:17 - pico-train - INFO - ├── Loss: 6.4622 2025-08-29 20:59:17 - pico-train - INFO - ├── Learning Rate: 2.09e-05 2025-08-29 20:59:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:59:30 - pico-train - INFO - Step 14650 -- 🔄 Training Metrics 2025-08-29 20:59:30 - pico-train - INFO - ├── Loss: 6.3997 2025-08-29 20:59:30 - pico-train - INFO - ├── Learning Rate: 2.08e-05 2025-08-29 20:59:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:59:42 - pico-train - INFO - Step 14675 -- 🔄 Training Metrics 2025-08-29 20:59:42 - pico-train - INFO - ├── Loss: 6.5009 2025-08-29 20:59:42 - pico-train - INFO - ├── Learning Rate: 2.06e-05 2025-08-29 20:59:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 20:59:55 - pico-train - INFO - Step 14700 -- 🔄 Training Metrics 2025-08-29 20:59:55 - pico-train - INFO - ├── Loss: 6.4203 2025-08-29 20:59:55 - pico-train - INFO - ├── Learning Rate: 2.04e-05 2025-08-29 20:59:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:00:08 - pico-train - INFO - Step 14725 -- 🔄 Training Metrics 2025-08-29 21:00:08 - pico-train - INFO - ├── Loss: 6.4063 2025-08-29 21:00:08 - pico-train - INFO - ├── Learning Rate: 2.03e-05 2025-08-29 21:00:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:00:21 - pico-train - INFO - Step 14750 -- 🔄 Training Metrics 2025-08-29 21:00:21 - pico-train - INFO - ├── Loss: 6.4672 2025-08-29 21:00:21 - pico-train - INFO - ├── Learning Rate: 2.01e-05 2025-08-29 21:00:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:00:34 - pico-train - INFO - Step 14775 -- 🔄 Training Metrics 2025-08-29 21:00:34 - pico-train - INFO - ├── Loss: 6.5252 2025-08-29 21:00:34 - pico-train - INFO - ├── Learning Rate: 2.00e-05 2025-08-29 21:00:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:00:47 - pico-train - INFO - Step 14800 -- 🔄 Training Metrics 2025-08-29 21:00:47 - pico-train - INFO - ├── Loss: 6.5220 2025-08-29 21:00:47 - pico-train - INFO - ├── Learning Rate: 1.98e-05 2025-08-29 21:00:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:00:59 - pico-train - INFO - Step 14825 -- 🔄 Training Metrics 2025-08-29 21:00:59 - pico-train - INFO - ├── Loss: 6.4118 2025-08-29 21:00:59 - pico-train - INFO - ├── Learning Rate: 1.96e-05 2025-08-29 21:00:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:01:12 - pico-train - INFO - Step 14850 -- 🔄 Training Metrics 2025-08-29 21:01:12 - pico-train - INFO - ├── Loss: 6.4979 2025-08-29 21:01:12 - pico-train - INFO - ├── Learning Rate: 1.95e-05 2025-08-29 21:01:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:01:24 - pico-train - INFO - Step 14875 -- 🔄 Training Metrics 2025-08-29 21:01:24 - pico-train - INFO - ├── Loss: 6.4114 2025-08-29 21:01:24 - pico-train - INFO - ├── Learning Rate: 1.93e-05 2025-08-29 21:01:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:01:37 - pico-train - INFO - Step 14900 -- 🔄 Training Metrics 2025-08-29 21:01:37 - pico-train - INFO - ├── Loss: 6.4437 2025-08-29 21:01:37 - pico-train - INFO - ├── Learning Rate: 1.92e-05 2025-08-29 21:01:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:01:49 - pico-train - INFO - Step 14925 -- 🔄 Training Metrics 2025-08-29 21:01:49 - pico-train - INFO - ├── Loss: 6.5580 2025-08-29 21:01:49 - pico-train - INFO - ├── Learning Rate: 1.90e-05 2025-08-29 21:01:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:02:02 - pico-train - INFO - Step 14950 -- 🔄 Training Metrics 2025-08-29 21:02:02 - pico-train - INFO - ├── Loss: 6.4578 2025-08-29 21:02:02 - pico-train - INFO - ├── Learning Rate: 1.88e-05 2025-08-29 21:02:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:02:15 - pico-train - INFO - Step 14975 -- 🔄 Training Metrics 2025-08-29 21:02:15 - pico-train - INFO - ├── Loss: 6.4092 2025-08-29 21:02:15 - pico-train - INFO - ├── Learning Rate: 1.87e-05 2025-08-29 21:02:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:02:27 - pico-train - INFO - Step 15000 -- 💾 Saving Checkpoint 2025-08-29 21:06:10 - pico-train - INFO - Step 15000 -- 📊 Evaluation Results 2025-08-29 21:06:10 - pico-train - INFO - └── paloma: 7.425894520816826e+23 2025-08-29 21:06:12 - pico-train - INFO - Step 15000 -- 🔄 Training Metrics 2025-08-29 21:06:12 - pico-train - INFO - ├── Loss: 6.5556 2025-08-29 21:06:12 - pico-train - INFO - ├── Learning Rate: 1.85e-05 2025-08-29 21:06:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:06:12 - pico-train - INFO - Step 15000 -- 📈 Saving Learning Dynamics 2025-08-29 21:06:28 - pico-train - INFO - Step 15025 -- 🔄 Training Metrics 2025-08-29 21:06:28 - pico-train - INFO - ├── Loss: 6.5084 2025-08-29 21:06:28 - pico-train - INFO - ├── Learning Rate: 1.84e-05 2025-08-29 21:06:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:06:41 - pico-train - INFO - Step 15050 -- 🔄 Training Metrics 2025-08-29 21:06:41 - pico-train - INFO - ├── Loss: 6.4875 2025-08-29 21:06:41 - pico-train - INFO - ├── Learning Rate: 1.82e-05 2025-08-29 21:06:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:06:53 - pico-train - INFO - Step 15075 -- 🔄 Training Metrics 2025-08-29 21:06:53 - pico-train - INFO - ├── Loss: 6.4415 2025-08-29 21:06:53 - pico-train - INFO - ├── Learning Rate: 1.81e-05 2025-08-29 21:06:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:07:06 - pico-train - INFO - Step 15100 -- 🔄 Training Metrics 2025-08-29 21:07:06 - pico-train - INFO - ├── Loss: 6.4890 2025-08-29 21:07:06 - pico-train - INFO - ├── Learning Rate: 1.79e-05 2025-08-29 21:07:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:07:18 - pico-train - INFO - Step 15125 -- 🔄 Training Metrics 2025-08-29 21:07:18 - pico-train - INFO - ├── Loss: 6.4124 2025-08-29 21:07:18 - pico-train - INFO - ├── Learning Rate: 1.77e-05 2025-08-29 21:07:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:07:31 - pico-train - INFO - Step 15150 -- 🔄 Training Metrics 2025-08-29 21:07:31 - pico-train - INFO - ├── Loss: 6.3762 2025-08-29 21:07:31 - pico-train - INFO - ├── Learning Rate: 1.76e-05 2025-08-29 21:07:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:07:43 - pico-train - INFO - Step 15175 -- 🔄 Training Metrics 2025-08-29 21:07:43 - pico-train - INFO - ├── Loss: 6.4269 2025-08-29 21:07:43 - pico-train - INFO - ├── Learning Rate: 1.74e-05 2025-08-29 21:07:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:07:56 - pico-train - INFO - Step 15200 -- 🔄 Training Metrics 2025-08-29 21:07:56 - pico-train - INFO - ├── Loss: 6.4523 2025-08-29 21:07:56 - pico-train - INFO - ├── Learning Rate: 1.73e-05 2025-08-29 21:07:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:08:09 - pico-train - INFO - Step 15225 -- 🔄 Training Metrics 2025-08-29 21:08:09 - pico-train - INFO - ├── Loss: 6.4065 2025-08-29 21:08:09 - pico-train - INFO - ├── Learning Rate: 1.71e-05 2025-08-29 21:08:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:08:22 - pico-train - INFO - Step 15250 -- 🔄 Training Metrics 2025-08-29 21:08:22 - pico-train - INFO - ├── Loss: 6.4635 2025-08-29 21:08:22 - pico-train - INFO - ├── Learning Rate: 1.70e-05 2025-08-29 21:08:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:08:35 - pico-train - INFO - Step 15275 -- 🔄 Training Metrics 2025-08-29 21:08:35 - pico-train - INFO - ├── Loss: 6.4213 2025-08-29 21:08:35 - pico-train - INFO - ├── Learning Rate: 1.68e-05 2025-08-29 21:08:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:08:47 - pico-train - INFO - Step 15300 -- 🔄 