ThomasTheMaker's picture
Upload folder using huggingface_hub
6557434 verified
2025-08-30 18:45:19 - pico-train - INFO - Step 0 -- ๐Ÿ“Š Evaluation Results
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 18:45:19 - pico-train - INFO - ==================================================
2025-08-30 18:45:19 - pico-train - INFO - โœจ Training Configuration
2025-08-30 18:45:19 - pico-train - INFO - ==================================================
2025-08-30 18:45:19 - pico-train - INFO - โ•ญโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฎ
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ checkpointing: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ checkpoints_dir: checkpoints โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ evaluation: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ eval_results_dir: eval_results โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ fabric_checkpoint_dir: fabric_state โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ fabric_checkpoint_filename: checkpoint.pt โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ hf_checkpoint: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ collection_slug: null โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ repo_id: ThomasTheMaker/pico-decoder-tiny โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ learning_dynamics: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ batch_size: 1 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ eval_data: null โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ layer_suffixes: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ - attention.v_proj โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ - attention.o_proj โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ - swiglu.w_2 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ sequence_idx: -1 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ learning_dynamics_dir: learning_dynamics โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ logs_dir: logs โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ run_name: pico-decoder-tiny-wikipedia_en-v1 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ runs_dir: runs โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ save_every_n_steps: 2000 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ save_to_hf: false โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ training: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ auto_resume: true โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ data: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ dataloader: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ batch_size: 16 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ dataset: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ name: ThomasTheMaker/pretokenized_wiki_en โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ tokenizer: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ name: allenai/OLMo-7B-0724-hf โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ vocab_size: 50304 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ evaluation: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ metrics: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ - paloma โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ paloma: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ batch_size: 1 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ dataset_name: pico-lm/pretokenized-paloma-tinsy โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ dataset_split: val โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ max_length: 2048 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ model: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ activation_hidden_dim: 384 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ attention_n_heads: 12 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ attention_n_kv_heads: 4 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ batch_size: 1024 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ d_model: 96 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ max_seq_len: 2048 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ model_type: pico_decoder โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ n_layers: 12 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ norm_eps: 1.0e-06 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ position_emb_theta: 10000.0 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ vocab_size: 50304 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ monitoring: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ logging: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ log_every_n_steps: 100 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ log_level: INFO โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ save_to_wandb: false โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ wandb: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ entity: boymyc โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ project: pico-decoder-tiny โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ training: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ fabric: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ accelerator: cuda โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ num_devices: 1 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ num_nodes: 1 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ precision: bf16-mixed โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ max_steps: 100000 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ optimization: โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ gradient_accumulation_steps: 1 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ lr: 0.0002 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ lr_scheduler: cosine โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ lr_warmup_steps: 2000 โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ optimizer: adamw โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ”‚ โ”‚
2025-08-30 18:45:19 - pico-train - INFO - โ•ฐโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ•ฏ
2025-08-30 18:45:19 - pico-train - INFO - ==================================================
2025-08-30 18:45:19 - pico-train - INFO - โ›ญ Runtime Summary:
2025-08-30 18:45:19 - pico-train - INFO - ==================================================
2025-08-30 18:45:19 - pico-train - INFO - Starting from step: 0
2025-08-30 18:45:19 - pico-train - INFO - Model Setup:
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Total Parameters: 11,282,784
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Trainable Parameters: 11,282,784
2025-08-30 18:45:19 - pico-train - INFO - Distributed Setup:
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Number of Devices: 1
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Device Type: NVIDIA GeForce RTX 5090
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Available Memory: 33.68 GB
2025-08-30 18:45:19 - pico-train - INFO - Software Setup:
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Python Version: 3.10.12
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ PyTorch Version: 2.8.0+cu128
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ CUDA Version: 12.8
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Operating System: Linux 6.8.0-63-generic
2025-08-30 18:45:19 - pico-train - INFO - Batch Size Configuration:
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Global Batch Size: 4
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Per Device Batch Size: 1
2025-08-30 18:45:19 - pico-train - INFO - โ””โ”€ Gradient Accumulation Steps: 4
2025-08-30 18:45:19 - pico-train - INFO - ==================================================
2025-08-30 18:45:20 - pico-train - INFO - Step 0 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:45:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 10.9887
2025-08-30 18:45:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 0.00e+00
2025-08-30 18:45:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:45:20 - pico-train - INFO - Step 0 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 18:46:12 - pico-train - INFO - Step 100 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:46:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 10.9677
2025-08-30 18:46:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.00e-05
2025-08-30 18:46:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:47:04 - pico-train - INFO - Step 200 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:47:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 10.7751
2025-08-30 18:47:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-30 18:47:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:47:56 - pico-train - INFO - Step 300 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:47:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 10.2959
2025-08-30 18:47:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.00e-05
2025-08-30 18:47:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:48:47 - pico-train - INFO - Step 400 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:48:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 9.8408
2025-08-30 18:48:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.00e-05
2025-08-30 18:48:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:49:39 - pico-train - INFO - Step 500 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:49:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 9.4370
2025-08-30 18:49:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.00e-05
2025-08-30 18:49:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:50:31 - pico-train - INFO - Step 600 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:50:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 9.0035
2025-08-30 18:50:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.00e-05
2025-08-30 18:50:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:51:23 - pico-train - INFO - Step 700 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:51:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 8.5848
2025-08-30 18:51:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.00e-05
2025-08-30 18:51:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:52:15 - pico-train - INFO - Step 800 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:52:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 8.1784
2025-08-30 18:52:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.00e-05
2025-08-30 18:52:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:53:07 - pico-train - INFO - Step 900 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:53:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.8857
2025-08-30 18:53:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.00e-05
2025-08-30 18:53:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:53:59 - pico-train - INFO - Step 1000 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:53:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.7107
2025-08-30 18:53:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.00e-04
2025-08-30 18:53:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:54:51 - pico-train - INFO - Step 1100 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:54:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.6318
2025-08-30 18:54:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.10e-04
2025-08-30 18:54:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:55:42 - pico-train - INFO - Step 1200 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:55:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.5751
2025-08-30 18:55:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.20e-04
2025-08-30 18:55:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:56:34 - pico-train - INFO - Step 1300 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:56:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.4863
2025-08-30 18:56:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.30e-04
2025-08-30 18:56:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:57:26 - pico-train - INFO - Step 1400 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:57:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.4114
2025-08-30 18:57:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.40e-04
2025-08-30 18:57:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:58:18 - pico-train - INFO - Step 1500 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:58:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.3511
2025-08-30 18:58:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.50e-04
2025-08-30 18:58:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 18:59:10 - pico-train - INFO - Step 1600 -- ๐Ÿ”„ Training Metrics
2025-08-30 18:59:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.2875
2025-08-30 18:59:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.60e-04
2025-08-30 18:59:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:00:02 - pico-train - INFO - Step 1700 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:00:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.2048
2025-08-30 19:00:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.70e-04
2025-08-30 19:00:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:00:54 - pico-train - INFO - Step 1800 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:00:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.1454
2025-08-30 19:00:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.80e-04
2025-08-30 19:00:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:01:46 - pico-train - INFO - Step 1900 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:01:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.0684
2025-08-30 19:01:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 19:01:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:02:37 - pico-train - INFO - Step 2000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 19:04:26 - pico-train - INFO - Step 2000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 19:04:26 - pico-train - INFO - โ””โ”€โ”€ paloma: 5.052836452912709e+20
2025-08-30 19:04:27 - pico-train - INFO - Step 2000 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:04:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 7.0002
2025-08-30 19:04:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:04:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:04:27 - pico-train - INFO - Step 2000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 19:05:20 - pico-train - INFO - Step 2100 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:05:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.9488
2025-08-30 19:05:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:05:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:06:11 - pico-train - INFO - Step 2200 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:06:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.8843
2025-08-30 19:06:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:06:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:07:03 - pico-train - INFO - Step 2300 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:07:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.7946
2025-08-30 19:07:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:07:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:07:55 - pico-train - INFO - Step 2400 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:07:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.7990
2025-08-30 19:07:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:07:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:08:48 - pico-train - INFO - Step 2500 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:08:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.7534
2025-08-30 19:08:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:08:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:09:40 - pico-train - INFO - Step 2600 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:09:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.7236
2025-08-30 19:09:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:09:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:10:31 - pico-train - INFO - Step 2700 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:10:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.6555
2025-08-30 19:10:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:10:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:11:23 - pico-train - INFO - Step 2800 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:11:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.6370
2025-08-30 19:11:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:11:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:12:15 - pico-train - INFO - Step 2900 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:12:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.5945
2025-08-30 19:12:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:12:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:13:07 - pico-train - INFO - Step 3000 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:13:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.5725
2025-08-30 19:13:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:13:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:13:59 - pico-train - INFO - Step 3100 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:13:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.5427
2025-08-30 19:13:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:13:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:14:50 - pico-train - INFO - Step 3200 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:14:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.4710
2025-08-30 19:14:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:14:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:15:42 - pico-train - INFO - Step 3300 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:15:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.4428
2025-08-30 19:15:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:15:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:16:33 - pico-train - INFO - Step 3400 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:16:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.4280
2025-08-30 19:16:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:16:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:17:26 - pico-train - INFO - Step 3500 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:17:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.4210
2025-08-30 19:17:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:17:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:18:17 - pico-train - INFO - Step 3600 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:18:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.3990
2025-08-30 19:18:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:18:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:19:09 - pico-train - INFO - Step 3700 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:19:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.3625
2025-08-30 19:19:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:19:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:20:01 - pico-train - INFO - Step 3800 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:20:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.3046
2025-08-30 19:20:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:20:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:20:53 - pico-train - INFO - Step 3900 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:20:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.3153
2025-08-30 19:20:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:20:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:21:44 - pico-train - INFO - Step 4000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 19:23:33 - pico-train - INFO - Step 4000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 19:23:33 - pico-train - INFO - โ””โ”€โ”€ paloma: 2.7323051886316706e+23
2025-08-30 19:23:34 - pico-train - INFO - Step 4000 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:23:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.3194
2025-08-30 19:23:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:23:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:23:34 - pico-train - INFO - Step 4000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 19:24:26 - pico-train - INFO - Step 4100 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:24:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.2506
2025-08-30 19:24:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:24:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:25:18 - pico-train - INFO - Step 4200 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:25:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.2754
2025-08-30 19:25:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:25:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:26:10 - pico-train - INFO - Step 4300 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:26:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.2454
2025-08-30 19:26:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:26:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:27:02 - pico-train - INFO - Step 4400 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:27:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.1827