Training Metrics 2025-08-29 21:08:47 - pico-train - INFO - ├── Loss: 6.4003 2025-08-29 21:08:47 - pico-train - INFO - ├── Learning Rate: 1.67e-05 2025-08-29 21:08:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:09:00 - pico-train - INFO - Step 15325 -- 🔄 Training Metrics 2025-08-29 21:09:00 - pico-train - INFO - ├── Loss: 6.3599 2025-08-29 21:09:00 - pico-train - INFO - ├── Learning Rate: 1.65e-05 2025-08-29 21:09:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:09:12 - pico-train - INFO - Step 15350 -- 🔄 Training Metrics 2025-08-29 21:09:12 - pico-train - INFO - ├── Loss: 6.4026 2025-08-29 21:09:12 - pico-train - INFO - ├── Learning Rate: 1.63e-05 2025-08-29 21:09:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:09:26 - pico-train - INFO - Step 15375 -- 🔄 Training Metrics 2025-08-29 21:09:26 - pico-train - INFO - ├── Loss: 6.4583 2025-08-29 21:09:26 - pico-train - INFO - ├── Learning Rate: 1.62e-05 2025-08-29 21:09:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:09:39 - pico-train - INFO - Step 15400 -- 🔄 Training Metrics 2025-08-29 21:09:39 - pico-train - INFO - ├── Loss: 6.3811 2025-08-29 21:09:39 - pico-train - INFO - ├── Learning Rate: 1.60e-05 2025-08-29 21:09:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:09:51 - pico-train - INFO - Step 15425 -- 🔄 Training Metrics 2025-08-29 21:09:51 - pico-train - INFO - ├── Loss: 6.4031 2025-08-29 21:09:51 - pico-train - INFO - ├── Learning Rate: 1.59e-05 2025-08-29 21:09:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:10:04 - pico-train - INFO - Step 15450 -- 🔄 Training Metrics 2025-08-29 21:10:04 - pico-train - INFO - ├── Loss: 6.4722 2025-08-29 21:10:04 - pico-train - INFO - ├── Learning Rate: 1.57e-05 2025-08-29 21:10:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:10:17 - pico-train - INFO - Step 15475 -- 🔄 Training Metrics 2025-08-29 21:10:17 - pico-train - INFO - ├── Loss: 6.4515 2025-08-29 21:10:17 - pico-train - INFO - ├── Learning Rate: 1.56e-05 2025-08-29 21:10:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:10:29 - pico-train - INFO - Step 15500 -- 💾 Saving Checkpoint 2025-08-29 21:12:31 - pico-train - INFO - Step 15500 -- 📊 Evaluation Results 2025-08-29 21:12:31 - pico-train - INFO - └── paloma: 8.24811762866625e+23 2025-08-29 21:12:32 - pico-train - INFO - Step 15500 -- 🔄 Training Metrics 2025-08-29 21:12:32 - pico-train - INFO - ├── Loss: 6.5211 2025-08-29 21:12:32 - pico-train - INFO - ├── Learning Rate: 1.54e-05 2025-08-29 21:12:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:12:32 - pico-train - INFO - Step 15500 -- 📈 Saving Learning Dynamics 2025-08-29 21:12:47 - pico-train - INFO - Step 15525 -- 🔄 Training Metrics 2025-08-29 21:12:47 - pico-train - INFO - ├── Loss: 6.3531 2025-08-29 21:12:47 - pico-train - INFO - ├── Learning Rate: 1.53e-05 2025-08-29 21:12:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:13:00 - pico-train - INFO - Step 15550 -- 🔄 Training Metrics 2025-08-29 21:13:00 - pico-train - INFO - ├── Loss: 6.4191 2025-08-29 21:13:00 - pico-train - INFO - ├── Learning Rate: 1.51e-05 2025-08-29 21:13:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:13:12 - pico-train - INFO - Step 15575 -- 🔄 Training Metrics 2025-08-29 21:13:12 - pico-train - INFO - ├── Loss: 6.3696 2025-08-29 21:13:12 - pico-train - INFO - ├── Learning Rate: 1.50e-05 2025-08-29 21:13:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:13:25 - pico-train - INFO - Step 15600 -- 🔄 Training Metrics 2025-08-29 21:13:25 - pico-train - INFO - ├── Loss: 6.3854 2025-08-29 21:13:25 - pico-train - INFO - ├── Learning Rate: 1.48e-05 2025-08-29 21:13:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:13:38 - pico-train - INFO - Step 15625 -- 🔄 Training Metrics 2025-08-29 21:13:38 - pico-train - INFO - ├── Loss: 6.4512 2025-08-29 21:13:38 - pico-train - INFO - ├── Learning Rate: 1.47e-05 2025-08-29 21:13:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:13:50 - pico-train - INFO - Step 15650 -- 🔄 Training Metrics 2025-08-29 21:13:50 - pico-train - INFO - ├── Loss: 6.4353 2025-08-29 21:13:50 - pico-train - INFO - ├── Learning Rate: 1.45e-05 2025-08-29 21:13:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:14:03 - pico-train - INFO - Step 15675 -- 🔄 Training Metrics 2025-08-29 21:14:03 - pico-train - INFO - ├── Loss: 6.4748 2025-08-29 21:14:03 - pico-train - INFO - ├── Learning Rate: 1.44e-05 2025-08-29 21:14:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:14:15 - pico-train - INFO - Step 15700 -- 🔄 Training Metrics 2025-08-29 21:14:15 - pico-train - INFO - ├── Loss: 6.4150 2025-08-29 21:14:15 - pico-train - INFO - ├── Learning Rate: 1.42e-05 2025-08-29 21:14:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:14:28 - pico-train - INFO - Step 15725 -- 🔄 Training Metrics 2025-08-29 21:14:28 - pico-train - INFO - ├── Loss: 6.4840 2025-08-29 21:14:28 - pico-train - INFO - ├── Learning Rate: 1.41e-05 2025-08-29 21:14:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:14:40 - pico-train - INFO - Step 15750 -- 🔄 Training Metrics 2025-08-29 21:14:40 - pico-train - INFO - ├── Loss: 6.3685 2025-08-29 21:14:40 - pico-train - INFO - ├── Learning Rate: 1.39e-05 2025-08-29 21:14:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:14:53 - pico-train - INFO - Step 15775 -- 🔄 Training Metrics 2025-08-29 21:14:53 - pico-train - INFO - ├── Loss: 6.4182 2025-08-29 21:14:53 - pico-train - INFO - ├── Learning Rate: 1.38e-05 2025-08-29 21:14:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:15:06 - pico-train - INFO - Step 15800 -- 🔄 Training Metrics 2025-08-29 21:15:06 - pico-train - INFO - ├── Loss: 6.4032 2025-08-29 21:15:06 - pico-train - INFO - ├── Learning Rate: 1.37e-05 2025-08-29 21:15:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:15:18 - pico-train - INFO - Step 15825 -- 🔄 Training Metrics 2025-08-29 21:15:18 - pico-train - INFO - ├── Loss: 6.5306 2025-08-29 21:15:18 - pico-train - INFO - ├── Learning Rate: 1.35e-05 2025-08-29 21:15:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:15:31 - pico-train - INFO - Step 15850 -- 🔄 Training Metrics 2025-08-29 21:15:31 - pico-train - INFO - ├── Loss: 6.4199 2025-08-29 21:15:31 - pico-train - INFO - ├── Learning Rate: 1.34e-05 2025-08-29 21:15:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:15:44 - pico-train - INFO - Step 15875 -- 🔄 Training Metrics 2025-08-29 21:15:44 - pico-train - INFO - ├── Loss: 6.3861 2025-08-29 21:15:44 - pico-train - INFO - ├── Learning Rate: 1.32e-05 2025-08-29 21:15:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:15:57 - pico-train - INFO - Step 15900 -- 🔄 Training Metrics 2025-08-29 21:15:57 - pico-train - INFO - ├── Loss: 6.4234 2025-08-29 21:15:57 - pico-train - INFO - ├── Learning Rate: 1.31e-05 2025-08-29 21:15:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:16:09 - pico-train - INFO - Step 15925 -- 🔄 Training Metrics 2025-08-29 21:16:09 - pico-train - INFO - ├── Loss: 6.3634 2025-08-29 21:16:09 - pico-train - INFO - ├── Learning Rate: 1.29e-05 2025-08-29 21:16:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:16:22 - pico-train - INFO - Step 15950 -- 🔄 Training Metrics 2025-08-29 21:16:22 - pico-train - INFO - ├── Loss: 6.3444 2025-08-29 21:16:22 - pico-train - INFO - ├── Learning Rate: 1.28e-05 2025-08-29 21:16:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:16:35 - pico-train - INFO - Step 15975 -- 🔄 Training Metrics 2025-08-29 21:16:35 - pico-train - INFO - ├── Loss: 6.5188 2025-08-29 21:16:35 - pico-train - INFO - ├── Learning Rate: 1.26e-05 2025-08-29 21:16:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:16:47 - pico-train - INFO - Step 16000 -- 💾 Saving Checkpoint 2025-08-29 21:19:08 - pico-train - INFO - Step 16000 -- 📊 Evaluation Results 2025-08-29 21:19:08 - pico-train - INFO - └── paloma: 1.1206091008496824e+24 2025-08-29 21:19:11 - pico-train - INFO - Step 16000 -- 🔄 Training Metrics 2025-08-29 21:19:11 - pico-train - INFO - ├── Loss: 6.4775 2025-08-29 21:19:11 - pico-train - INFO - ├── Learning Rate: 1.25e-05 2025-08-29 21:19:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:19:11 - pico-train - INFO - Step 16000 -- 📈 Saving Learning Dynamics 2025-08-29 21:19:27 - pico-train - INFO - Step 16025 -- 🔄 Training Metrics 2025-08-29 21:19:27 - pico-train - INFO - ├── Loss: 6.4575 2025-08-29 21:19:27 - pico-train - INFO - ├── Learning Rate: 1.24e-05 2025-08-29 21:19:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:19:39 - pico-train - INFO - Step 16050 -- 🔄 Training Metrics 2025-08-29 21:19:39 - pico-train - INFO - ├── Loss: 6.4128 2025-08-29 21:19:39 - pico-train - INFO - ├── Learning Rate: 1.22e-05 2025-08-29 21:19:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:19:52 - pico-train - INFO - Step 16075 -- 🔄 Training Metrics 2025-08-29 21:19:52 - pico-train - INFO - ├── Loss: 6.3496 2025-08-29 21:19:52 - pico-train - INFO - ├── Learning Rate: 1.21e-05 2025-08-29 21:19:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:20:05 - pico-train - INFO - Step 16100 -- 🔄 Training Metrics 2025-08-29 21:20:05 - pico-train - INFO - ├── Loss: 6.3495 2025-08-29 21:20:05 - pico-train - INFO - ├── Learning Rate: 1.19e-05 2025-08-29 21:20:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:20:17 - pico-train - INFO - Step 16125 -- 🔄 Training Metrics 2025-08-29 21:20:17 - pico-train - INFO - ├── Loss: 6.4011 2025-08-29 21:20:17 - pico-train - INFO - ├── Learning Rate: 1.18e-05 2025-08-29 21:20:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:20:30 - pico-train - INFO - Step 16150 -- 🔄 Training Metrics 2025-08-29 21:20:30 - pico-train - INFO - ├── Loss: 6.3754 2025-08-29 21:20:30 - pico-train - INFO - ├── Learning Rate: 1.17e-05 2025-08-29 21:20:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:20:43 - pico-train - INFO - Step 16175 -- 🔄 Training Metrics 2025-08-29 21:20:43 - pico-train - INFO - ├── Loss: 6.4419 2025-08-29 21:20:43 - pico-train - INFO - ├── Learning Rate: 1.15e-05 2025-08-29 21:20:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:20:55 - pico-train - INFO - Step 16200 -- 🔄 Training Metrics 2025-08-29 21:20:55 - pico-train - INFO - ├── Loss: 6.5383 2025-08-29 21:20:55 - pico-train - INFO - ├── Learning Rate: 1.14e-05 2025-08-29 21:20:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:21:08 - pico-train - INFO - Step 16225 -- 🔄 Training Metrics 2025-08-29 21:21:08 - pico-train - INFO - ├── Loss: 6.4051 2025-08-29 21:21:08 - pico-train - INFO - ├── Learning Rate: 1.12e-05 2025-08-29 21:21:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:21:21 - pico-train - INFO - Step 16250 -- 🔄 Training Metrics 2025-08-29 21:21:21 - pico-train - INFO - ├── Loss: 6.4001 2025-08-29 21:21:21 - pico-train - INFO - ├── Learning Rate: 1.11e-05 2025-08-29 21:21:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:21:34 - pico-train - INFO - Step 16275 -- 🔄 Training Metrics 2025-08-29 21:21:34 - pico-train - INFO - ├── Loss: 6.4433 2025-08-29 21:21:34 - pico-train - INFO - ├── Learning Rate: 1.10e-05 2025-08-29 21:21:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:21:47 - pico-train - INFO - Step 16300 -- 🔄 Training Metrics 2025-08-29 21:21:47 - pico-train - INFO - ├── Loss: 6.4289 2025-08-29 21:21:47 - pico-train - INFO - ├── Learning Rate: 1.08e-05 2025-08-29 21:21:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:21:59 - pico-train - INFO - Step 16325 -- 🔄 Training Metrics 2025-08-29 21:21:59 - pico-train - INFO - ├── Loss: 6.4217 2025-08-29 21:21:59 - pico-train - INFO - ├── Learning Rate: 1.07e-05 2025-08-29 21:21:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:22:12 - pico-train - INFO - Step 16350 -- 🔄 Training Metrics 2025-08-29 21:22:12 - pico-train - INFO - ├── Loss: 6.3954 2025-08-29 21:22:12 - pico-train - INFO - ├── Learning Rate: 1.06e-05 2025-08-29 21:22:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:22:34 - pico-train - INFO - Step 16375 -- 🔄 Training Metrics 2025-08-29 21:22:34 - pico-train - INFO - ├── Loss: 6.4462 2025-08-29 21:22:34 - pico-train - INFO - ├── Learning Rate: 1.04e-05 2025-08-29 21:22:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:22:47 - pico-train - INFO - Step 16400 -- 🔄 Training Metrics 2025-08-29 21:22:47 - pico-train - INFO - ├── Loss: 6.4041 2025-08-29 21:22:47 - pico-train - INFO - ├── Learning Rate: 1.03e-05 2025-08-29 21:22:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:23:00 - pico-train - INFO - Step 16425 -- 🔄 Training Metrics 2025-08-29 21:23:00 - pico-train - INFO - ├── Loss: 6.4381 2025-08-29 21:23:00 - pico-train - INFO - ├── Learning Rate: 1.02e-05 2025-08-29 21:23:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:23:13 - pico-train - INFO - Step 16450 -- 🔄 Training Metrics 2025-08-29 21:23:13 - pico-train - INFO - ├── Loss: 6.3713 2025-08-29 21:23:13 - pico-train - INFO - ├── Learning Rate: 1.00e-05 2025-08-29 21:23:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:23:25 - pico-train - INFO - Step 16475 -- 🔄 Training Metrics 2025-08-29 21:23:25 - pico-train - INFO - ├── Loss: 6.3954 2025-08-29 21:23:25 - pico-train - INFO - ├── Learning Rate: 9.91e-06 2025-08-29 21:23:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:23:38 - pico-train - INFO - Step 16500 -- 💾 Saving Checkpoint 2025-08-29 21:25:45 - pico-train - INFO - Step 16500 -- 📊 Evaluation Results 2025-08-29 21:25:45 - pico-train - INFO - └── paloma: 1.237561338460672e+24 2025-08-29 21:25:47 - pico-train - INFO - Step 16500 -- 🔄 Training Metrics 2025-08-29 21:25:47 - pico-train - INFO - ├── Loss: 6.4280 2025-08-29 21:25:47 - pico-train - INFO - ├── Learning Rate: 9.78e-06 2025-08-29 21:25:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:25:47 - pico-train - INFO - Step 16500 -- 📈 Saving Learning Dynamics 2025-08-29 21:26:02 - pico-train - INFO - Step 16525 -- 🔄 Training Metrics 2025-08-29 21:26:02 - pico-train - INFO - ├── Loss: 6.3385 2025-08-29 21:26:02 - pico-train - INFO - ├── Learning Rate: 9.65e-06 2025-08-29 21:26:02 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:26:15 - pico-train - INFO - Step 16550 -- 🔄 Training Metrics 2025-08-29 21:26:15 - pico-train - INFO - ├── Loss: 6.3865 2025-08-29 21:26:15 - pico-train - INFO - ├── Learning Rate: 9.52e-06 2025-08-29 21:26:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:26:27 - pico-train - INFO - Step 16575 -- 🔄 Training Metrics 2025-08-29 21:26:27 - pico-train - INFO - ├── Loss: 6.3920 2025-08-29 21:26:27 - pico-train - INFO - ├── Learning Rate: 9.39e-06 2025-08-29 21:26:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:26:40 - pico-train - INFO - Step 16600 -- 🔄 Training Metrics 2025-08-29 21:26:40 - pico-train - INFO - ├── Loss: 6.4103 2025-08-29 21:26:40 - pico-train - INFO - ├── Learning Rate: 9.27e-06 