2025-08-30 19:27:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:27:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:27:54 - pico-train - INFO - Step 4500 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:27:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.1813
2025-08-30 19:27:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:27:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:28:46 - pico-train - INFO - Step 4600 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:28:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.1643
2025-08-30 19:28:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:28:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:29:37 - pico-train - INFO - Step 4700 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:29:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.1493
2025-08-30 19:29:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:29:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:30:29 - pico-train - INFO - Step 4800 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:30:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.1469
2025-08-30 19:30:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:30:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:31:20 - pico-train - INFO - Step 4900 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:31:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.0782
2025-08-30 19:31:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:31:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:32:13 - pico-train - INFO - Step 5000 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:32:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.1336
2025-08-30 19:32:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:32:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:33:04 - pico-train - INFO - Step 5100 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:33:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.1217
2025-08-30 19:33:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-04
2025-08-30 19:33:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:33:56 - pico-train - INFO - Step 5200 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:33:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.0658
2025-08-30 19:33:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:33:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:34:47 - pico-train - INFO - Step 5300 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:34:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.0400
2025-08-30 19:34:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:34:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:35:39 - pico-train - INFO - Step 5400 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:35:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.0474
2025-08-30 19:35:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:35:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:36:31 - pico-train - INFO - Step 5500 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:36:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.9896
2025-08-30 19:36:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:36:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:37:23 - pico-train - INFO - Step 5600 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:37:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.0158
2025-08-30 19:37:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:37:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:38:15 - pico-train - INFO - Step 5700 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:38:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 6.0185
2025-08-30 19:38:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:38:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:39:07 - pico-train - INFO - Step 5800 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:39:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.9898
2025-08-30 19:39:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:39:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:39:58 - pico-train - INFO - Step 5900 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:39:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.9851
2025-08-30 19:39:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:39:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:40:49 - pico-train - INFO - Step 6000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 19:42:40 - pico-train - INFO - Step 6000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 19:42:40 - pico-train - INFO - โ””โ”€โ”€ paloma: 1.6707155203187867e+26
2025-08-30 19:42:41 - pico-train - INFO - Step 6000 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:42:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.9321
2025-08-30 19:42:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:42:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:42:41 - pico-train - INFO - Step 6000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 19:43:34 - pico-train - INFO - Step 6100 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:43:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.9322
2025-08-30 19:43:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:43:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:44:26 - pico-train - INFO - Step 6200 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:44:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.9436
2025-08-30 19:44:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:44:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:45:17 - pico-train - INFO - Step 6300 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:45:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.8953
2025-08-30 19:45:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:45:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:46:09 - pico-train - INFO - Step 6400 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:46:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.8631
2025-08-30 19:46:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:46:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:47:01 - pico-train - INFO - Step 6500 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:47:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.8680
2025-08-30 19:47:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:47:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:47:53 - pico-train - INFO - Step 6600 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:47:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.8913
2025-08-30 19:47:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:47:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:48:45 - pico-train - INFO - Step 6700 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:48:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.9308
2025-08-30 19:48:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:48:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:49:37 - pico-train - INFO - Step 6800 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:49:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.8280
2025-08-30 19:49:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:49:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:50:29 - pico-train - INFO - Step 6900 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:50:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.8122
2025-08-30 19:50:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:50:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:51:21 - pico-train - INFO - Step 7000 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:51:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.8374
2025-08-30 19:51:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:51:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:52:13 - pico-train - INFO - Step 7100 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:52:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4755
2025-08-30 19:52:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:52:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:53:05 - pico-train - INFO - Step 7200 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:53:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6391
2025-08-30 19:53:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:53:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:53:57 - pico-train - INFO - Step 7300 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:53:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.7914
2025-08-30 19:53:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:53:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:54:48 - pico-train - INFO - Step 7400 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:54:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.7551
2025-08-30 19:54:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.99e-04
2025-08-30 19:54:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:55:41 - pico-train - INFO - Step 7500 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:55:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.7208
2025-08-30 19:55:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 19:55:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:56:32 - pico-train - INFO - Step 7600 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:56:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6070
2025-08-30 19:56:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 19:56:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:57:24 - pico-train - INFO - Step 7700 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:57:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3528
2025-08-30 19:57:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 19:57:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:58:15 - pico-train - INFO - Step 7800 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:58:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4300
2025-08-30 19:58:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 19:58:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:59:07 - pico-train - INFO - Step 7900 -- ๐Ÿ”„ Training Metrics
2025-08-30 19:59:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4836
2025-08-30 19:59:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 19:59:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 19:59:58 - pico-train - INFO - Step 8000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 20:01:49 - pico-train - INFO - Step 8000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 20:01:49 - pico-train - INFO - โ””โ”€โ”€ paloma: 5.458564756516313e+32
2025-08-30 20:01:50 - pico-train - INFO - Step 8000 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:01:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6596
2025-08-30 20:01:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:01:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:01:50 - pico-train - INFO - Step 8000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 20:02:43 - pico-train - INFO - Step 8100 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:02:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6682
2025-08-30 20:02:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:02:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:03:34 - pico-train - INFO - Step 8200 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:03:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.7168
2025-08-30 20:03:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:03:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:04:26 - pico-train - INFO - Step 8300 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:04:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6882
2025-08-30 20:04:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:04:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:05:18 - pico-train - INFO - Step 8400 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:05:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6670
2025-08-30 20:05:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:05:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:06:11 - pico-train - INFO - Step 8500 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:06:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6494
2025-08-30 20:06:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:06:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:07:03 - pico-train - INFO - Step 8600 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:07:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6230
2025-08-30 20:07:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:07:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:07:54 - pico-train - INFO - Step 8700 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:07:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6758
2025-08-30 20:07:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:07:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:08:46 - pico-train - INFO - Step 8800 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:08:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2235
2025-08-30 20:08:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:08:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:09:37 - pico-train - INFO - Step 8900 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:09:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3350
2025-08-30 20:09:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.98e-04
2025-08-30 20:09:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:10:30 - pico-train - INFO - Step 9000 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:10:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5705
2025-08-30 20:10:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:10:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:11:21 - pico-train - INFO - Step 9100 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:11:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6158
2025-08-30 20:11:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:11:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:12:13 - pico-train - INFO - Step 9200 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:12:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6318
2025-08-30 20:12:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:12:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:13:04 - pico-train - INFO - Step 9300 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:13:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5648
2025-08-30 20:13:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:13:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:13:56 - pico-train - INFO - Step 9400 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:13:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5175
2025-08-30 20:13:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:13:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:14:49 - pico-train - INFO - Step 9500 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:14:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5606
2025-08-30 20:14:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:14:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:15:40 - pico-train - INFO - Step 9600 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:15:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5785
2025-08-30 20:15:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:15:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:16:32 - pico-train - INFO - Step 9700 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:16:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6221
2025-08-30 20:16:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:16:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:17:24 - pico-train - INFO - Step 9800 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:17:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5889
2025-08-30 20:17:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:17:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:18:15 - pico-train - INFO - Step 9900 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:18:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6375
2025-08-30 20:18:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:18:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:19:07 - pico-train - INFO - Step 10000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 20:20:57 - pico-train - INFO - Step 10000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 20:20:57 - pico-train - INFO - โ””โ”€โ”€ paloma: 2.30417566298098e+31
2025-08-30 20:20:58 - pico-train - INFO - Step 10000 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:20:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5828
2025-08-30 20:20:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:20:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:20:58 - pico-train - INFO - Step 10000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 20:21:51 - pico-train - INFO - Step 10100 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:21:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5754
2025-08-30 20:21:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:21:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:22:42 - pico-train - INFO - Step 10200 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:22:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.6074
2025-08-30 20:22:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.97e-04
2025-08-30 20:22:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:23:34 - pico-train - INFO - Step 10300 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:23:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5959
2025-08-30 20:23:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:23:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:24:25 - pico-train - INFO - Step 10400 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:24:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5846
2025-08-30 20:24:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:24:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:25:18 - pico-train - INFO - Step 10500 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:25:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5355
2025-08-30 20:25:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:25:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:26:10 - pico-train - INFO - Step 10600 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:26:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5638
2025-08-30 20:26:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:26:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:27:02 - pico-train - INFO - Step 10700 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:27:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5035
2025-08-30 20:27:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:27:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:27:53 - pico-train - INFO - Step 10800 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:27:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4736
2025-08-30 20:27:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:27:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:28:45 - pico-train - INFO - Step 10900 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:28:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5359
2025-08-30 20:28:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:28:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:29:37 - pico-train - INFO - Step 11000 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:29:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5173
2025-08-30 20:29:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:29:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:30:29 - pico-train - INFO - Step 11100 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:30:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4951
2025-08-30 20:30:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:30:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:31:20 - pico-train - INFO - Step 11200 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:31:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4697
2025-08-30 20:31:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:31:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:32:12 - pico-train - INFO - Step 11300 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:32:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4093
2025-08-30 20:32:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.96e-04
2025-08-30 20:32:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:33:04 - pico-train - INFO - Step 11400 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:33:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.5173
2025-08-30 20:33:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:33:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:33:56 - pico-train - INFO - Step 11500 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:33:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4804
2025-08-30 20:33:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:33:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:34:48 - pico-train - INFO - Step 11600 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:34:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4382