2025-08-29 21:26:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:26:53 - pico-train - INFO - Step 16625 -- 🔄 Training Metrics 2025-08-29 21:26:53 - pico-train - INFO - ├── Loss: 6.5227 2025-08-29 21:26:53 - pico-train - INFO - ├── Learning Rate: 9.14e-06 2025-08-29 21:26:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:27:05 - pico-train - INFO - Step 16650 -- 🔄 Training Metrics 2025-08-29 21:27:05 - pico-train - INFO - ├── Loss: 6.3691 2025-08-29 21:27:05 - pico-train - INFO - ├── Learning Rate: 9.01e-06 2025-08-29 21:27:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:27:18 - pico-train - INFO - Step 16675 -- 🔄 Training Metrics 2025-08-29 21:27:18 - pico-train - INFO - ├── Loss: 6.4122 2025-08-29 21:27:18 - pico-train - INFO - ├── Learning Rate: 8.89e-06 2025-08-29 21:27:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:27:31 - pico-train - INFO - Step 16700 -- 🔄 Training Metrics 2025-08-29 21:27:31 - pico-train - INFO - ├── Loss: 6.4154 2025-08-29 21:27:31 - pico-train - INFO - ├── Learning Rate: 8.76e-06 2025-08-29 21:27:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:27:43 - pico-train - INFO - Step 16725 -- 🔄 Training Metrics 2025-08-29 21:27:43 - pico-train - INFO - ├── Loss: 6.3769 2025-08-29 21:27:43 - pico-train - INFO - ├── Learning Rate: 8.64e-06 2025-08-29 21:27:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:27:56 - pico-train - INFO - Step 16750 -- 🔄 Training Metrics 2025-08-29 21:27:56 - pico-train - INFO - ├── Loss: 6.3878 2025-08-29 21:27:56 - pico-train - INFO - ├── Learning Rate: 8.52e-06 2025-08-29 21:27:56 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:28:08 - pico-train - INFO - Step 16775 -- 🔄 Training Metrics 2025-08-29 21:28:08 - pico-train - INFO - ├── Loss: 6.4015 2025-08-29 21:28:08 - pico-train - INFO - ├── Learning Rate: 8.39e-06 2025-08-29 21:28:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:28:21 - pico-train - INFO - Step 16800 -- 🔄 Training Metrics 2025-08-29 21:28:21 - pico-train - INFO - ├── Loss: 6.4290 2025-08-29 21:28:21 - pico-train - INFO - ├── Learning Rate: 8.27e-06 2025-08-29 21:28:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:28:33 - pico-train - INFO - Step 16825 -- 🔄 Training Metrics 2025-08-29 21:28:33 - pico-train - INFO - ├── Loss: 6.4070 2025-08-29 21:28:33 - pico-train - INFO - ├── Learning Rate: 8.15e-06 2025-08-29 21:28:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:28:46 - pico-train - INFO - Step 16850 -- 🔄 Training Metrics 2025-08-29 21:28:46 - pico-train - INFO - ├── Loss: 6.4331 2025-08-29 21:28:46 - pico-train - INFO - ├── Learning Rate: 8.03e-06 2025-08-29 21:28:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:28:59 - pico-train - INFO - Step 16875 -- 🔄 Training Metrics 2025-08-29 21:28:59 - pico-train - INFO - ├── Loss: 6.3833 2025-08-29 21:28:59 - pico-train - INFO - ├── Learning Rate: 7.91e-06 2025-08-29 21:28:59 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:29:12 - pico-train - INFO - Step 16900 -- 🔄 Training Metrics 2025-08-29 21:29:12 - pico-train - INFO - ├── Loss: 6.4244 2025-08-29 21:29:12 - pico-train - INFO - ├── Learning Rate: 7.79e-06 2025-08-29 21:29:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:29:24 - pico-train - INFO - Step 16925 -- 🔄 Training Metrics 2025-08-29 21:29:24 - pico-train - INFO - ├── Loss: 6.3542 2025-08-29 21:29:24 - pico-train - INFO - ├── Learning Rate: 7.67e-06 2025-08-29 21:29:24 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:29:37 - pico-train - INFO - Step 16950 -- 🔄 Training Metrics 2025-08-29 21:29:37 - pico-train - INFO - ├── Loss: 6.4249 2025-08-29 21:29:37 - pico-train - INFO - ├── Learning Rate: 7.56e-06 2025-08-29 21:29:37 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:29:50 - pico-train - INFO - Step 16975 -- 🔄 Training Metrics 2025-08-29 21:29:50 - pico-train - INFO - ├── Loss: 6.4345 2025-08-29 21:29:50 - pico-train - INFO - ├── Learning Rate: 7.44e-06 2025-08-29 21:29:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:30:02 - pico-train - INFO - Step 17000 -- 💾 Saving Checkpoint 2025-08-29 21:32:11 - pico-train - INFO - Step 17000 -- 📊 Evaluation Results 2025-08-29 21:32:11 - pico-train - INFO - └── paloma: 1.304531243949835e+24 2025-08-29 21:32:12 - pico-train - INFO - Step 17000 -- 🔄 Training Metrics 2025-08-29 21:32:12 - pico-train - INFO - ├── Loss: 6.3667 2025-08-29 21:32:12 - pico-train - INFO - ├── Learning Rate: 7.32e-06 2025-08-29 21:32:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:32:12 - pico-train - INFO - Step 17000 -- 📈 Saving Learning Dynamics 2025-08-29 21:32:27 - pico-train - INFO - Step 17025 -- 🔄 Training Metrics 2025-08-29 21:32:27 - pico-train - INFO - ├── Loss: 6.4075 2025-08-29 21:32:27 - pico-train - INFO - ├── Learning Rate: 7.21e-06 2025-08-29 21:32:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:32:39 - pico-train - INFO - Step 17050 -- 🔄 Training Metrics 2025-08-29 21:32:39 - pico-train - INFO - ├── Loss: 6.4075 2025-08-29 21:32:39 - pico-train - INFO - ├── Learning Rate: 7.09e-06 2025-08-29 21:32:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:32:52 - pico-train - INFO - Step 17075 -- 🔄 Training Metrics 2025-08-29 21:32:52 - pico-train - INFO - ├── Loss: 6.4692 2025-08-29 21:32:52 - pico-train - INFO - ├── Learning Rate: 6.98e-06 2025-08-29 21:32:52 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:33:05 - pico-train - INFO - Step 17100 -- 🔄 Training Metrics 2025-08-29 21:33:05 - pico-train - INFO - ├── Loss: 6.4737 2025-08-29 21:33:05 - pico-train - INFO - ├── Learning Rate: 6.87e-06 2025-08-29 21:33:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:33:17 - pico-train - INFO - Step 17125 -- 🔄 Training Metrics 2025-08-29 21:33:17 - pico-train - INFO - ├── Loss: 6.3527 2025-08-29 21:33:17 - pico-train - INFO - ├── Learning Rate: 6.75e-06 2025-08-29 21:33:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:33:30 - pico-train - INFO - Step 17150 -- 🔄 Training Metrics 2025-08-29 21:33:30 - pico-train - INFO - ├── Loss: 6.4079 2025-08-29 21:33:30 - pico-train - INFO - ├── Learning Rate: 6.64e-06 2025-08-29 21:33:30 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:33:43 - pico-train - INFO - Step 17175 -- 🔄 Training Metrics 2025-08-29 21:33:43 - pico-train - INFO - ├── Loss: 6.2427 2025-08-29 21:33:43 - pico-train - INFO - ├── Learning Rate: 6.53e-06 2025-08-29 21:33:43 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:33:55 - pico-train - INFO - Step 17200 -- 🔄 Training Metrics 2025-08-29 21:33:55 - pico-train - INFO - ├── Loss: 6.3806 2025-08-29 21:33:55 - pico-train - INFO - ├── Learning Rate: 6.42e-06 2025-08-29 21:33:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:34:08 - pico-train - INFO - Step 17225 -- 🔄 Training Metrics 2025-08-29 21:34:08 - pico-train - INFO - ├── Loss: 6.4464 2025-08-29 21:34:08 - pico-train - INFO - ├── Learning Rate: 6.31e-06 2025-08-29 21:34:08 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:34:21 - pico-train - INFO - Step 17250 -- 🔄 Training Metrics 2025-08-29 21:34:21 - pico-train - INFO - ├── Loss: 6.4264 2025-08-29 21:34:21 - pico-train - INFO - ├── Learning Rate: 6.20e-06 2025-08-29 21:34:21 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:34:33 - pico-train - INFO - Step 17275 -- 🔄 Training Metrics 2025-08-29 21:34:33 - pico-train - INFO - ├── Loss: 6.4196 2025-08-29 