2025-08-30 20:34:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:34:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:35:39 - pico-train - INFO - Step 11700 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:35:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4080
2025-08-30 20:35:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:35:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:36:31 - pico-train - INFO - Step 11800 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:36:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4179
2025-08-30 20:36:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:36:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:37:23 - pico-train - INFO - Step 11900 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:37:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4318
2025-08-30 20:37:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:37:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:38:14 - pico-train - INFO - Step 12000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 20:40:02 - pico-train - INFO - Step 12000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 20:40:02 - pico-train - INFO - โ””โ”€โ”€ paloma: 1.5035041453279693e+33
2025-08-30 20:40:03 - pico-train - INFO - Step 12000 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:40:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4911
2025-08-30 20:40:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:40:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:40:03 - pico-train - INFO - Step 12000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 20:40:56 - pico-train - INFO - Step 12100 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:40:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4785
2025-08-30 20:40:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:40:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:41:47 - pico-train - INFO - Step 12200 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:41:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4698
2025-08-30 20:41:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:41:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:42:39 - pico-train - INFO - Step 12300 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:42:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4358
2025-08-30 20:42:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.95e-04
2025-08-30 20:42:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:43:31 - pico-train - INFO - Step 12400 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:43:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4874
2025-08-30 20:43:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:43:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:44:23 - pico-train - INFO - Step 12500 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:44:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4446
2025-08-30 20:44:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:44:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:45:15 - pico-train - INFO - Step 12600 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:45:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4319
2025-08-30 20:45:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:45:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:46:07 - pico-train - INFO - Step 12700 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:46:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4340
2025-08-30 20:46:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:46:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:46:59 - pico-train - INFO - Step 12800 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:46:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3721
2025-08-30 20:46:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:46:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:47:50 - pico-train - INFO - Step 12900 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:47:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.4168
2025-08-30 20:47:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:47:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:48:42 - pico-train - INFO - Step 13000 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:48:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3633
2025-08-30 20:48:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:48:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:49:33 - pico-train - INFO - Step 13100 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:49:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1710
2025-08-30 20:49:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:49:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:50:25 - pico-train - INFO - Step 13200 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:50:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2070
2025-08-30 20:50:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:50:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:51:17 - pico-train - INFO - Step 13300 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:51:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2383
2025-08-30 20:51:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.94e-04
2025-08-30 20:51:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:52:09 - pico-train - INFO - Step 13400 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:52:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9534
2025-08-30 20:52:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 20:52:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:53:01 - pico-train - INFO - Step 13500 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:53:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3736
2025-08-30 20:53:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 20:53:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:53:53 - pico-train - INFO - Step 13600 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:53:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3662
2025-08-30 20:53:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 20:53:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:54:45 - pico-train - INFO - Step 13700 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:54:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3711
2025-08-30 20:54:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 20:54:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:55:36 - pico-train - INFO - Step 13800 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:55:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3487
2025-08-30 20:55:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 20:55:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:56:27 - pico-train - INFO - Step 13900 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:56:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3742
2025-08-30 20:56:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 20:56:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:57:19 - pico-train - INFO - Step 14000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 20:59:09 - pico-train - INFO - Step 14000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 20:59:09 - pico-train - INFO - โ””โ”€โ”€ paloma: 7.8069653363655655e+34
2025-08-30 20:59:09 - pico-train - INFO - Step 14000 -- ๐Ÿ”„ Training Metrics
2025-08-30 20:59:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3518
2025-08-30 20:59:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 20:59:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 20:59:09 - pico-train - INFO - Step 14000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 21:00:02 - pico-train - INFO - Step 14100 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:00:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0946
2025-08-30 21:00:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.93e-04
2025-08-30 21:00:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:00:54 - pico-train - INFO - Step 14200 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:00:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3664
2025-08-30 21:00:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:00:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:01:45 - pico-train - INFO - Step 14300 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:01:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1603
2025-08-30 21:01:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:01:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:02:37 - pico-train - INFO - Step 14400 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:02:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3446
2025-08-30 21:02:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:02:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:03:29 - pico-train - INFO - Step 14500 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:03:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2801
2025-08-30 21:03:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:03:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:04:21 - pico-train - INFO - Step 14600 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:04:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3449
2025-08-30 21:04:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:04:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:05:13 - pico-train - INFO - Step 14700 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:05:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2675
2025-08-30 21:05:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:05:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:06:05 - pico-train - INFO - Step 14800 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:06:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3139
2025-08-30 21:06:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:06:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:06:56 - pico-train - INFO - Step 14900 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:06:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2704
2025-08-30 21:06:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.92e-04
2025-08-30 21:06:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:07:49 - pico-train - INFO - Step 15000 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:07:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3162
2025-08-30 21:07:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:07:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:08:40 - pico-train - INFO - Step 15100 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:08:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3013
2025-08-30 21:08:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:08:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:09:32 - pico-train - INFO - Step 15200 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:09:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3360
2025-08-30 21:09:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:09:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:10:26 - pico-train - INFO - Step 15300 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:10:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2511
2025-08-30 21:10:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:10:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:11:17 - pico-train - INFO - Step 15400 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:11:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3518
2025-08-30 21:11:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:11:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:12:09 - pico-train - INFO - Step 15500 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:12:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3463
2025-08-30 21:12:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:12:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:13:01 - pico-train - INFO - Step 15600 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:13:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3388
2025-08-30 21:13:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:13:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:13:53 - pico-train - INFO - Step 15700 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:13:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2737
2025-08-30 21:13:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.91e-04
2025-08-30 21:13:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:14:45 - pico-train - INFO - Step 15800 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:14:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3195
2025-08-30 21:14:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 21:14:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:15:37 - pico-train - INFO - Step 15900 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:15:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2779
2025-08-30 21:15:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 21:15:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:16:28 - pico-train - INFO - Step 16000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 21:18:17 - pico-train - INFO - Step 16000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 21:18:17 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 21:18:17 - pico-train - INFO - Step 16000 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:18:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2974
2025-08-30 21:18:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 21:18:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:18:17 - pico-train - INFO - Step 16000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 21:19:09 - pico-train - INFO - Step 16100 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:19:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2737
2025-08-30 21:19:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 21:19:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:20:01 - pico-train - INFO - Step 16200 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:20:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2285
2025-08-30 21:20:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 21:20:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:20:52 - pico-train - INFO - Step 16300 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:20:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2327
2025-08-30 21:20:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 21:20:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:21:44 - pico-train - INFO - Step 16400 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:21:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2827
2025-08-30 21:21:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.90e-04
2025-08-30 21:21:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:22:37 - pico-train - INFO - Step 16500 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:22:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2770
2025-08-30 21:22:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.89e-04
2025-08-30 21:22:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:23:29 - pico-train - INFO - Step 16600 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:23:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.3294
2025-08-30 21:23:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.89e-04
2025-08-30 21:23:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:24:21 - pico-train - INFO - Step 16700 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:24:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2354
2025-08-30 21:24:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.89e-04
2025-08-30 21:24:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:25:13 - pico-train - INFO - Step 16800 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:25:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2687
2025-08-30 21:25:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.89e-04
2025-08-30 21:25:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:26:04 - pico-train - INFO - Step 16900 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:26:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2713
2025-08-30 21:26:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.89e-04
2025-08-30 21:26:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:26:56 - pico-train - INFO - Step 17000 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:26:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2079
2025-08-30 21:26:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.89e-04
2025-08-30 21:26:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:27:48 - pico-train - INFO - Step 17100 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:27:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2177
2025-08-30 21:27:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.89e-04
2025-08-30 21:27:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:28:39 - pico-train - INFO - Step 17200 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:28:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2245
2025-08-30 21:28:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.88e-04
2025-08-30 21:28:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:29:31 - pico-train - INFO - Step 17300 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:29:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0896
2025-08-30 21:29:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.88e-04
2025-08-30 21:29:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:30:22 - pico-train - INFO - Step 17400 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:30:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9397
2025-08-30 21:30:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.88e-04
2025-08-30 21:30:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:31:16 - pico-train - INFO - Step 17500 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:31:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9093
2025-08-30 21:31:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.88e-04
2025-08-30 21:31:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:32:08 - pico-train - INFO - Step 17600 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:32:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0573
2025-08-30 21:32:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.88e-04
2025-08-30 21:32:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:33:00 - pico-train - INFO - Step 17700 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:33:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0873
2025-08-30 21:33:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.88e-04
2025-08-30 21:33:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:33:51 - pico-train - INFO - Step 17800 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:33:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0730
2025-08-30 21:33:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.87e-04
2025-08-30 21:33:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:34:43 - pico-train - INFO - Step 17900 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:34:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1804
2025-08-30 21:34:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.87e-04
2025-08-30 21:34:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:35:35 - pico-train - INFO - Step 18000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 21:37:23 - pico-train - INFO - Step 18000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 21:37:23 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 21:37:23 - pico-train - INFO - Step 18000 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:37:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2105
2025-08-30 21:37:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.87e-04
2025-08-30 21:37:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:37:23 - pico-train - INFO - Step 18000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 21:38:16 - pico-train - INFO - Step 18100 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:38:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1961
2025-08-30 21:38:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.87e-04
2025-08-30 21:38:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:39:08 - pico-train - INFO - Step 18200 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:39:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2475
2025-08-30 21:39:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.87e-04
2025-08-30 21:39:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:39:59 - pico-train - INFO - Step 18300 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:39:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2362
2025-08-30 21:39:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.87e-04
2025-08-30 21:39:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:40:51 - pico-train - INFO - Step 18400 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:40:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2194
2025-08-30 21:40:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.86e-04
2025-08-30 21:40:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:41:44 - pico-train - INFO - Step 18500 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:41:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.2559
2025-08-30 21:41:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.86e-04