21:34:33 - pico-train - INFO - ├── Learning Rate: 6.10e-06 2025-08-29 21:34:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:34:46 - pico-train - INFO - Step 17300 -- 🔄 Training Metrics 2025-08-29 21:34:46 - pico-train - INFO - ├── Loss: 6.3639 2025-08-29 21:34:46 - pico-train - INFO - ├── Learning Rate: 5.99e-06 2025-08-29 21:34:46 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:34:58 - pico-train - INFO - Step 17325 -- 🔄 Training Metrics 2025-08-29 21:34:58 - pico-train - INFO - ├── Loss: 6.3534 2025-08-29 21:34:58 - pico-train - INFO - ├── Learning Rate: 5.88e-06 2025-08-29 21:34:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:35:11 - pico-train - INFO - Step 17350 -- 🔄 Training Metrics 2025-08-29 21:35:11 - pico-train - INFO - ├── Loss: 6.4196 2025-08-29 21:35:11 - pico-train - INFO - ├── Learning Rate: 5.78e-06 2025-08-29 21:35:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:35:25 - pico-train - INFO - Step 17375 -- 🔄 Training Metrics 2025-08-29 21:35:25 - pico-train - INFO - ├── Loss: 6.4977 2025-08-29 21:35:25 - pico-train - INFO - ├── Learning Rate: 5.67e-06 2025-08-29 21:35:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:35:38 - pico-train - INFO - Step 17400 -- 🔄 Training Metrics 2025-08-29 21:35:38 - pico-train - INFO - ├── Loss: 6.4950 2025-08-29 21:35:38 - pico-train - INFO - ├── Learning Rate: 5.57e-06 2025-08-29 21:35:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:35:50 - pico-train - INFO - Step 17425 -- 🔄 Training Metrics 2025-08-29 21:35:50 - pico-train - INFO - ├── Loss: 6.4814 2025-08-29 21:35:50 - pico-train - INFO - ├── Learning Rate: 5.47e-06 2025-08-29 21:35:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:36:03 - pico-train - INFO - Step 17450 -- 🔄 Training Metrics 2025-08-29 21:36:03 - pico-train - INFO - ├── Loss: 6.3986 2025-08-29 21:36:03 - pico-train - INFO - ├── Learning Rate: 5.37e-06 2025-08-29 21:36:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:36:16 - pico-train - INFO - Step 17475 -- 🔄 Training Metrics 2025-08-29 21:36:16 - pico-train - INFO - ├── Loss: 6.3909 2025-08-29 21:36:16 - pico-train - INFO - ├── Learning Rate: 5.27e-06 2025-08-29 21:36:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:36:28 - pico-train - INFO - Step 17500 -- 💾 Saving Checkpoint 2025-08-29 21:38:26 - pico-train - INFO - Step 17500 -- 📊 Evaluation Results 2025-08-29 21:38:26 - pico-train - INFO - └── paloma: 1.263308985203994e+24 2025-08-29 21:38:27 - pico-train - INFO - Step 17500 -- 🔄 Training Metrics 2025-08-29 21:38:27 - pico-train - INFO - ├── Loss: 6.3834 2025-08-29 21:38:27 - pico-train - INFO - ├── Learning Rate: 5.17e-06 2025-08-29 21:38:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:38:27 - pico-train - INFO - Step 17500 -- 📈 Saving Learning Dynamics 2025-08-29 21:38:42 - pico-train - INFO - Step 17525 -- 🔄 Training Metrics 2025-08-29 21:38:42 - pico-train - INFO - ├── Loss: 6.4161 2025-08-29 21:38:42 - pico-train - INFO - ├── Learning Rate: 5.07e-06 2025-08-29 21:38:42 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:38:55 - pico-train - INFO - Step 17550 -- 🔄 Training Metrics 2025-08-29 21:38:55 - pico-train - INFO - ├── Loss: 6.3901 2025-08-29 21:38:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:38:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:39:07 - pico-train - INFO - Step 17575 -- 🔄 Training Metrics 2025-08-29 21:39:07 - pico-train - INFO - ├── Loss: 6.3559 2025-08-29 21:39:07 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:39:07 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:39:20 - pico-train - INFO - Step 17600 -- 🔄 Training Metrics 2025-08-29 21:39:20 - pico-train - INFO - ├── Loss: 6.3792 2025-08-29 21:39:20 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:39:20 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:39:33 - pico-train - INFO - Step 17625 -- 🔄 Training Metrics 2025-08-29 21:39:33 - pico-train - INFO - ├── Loss: 6.4937 2025-08-29 21:39:33 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:39:33 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:39:45 - pico-train - INFO - Step 17650 -- 🔄 Training Metrics 2025-08-29 21:39:45 - pico-train - INFO - ├── Loss: 6.4112 2025-08-29 21:39:45 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:39:45 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:39:58 - pico-train - INFO - Step 17675 -- 🔄 Training Metrics 2025-08-29 21:39:58 - pico-train - INFO - ├── Loss: 6.4311 2025-08-29 21:39:58 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:39:58 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:40:11 - pico-train - INFO - Step 17700 -- 🔄 Training Metrics 2025-08-29 21:40:11 - pico-train - INFO - ├── Loss: 6.4455 2025-08-29 21:40:11 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:40:11 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:40:23 - pico-train - INFO - Step 17725 -- 🔄 Training Metrics 2025-08-29 21:40:23 - pico-train - INFO - ├── Loss: 6.4370 2025-08-29 21:40:23 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:40:23 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:40:36 - pico-train - INFO - Step 17750 -- 🔄 Training Metrics 2025-08-29 21:40:36 - pico-train - INFO - ├── Loss: 6.3680 2025-08-29 21:40:36 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:40:36 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:40:49 - pico-train - INFO - Step 17775 -- 🔄 Training Metrics 2025-08-29 21:40:49 - pico-train - INFO - ├── Loss: 6.4037 2025-08-29 21:40:49 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:40:49 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:41:01 - pico-train - INFO - Step 17800 -- 🔄 Training Metrics 2025-08-29 21:41:01 - pico-train - INFO - ├── Loss: 6.3438 2025-08-29 21:41:01 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:41:01 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:41:14 - pico-train - INFO - Step 17825 -- 🔄 Training Metrics 2025-08-29 21:41:14 - pico-train - INFO - ├── Loss: 6.5015 2025-08-29 21:41:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:41:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:41:27 - pico-train - INFO - Step 17850 -- 🔄 Training Metrics 2025-08-29 21:41:27 - pico-train - INFO - ├── Loss: 6.3998 2025-08-29 21:41:27 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:41:27 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:41:40 - pico-train - INFO - Step 17875 -- 🔄 Training Metrics 2025-08-29 21:41:40 - pico-train - INFO - ├── Loss: 6.3919 2025-08-29 21:41:40 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:41:40 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:41:53 - pico-train - INFO - Step 17900 -- 🔄 Training Metrics 2025-08-29 21:41:53 - pico-train - INFO - ├── Loss: 6.4118 2025-08-29 21:41:53 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:41:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:42:06 - pico-train - INFO - Step 17925 -- 🔄 Training Metrics 2025-08-29 21:42:06 - pico-train - INFO - ├── Loss: 6.4447 2025-08-29 21:42:06 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:42:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:42:18 - pico-train - INFO - Step 17950 -- 🔄 Training Metrics 2025-08-29 21:42:18 - pico-train - INFO - ├── Loss: 6.4113 2025-08-29 21:42:18 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:42:18 