2025-08-30 21:41:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:42:35 - pico-train - INFO - Step 18600 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:42:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1074
2025-08-30 21:42:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.86e-04
2025-08-30 21:42:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:43:27 - pico-train - INFO - Step 18700 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:43:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1509
2025-08-30 21:43:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.86e-04
2025-08-30 21:43:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:44:19 - pico-train - INFO - Step 18800 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:44:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1142
2025-08-30 21:44:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.86e-04
2025-08-30 21:44:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:45:10 - pico-train - INFO - Step 18900 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:45:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1417
2025-08-30 21:45:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.86e-04
2025-08-30 21:45:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:46:03 - pico-train - INFO - Step 19000 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:46:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1488
2025-08-30 21:46:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.86e-04
2025-08-30 21:46:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:46:54 - pico-train - INFO - Step 19100 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:46:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1151
2025-08-30 21:46:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.85e-04
2025-08-30 21:46:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:47:46 - pico-train - INFO - Step 19200 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:47:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1375
2025-08-30 21:47:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.85e-04
2025-08-30 21:47:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:48:38 - pico-train - INFO - Step 19300 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:48:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1469
2025-08-30 21:48:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.85e-04
2025-08-30 21:48:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:49:30 - pico-train - INFO - Step 19400 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:49:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1239
2025-08-30 21:49:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.85e-04
2025-08-30 21:49:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:50:22 - pico-train - INFO - Step 19500 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:50:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1759
2025-08-30 21:50:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.85e-04
2025-08-30 21:50:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:51:14 - pico-train - INFO - Step 19600 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:51:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0507
2025-08-30 21:51:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.85e-04
2025-08-30 21:51:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:52:05 - pico-train - INFO - Step 19700 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:52:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0907
2025-08-30 21:52:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.84e-04
2025-08-30 21:52:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:52:57 - pico-train - INFO - Step 19800 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:52:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4806
2025-08-30 21:52:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.84e-04
2025-08-30 21:52:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:53:49 - pico-train - INFO - Step 19900 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:53:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9627
2025-08-30 21:53:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.84e-04
2025-08-30 21:53:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:54:40 - pico-train - INFO - Step 20000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 21:56:29 - pico-train - INFO - Step 20000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 21:56:29 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 21:56:30 - pico-train - INFO - Step 20000 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:56:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9833
2025-08-30 21:56:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.84e-04
2025-08-30 21:56:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:56:30 - pico-train - INFO - Step 20000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 21:57:22 - pico-train - INFO - Step 20100 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:57:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7830
2025-08-30 21:57:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.84e-04
2025-08-30 21:57:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:58:14 - pico-train - INFO - Step 20200 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:58:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9470
2025-08-30 21:58:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.83e-04
2025-08-30 21:58:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:59:06 - pico-train - INFO - Step 20300 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:59:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0469
2025-08-30 21:59:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.83e-04
2025-08-30 21:59:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 21:59:57 - pico-train - INFO - Step 20400 -- ๐Ÿ”„ Training Metrics
2025-08-30 21:59:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9170
2025-08-30 21:59:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.83e-04
2025-08-30 21:59:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:00:49 - pico-train - INFO - Step 20500 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:00:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1611
2025-08-30 22:00:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.83e-04
2025-08-30 22:00:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:01:41 - pico-train - INFO - Step 20600 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:01:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1110
2025-08-30 22:01:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.83e-04
2025-08-30 22:01:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:02:33 - pico-train - INFO - Step 20700 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:02:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1728
2025-08-30 22:02:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.83e-04
2025-08-30 22:02:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:03:24 - pico-train - INFO - Step 20800 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:03:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1312
2025-08-30 22:03:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.82e-04
2025-08-30 22:03:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:04:16 - pico-train - INFO - Step 20900 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:04:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1331
2025-08-30 22:04:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.82e-04
2025-08-30 22:04:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:05:08 - pico-train - INFO - Step 21000 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:05:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1372
2025-08-30 22:05:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.82e-04
2025-08-30 22:05:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:06:00 - pico-train - INFO - Step 21100 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:06:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1923
2025-08-30 22:06:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.82e-04
2025-08-30 22:06:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:06:52 - pico-train - INFO - Step 21200 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:06:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0971
2025-08-30 22:06:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.82e-04
2025-08-30 22:06:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:07:44 - pico-train - INFO - Step 21300 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:07:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1132
2025-08-30 22:07:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.81e-04
2025-08-30 22:07:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:08:35 - pico-train - INFO - Step 21400 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:08:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0486
2025-08-30 22:08:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.81e-04
2025-08-30 22:08:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:09:28 - pico-train - INFO - Step 21500 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:09:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0345
2025-08-30 22:09:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.81e-04
2025-08-30 22:09:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:10:19 - pico-train - INFO - Step 21600 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:10:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0882
2025-08-30 22:10:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.81e-04
2025-08-30 22:10:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:11:11 - pico-train - INFO - Step 21700 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:11:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1284
2025-08-30 22:11:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.81e-04
2025-08-30 22:11:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:12:03 - pico-train - INFO - Step 21800 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:12:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0334
2025-08-30 22:12:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.81e-04
2025-08-30 22:12:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:12:55 - pico-train - INFO - Step 21900 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:12:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0281
2025-08-30 22:12:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.80e-04