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:42:31 - pico-train - INFO - Step 17975 -- 🔄 Training Metrics 2025-08-29 21:42:31 - pico-train - INFO - ├── Loss: 6.3771 2025-08-29 21:42:31 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:42:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:42:43 - pico-train - INFO - Step 18000 -- 💾 Saving Checkpoint 2025-08-29 21:44:54 - pico-train - INFO - Step 18000 -- 📊 Evaluation Results 2025-08-29 21:44:54 - pico-train - INFO - └── paloma: 1.4237252986808802e+24 2025-08-29 21:44:55 - pico-train - INFO - Step 18000 -- 🔄 Training Metrics 2025-08-29 21:44:55 - pico-train - INFO - ├── Loss: 6.4250 2025-08-29 21:44:55 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:44:55 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:44:55 - pico-train - INFO - Step 18000 -- 📈 Saving Learning Dynamics 2025-08-29 21:45:09 - pico-train - INFO - Step 18025 -- 🔄 Training Metrics 2025-08-29 21:45:09 - pico-train - INFO - ├── Loss: 6.4218 2025-08-29 21:45:09 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:45:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:45:22 - pico-train - INFO - Step 18050 -- 🔄 Training Metrics 2025-08-29 21:45:22 - pico-train - INFO - ├── Loss: 6.3776 2025-08-29 21:45:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:45:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:45:35 - pico-train - INFO - Step 18075 -- 🔄 Training Metrics 2025-08-29 21:45:35 - pico-train - INFO - ├── Loss: 6.3610 2025-08-29 21:45:35 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:45:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:45:47 - pico-train - INFO - Step 18100 -- 🔄 Training Metrics 2025-08-29 21:45:47 - pico-train - INFO - ├── Loss: 6.3657 2025-08-29 21:45:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:45:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:46:00 - pico-train - INFO - Step 18125 -- 🔄 Training Metrics 2025-08-29 21:46:00 - pico-train - INFO - ├── Loss: 6.4142 2025-08-29 21:46:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:46:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:46:13 - pico-train - INFO - Step 18150 -- 🔄 Training Metrics 2025-08-29 21:46:13 - pico-train - INFO - ├── Loss: 6.3405 2025-08-29 21:46:13 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:46:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:46:25 - pico-train - INFO - Step 18175 -- 🔄 Training Metrics 2025-08-29 21:46:25 - pico-train - INFO - ├── Loss: 6.4436 2025-08-29 21:46:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:46:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:46:38 - pico-train - INFO - Step 18200 -- 🔄 Training Metrics 2025-08-29 21:46:38 - pico-train - INFO - ├── Loss: 6.3272 2025-08-29 21:46:38 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:46:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:46:50 - pico-train - INFO - Step 18225 -- 🔄 Training Metrics 2025-08-29 21:46:50 - pico-train - INFO - ├── Loss: 6.4581 2025-08-29 21:46:50 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:46:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:47:03 - pico-train - INFO - Step 18250 -- 🔄 Training Metrics 2025-08-29 21:47:03 - pico-train - INFO - ├── Loss: 6.4066 2025-08-29 21:47:03 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:47:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:47:15 - pico-train - INFO - Step 18275 -- 🔄 Training Metrics 2025-08-29 21:47:15 - pico-train - INFO - ├── Loss: 6.4504 2025-08-29 21:47:15 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:47:15 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:47:28 - pico-train - INFO - Step 18300 -- 🔄 Training Metrics 2025-08-29 21:47:28 - pico-train - INFO - ├── Loss: 6.3557 2025-08-29 21:47:28 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:47:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:47:41 - pico-train - INFO - Step 18325 -- 🔄 Training Metrics 2025-08-29 21:47:41 - pico-train - INFO - ├── Loss: 6.3500 2025-08-29 21:47:41 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:47:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:47:53 - pico-train - INFO - Step 18350 -- 🔄 Training Metrics 2025-08-29 21:47:53 - pico-train - INFO - ├── Loss: 6.4390 2025-08-29 21:47:53 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:47:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:48:06 - pico-train - INFO - Step 18375 -- 🔄 Training Metrics 2025-08-29 21:48:06 - pico-train - INFO - ├── Loss: 6.3690 2025-08-29 21:48:06 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:48:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:48:19 - pico-train - INFO - Step 18400 -- 🔄 Training Metrics 2025-08-29 21:48:19 - pico-train - INFO - ├── Loss: 6.3101 2025-08-29 21:48:19 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:48:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:48:32 - pico-train - INFO - Step 18425 -- 🔄 Training Metrics 2025-08-29 21:48:32 - pico-train - INFO - ├── Loss: 6.3969 2025-08-29 21:48:32 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:48:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:48:44 - pico-train - INFO - Step 18450 -- 🔄 Training Metrics 2025-08-29 21:48:44 - pico-train - INFO - ├── Loss: 6.3362 2025-08-29 21:48:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:48:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:48:57 - pico-train - INFO - Step 18475 -- 🔄 Training Metrics 2025-08-29 21:48:57 - pico-train - INFO - ├── Loss: 6.3378 2025-08-29 21:48:57 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:48:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:49:09 - pico-train - INFO - Step 18500 -- 💾 Saving Checkpoint 2025-08-29 21:51:03 - pico-train - INFO - Step 18500 -- 📊 Evaluation Results 2025-08-29 21:51:03 - pico-train - INFO - └── paloma: 1.4819541114529576e+24 2025-08-29 21:51:05 - pico-train - INFO - Step 18500 -- 🔄 Training Metrics 2025-08-29 21:51:05 - pico-train - INFO - ├── Loss: 6.3848 2025-08-29 21:51:05 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:51:05 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:51:05 - pico-train - INFO - Step 18500 -- 📈 Saving Learning Dynamics 2025-08-29 21:51:19 - pico-train - INFO - Step 18525 -- 🔄 Training Metrics 2025-08-29 21:51:19 - pico-train - INFO - ├── Loss: 6.3383 2025-08-29 21:51:19 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:51:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:51:32 - pico-train - INFO - Step 18550 -- 🔄 Training Metrics 2025-08-29 21:51:32 - pico-train - INFO - ├── Loss: 6.3507 2025-08-29 21:51:32 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:51:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:51:44 - pico-train - INFO - Step 18575 -- 🔄 Training Metrics 2025-08-29 21:51:44 - pico-train - INFO - ├── Loss: 6.4269 2025-08-29 21:51:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:51:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:51:57 - pico-train - INFO - Step 18600 -- 🔄 Training Metrics 2025-08-29 21:51:57 - pico-train - INFO - ├── Loss: 6.3890 2025-08-29 21:51:57 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:51:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:52:10 - pico-train - INFO - Step 18625 -- 🔄 Training Metrics 2025-08-29 21:52:10 - pico-train - INFO - ├── Loss: 6.3352 2025-08-29 21:52:10 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:52:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:52:22 - pico-train - INFO - Step 18650 -- 🔄 Training Metrics 2025-08-29 21:52:22 - pico-train - INFO - ├── Loss: 6.3953 2025-08-29 21:52:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:52:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:52:35 - pico-train - INFO - Step 18675 -- 🔄 Training Metrics 2025-08-29 21:52:35 - pico-train - INFO - ├── Loss: 6.4438 2025-08-29 21:52:35 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:52:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:52:47 - pico-train - INFO - Step 18700 -- 🔄 Training Metrics 2025-08-29 21:52:47 - pico-train - INFO - ├── Loss: 6.4212 2025-08-29 21:52:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:52:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:53:00 - pico-train - INFO - Step 18725 -- 🔄 Training Metrics 2025-08-29 21:53:00 - pico-train - INFO - ├── Loss: 6.3805 2025-08-29 21:53:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:53:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:53:12 - pico-train - INFO - Step 18750 -- 🔄 Training Metrics 2025-08-29 21:53:12 - pico-train - INFO - ├── Loss: 6.3933 2025-08-29 21:53:12 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:53:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:53:25 - pico-train - INFO - Step 18775 -- 🔄 Training Metrics 2025-08-29 21:53:25 - pico-train - INFO - ├── Loss: 6.3642 2025-08-29 21:53:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:53:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:53:38 - pico-train - INFO - Step 18800 -- 🔄 Training Metrics 2025-08-29 21:53:38 - pico-train - INFO - ├── Loss: 6.3683 2025-08-29 21:53:38 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:53:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:53:50 - pico-train - INFO - Step 18825 -- 🔄 Training Metrics 2025-08-29 21:53:50 - pico-train - INFO - ├── Loss: 6.4197 2025-08-29 21:53:50 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:53:50 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:54:03 - pico-train - INFO - Step 18850 -- 🔄 Training Metrics 2025-08-29 21:54:03 - pico-train - INFO - ├── Loss: 6.3640 2025-08-29 21:54:03 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:54:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:54:16 - pico-train - INFO - Step 18875 -- 🔄 Training Metrics 2025-08-29 21:54:16 - pico-train - INFO - ├── Loss: 6.3246 2025-08-29 21:54:16 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:54:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:54:29 - pico-train - INFO - Step 18900 -- 🔄 Training Metrics 2025-08-29 21:54:29 - pico-train - INFO - ├── Loss: 6.4408 2025-08-29 21:54:29 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:54:29 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:54:41 - pico-train - INFO - Step 18925 -- 🔄 Training Metrics 2025-08-29 21:54:41 - pico-train - INFO - ├── Loss: 6.4179 2025-08-29 21:54:41 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:54:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:54:54 - pico-train - INFO - Step 18950 -- 🔄 Training Metrics 2025-08-29 21:54:54 - pico-train - INFO - ├── Loss: 6.4054 2025-08-29 21:54:54 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:54:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:55:06 - pico-train - INFO - Step 18975 -- 🔄 Training Metrics 2025-08-29 21:55:06 - pico-train - INFO - ├── Loss: 6.3416 2025-08-29 21:55:06 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:55:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:55:18 - pico-train - INFO - Step 19000 -- 💾 Saving Checkpoint 2025-08-29 21:57:12 - pico-train - INFO - Step 19000 -- 📊 Evaluation Results 2025-08-29 21:57:12 - pico-train - INFO - └── paloma: 1.5800319204327158e+24 2025-08-29 21:57:14 - pico-train - INFO - Step 19000 -- 🔄 Training Metrics 2025-08-29 21:57:14 - pico-train - INFO - ├── Loss: 6.3180 2025-08-29 21:57:14 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:57:14 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:57:14 - pico-train - INFO - Step 19000 -- 📈 Saving Learning Dynamics 2025-08-29 21:57:28 - pico-train - INFO - Step 19025 -- 🔄 Training Metrics 2025-08-29 21:57:28 - pico-train - INFO - ├── Loss: 6.3237 2025-08-29 21:57:28 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:57:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:57:41 - pico-train - INFO - Step 19050 -- 🔄 Training Metrics 2025-08-29 21:57:41 - pico-train - INFO - ├── Loss: 6.3803 2025-08-29 21:57:41 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:57:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:57:53 - pico-train - INFO - Step 19075 -- 🔄 Training Metrics 2025-08-29 21:57:53 - pico-train - INFO - ├── Loss: 6.4063 2025-08-29 21:57:53 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:57:53 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:58:06 - pico-train - INFO - Step 19100 -- 🔄 Training Metrics 2025-08-29 21:58:06 - pico-train - INFO - ├── Loss: 6.3269 2025-08-29 21:58:06 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:58:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:58:19 - pico-train - INFO - Step 19125 -- 🔄 Training Metrics 2025-08-29 21:58:19 - pico-train - INFO - ├── Loss: 6.2963 2025-08-29 21:58:19 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:58:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:58:32 - pico-train - INFO - Step 19150 -- 🔄 Training Metrics 2025-08-29 21:58:32 - pico-train - INFO - ├── Loss: 6.4027 2025-08-29 21:58:32 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:58:32 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:58:44 - pico-train - INFO - Step 19175 -- 🔄 Training Metrics 2025-08-29 21:58:44 - pico-train - INFO - ├── Loss: 6.4356 2025-08-29 21:58:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:58:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:58:57 - pico-train - INFO - Step 19200 -- 🔄 Training Metrics 2025-08-29 21:58:57 - pico-train - INFO - ├── Loss: 6.3680 2025-08-29 21:58:57 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:58:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:59:10 - pico-train - INFO - Step 19225 -- 🔄 Training Metrics 2025-08-29 21:59:10 - pico-train - INFO - ├── Loss: 6.3971 2025-08-29 21:59:10 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:59:10 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:59:22 - pico-train - INFO - Step 19250 -- 🔄 Training Metrics 2025-08-29 21:59:22 - pico-train - INFO - ├── Loss: 6.3903 2025-08-29 21:59:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:59:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:59:35 - pico-train - INFO - Step 19275 -- 🔄 Training Metrics 2025-08-29 21:59:35 - pico-train - INFO - ├── Loss: 6.3859 2025-08-29 21:59:35 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:59:35 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 21:59:47 - pico-train - INFO - Step 19300 -- 🔄 Training Metrics 2025-08-29 21:59:47 - pico-train - INFO - ├── Loss: 6.3196 2025-08-29 21:59:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 21:59:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:00:00 - pico-train - INFO - Step 19325 -- 🔄 Training Metrics 2025-08-29 22:00:00 - pico-train - INFO - ├── Loss: 6.3837 2025-08-29 22:00:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:00:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:00:13 - pico-train - INFO - Step 19350 -- 🔄 Training Metrics 2025-08-29 22:00:13 - pico-train - INFO - ├── Loss: 6.3884 2025-08-29 22:00:13 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:00:13 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:00:26 - pico-train - INFO - Step 19375 -- 🔄 Training Metrics 2025-08-29 22:00:26 - pico-train - INFO - ├── Loss: 6.3896 2025-08-29 22:00:26 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:00:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:00:39 - pico-train - INFO - Step 19400 -- 🔄 Training Metrics 2025-08-29 22:00:39 - pico-train - INFO - ├── Loss: 6.3826 2025-08-29 22:00:39 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:00:39 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:00:51 - pico-train - INFO - Step 19425 -- 🔄 Training Metrics 2025-08-29 22:00:51 - pico-train - INFO - ├── Loss: 6.3350 2025-08-29 22:00:51 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:00:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:01:04 - pico-train - INFO - Step 19450 -- 🔄 Training Metrics 2025-08-29 22:01:04 - pico-train - INFO - ├── Loss: 6.3507 2025-08-29 22:01:04 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:01:04 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:01:17 - pico-train - INFO - Step 19475 -- 🔄 Training Metrics 2025-08-29 22:01:17 - pico-train - INFO - ├── Loss: 6.4104 2025-08-29 22:01:17 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:01:17 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:01:29 - pico-train - INFO - Step 19500 -- 💾 Saving Checkpoint 2025-08-29 22:03:25 - pico-train - INFO - Step 19500 -- 📊 Evaluation Results 2025-08-29 22:03:25 - pico-train - INFO - └── paloma: 1.7237442602041698e+24 2025-08-29 22:03:26 - pico-train - INFO - Step 19500 -- 🔄 Training Metrics 2025-08-29 22:03:26 - pico-train - INFO - ├── Loss: 6.4120 2025-08-29 22:03:26 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:03:26 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:03:26 - pico-train - INFO - Step 19500 -- 📈 Saving Learning Dynamics 2025-08-29 22:03:41 - pico-train - INFO - Step 19525 -- 🔄 Training Metrics 2025-08-29 22:03:41 - pico-train - INFO - ├── Loss: 6.4176 2025-08-29 22:03:41 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:03:41 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:03:54 - pico-train - INFO - Step 19550 -- 🔄 Training Metrics 2025-08-29 22:03:54 - pico-train - INFO - ├── Loss: 6.3271 2025-08-29 22:03:54 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:03:54 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:04:06 - pico-train - INFO - Step 19575 -- 🔄 Training Metrics 2025-08-29 22:04:06 - pico-train - INFO - ├── Loss: 6.3965 2025-08-29 22:04:06 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:04:06 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:04:19 - pico-train - INFO - Step 19600 -- 🔄 Training Metrics 2025-08-29 22:04:19 - pico-train - INFO - ├── Loss: 6.3484 2025-08-29 22:04:19 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:04:19 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:04:31 - pico-train - INFO - Step 19625 -- 🔄 Training Metrics 2025-08-29 22:04:31 - pico-train - INFO - ├── Loss: 6.3829 2025-08-29 22:04:31 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:04:31 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:04:44 - pico-train - INFO - Step 19650 -- 🔄 Training Metrics 2025-08-29 22:04:44 - pico-train - INFO - ├── Loss: 6.3032 2025-08-29 22:04:44 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:04:44 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:04:57 - pico-train - INFO - Step 19675 -- 🔄 Training Metrics 2025-08-29 22:04:57 - pico-train - INFO - ├── Loss: 6.3678 2025-08-29 22:04:57 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:04:57 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:05:09 - pico-train - INFO - Step 19700 -- 🔄 Training Metrics 2025-08-29 22:05:09 - pico-train - INFO - ├── Loss: 6.3765 2025-08-29 22:05:09 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:05:09 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:05:22 - pico-train - INFO - Step 19725 -- 🔄 Training Metrics 2025-08-29 22:05:22 - pico-train - INFO - ├── Loss: 6.3547 2025-08-29 22:05:22 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:05:22 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:05:34 - pico-train - INFO - Step 19750 -- 🔄 Training Metrics 2025-08-29 22:05:34 - pico-train - INFO - ├── Loss: 6.4484 2025-08-29 22:05:34 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:05:34 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:05:47 - pico-train - INFO - Step 19775 -- 🔄 Training Metrics 2025-08-29 22:05:47 - pico-train - INFO - ├── Loss: 6.3166 2025-08-29 22:05:47 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:05:47 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:06:00 - pico-train - INFO - Step 19800 -- 🔄 Training Metrics 2025-08-29 22:06:00 - pico-train - INFO - ├── Loss: 6.4591 2025-08-29 22:06:00 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:06:00 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:06:12 - pico-train - INFO - Step 19825 -- 🔄 Training Metrics 2025-08-29 22:06:12 - pico-train - INFO - ├── Loss: 6.4335 2025-08-29 22:06:12 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:06:12 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:06:25 - pico-train - INFO - Step 19850 -- 🔄 Training Metrics 2025-08-29 22:06:25 - pico-train - INFO - ├── Loss: 6.4255 2025-08-29 22:06:25 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:06:25 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:06:38 - pico-train - INFO - Step 19875 -- 🔄 Training Metrics 2025-08-29 22:06:38 - pico-train - INFO - ├── Loss: 6.4091 2025-08-29 22:06:38 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:06:38 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:06:51 - pico-train - INFO - Step 19900 -- 🔄 Training Metrics 2025-08-29 22:06:51 - pico-train - INFO - ├── Loss: 6.3115 2025-08-29 22:06:51 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:06:51 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:07:03 - pico-train - INFO - Step 19925 -- 🔄 Training Metrics 2025-08-29 22:07:03 - pico-train - INFO - ├── Loss: 6.4247 2025-08-29 22:07:03 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:07:03 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:07:16 - pico-train - INFO - Step 19950 -- 🔄 Training Metrics 2025-08-29 22:07:16 - pico-train - INFO - ├── Loss: 6.4009 2025-08-29 22:07:16 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:07:16 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:07:28 - pico-train - INFO - Step 19975 -- 🔄 Training Metrics 2025-08-29 22:07:28 - pico-train - INFO - ├── Loss: 6.4714 2025-08-29 22:07:28 - pico-train - INFO - ├── Learning Rate: 5.00e-06 2025-08-29 22:07:28 - pico-train - INFO - └── Inf/NaN count: 0 2025-08-29 22:07:40 - pico-train - INFO - Step 20000 -- 💾 Saving Checkpoint 2025-08-29 22:11:41 - pico-train - INFO - Step 20000 -- 📊 Evaluation Results 2025-08-29 22:11:41 - pico-train - INFO - └── paloma: 1.8399778163273925e+24 2025-08-29 22:11:42 - pico-train - INFO - 🎉 Training complete! Final step: 20000