2025-08-30 22:12:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:13:46 - pico-train - INFO - Step 22000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 22:15:34 - pico-train - INFO - Step 22000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 22:15:34 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 22:15:35 - pico-train - INFO - Step 22000 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:15:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0481
2025-08-30 22:15:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.80e-04
2025-08-30 22:15:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:15:35 - pico-train - INFO - Step 22000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 22:16:27 - pico-train - INFO - Step 22100 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:16:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0789
2025-08-30 22:16:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.80e-04
2025-08-30 22:16:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:17:19 - pico-train - INFO - Step 22200 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:17:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1574
2025-08-30 22:17:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.80e-04
2025-08-30 22:17:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:18:11 - pico-train - INFO - Step 22300 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:18:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0839
2025-08-30 22:18:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.80e-04
2025-08-30 22:18:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:19:02 - pico-train - INFO - Step 22400 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:19:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9870
2025-08-30 22:19:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.79e-04
2025-08-30 22:19:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:20:06 - pico-train - INFO - Step 22500 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:20:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0445
2025-08-30 22:20:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.79e-04
2025-08-30 22:20:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:20:57 - pico-train - INFO - Step 22600 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:20:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0542
2025-08-30 22:20:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.79e-04
2025-08-30 22:20:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:21:49 - pico-train - INFO - Step 22700 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:21:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8050
2025-08-30 22:21:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.79e-04
2025-08-30 22:21:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:22:41 - pico-train - INFO - Step 22800 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:22:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9966
2025-08-30 22:22:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.79e-04
2025-08-30 22:22:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:23:33 - pico-train - INFO - Step 22900 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:23:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0640
2025-08-30 22:23:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.78e-04
2025-08-30 22:23:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:24:32 - pico-train - INFO - Step 23000 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:24:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0862
2025-08-30 22:24:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.78e-04
2025-08-30 22:24:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:25:24 - pico-train - INFO - Step 23100 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:25:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0783
2025-08-30 22:25:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.78e-04
2025-08-30 22:25:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:26:15 - pico-train - INFO - Step 23200 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:26:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0221
2025-08-30 22:26:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.78e-04
2025-08-30 22:26:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:27:07 - pico-train - INFO - Step 23300 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:27:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0721
2025-08-30 22:27:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.78e-04
2025-08-30 22:27:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:27:59 - pico-train - INFO - Step 23400 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:27:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0740
2025-08-30 22:27:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.77e-04
2025-08-30 22:27:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:28:52 - pico-train - INFO - Step 23500 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:28:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0539
2025-08-30 22:28:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.77e-04
2025-08-30 22:28:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:29:44 - pico-train - INFO - Step 23600 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:29:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0133
2025-08-30 22:29:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.77e-04
2025-08-30 22:29:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:30:36 - pico-train - INFO - Step 23700 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:30:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9849
2025-08-30 22:30:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.77e-04
2025-08-30 22:30:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:31:28 - pico-train - INFO - Step 23800 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:31:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8925
2025-08-30 22:31:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.77e-04
2025-08-30 22:31:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:32:19 - pico-train - INFO - Step 23900 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:32:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9386
2025-08-30 22:32:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.76e-04
2025-08-30 22:32:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:33:11 - pico-train - INFO - Step 24000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 22:35:00 - pico-train - INFO - Step 24000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 22:35:00 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 22:35:01 - pico-train - INFO - Step 24000 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:35:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9406
2025-08-30 22:35:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.76e-04
2025-08-30 22:35:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:35:01 - pico-train - INFO - Step 24000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 22:35:53 - pico-train - INFO - Step 24100 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:35:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9201
2025-08-30 22:35:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.76e-04
2025-08-30 22:35:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:36:45 - pico-train - INFO - Step 24200 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:36:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0127
2025-08-30 22:36:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.76e-04
2025-08-30 22:36:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:37:36 - pico-train - INFO - Step 24300 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:37:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0086
2025-08-30 22:37:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.76e-04
2025-08-30 22:37:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:38:28 - pico-train - INFO - Step 24400 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:38:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0631
2025-08-30 22:38:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.75e-04
2025-08-30 22:38:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:39:21 - pico-train - INFO - Step 24500 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:39:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0557
2025-08-30 22:39:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.75e-04
2025-08-30 22:39:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:40:12 - pico-train - INFO - Step 24600 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:40:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1006
2025-08-30 22:40:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.75e-04
2025-08-30 22:40:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:41:04 - pico-train - INFO - Step 24700 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:41:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9891
2025-08-30 22:41:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.75e-04
2025-08-30 22:41:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:41:56 - pico-train - INFO - Step 24800 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:41:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0367
2025-08-30 22:41:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.74e-04
2025-08-30 22:41:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:42:48 - pico-train - INFO - Step 24900 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:42:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1347
2025-08-30 22:42:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.74e-04
2025-08-30 22:42:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:43:40 - pico-train - INFO - Step 25000 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:43:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0413
2025-08-30 22:43:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.74e-04
2025-08-30 22:43:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:44:32 - pico-train - INFO - Step 25100 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:44:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0933
2025-08-30 22:44:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.74e-04
2025-08-30 22:44:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:45:23 - pico-train - INFO - Step 25200 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:45:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0863
2025-08-30 22:45:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.74e-04
2025-08-30 22:45:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:46:15 - pico-train - INFO - Step 25300 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:46:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0696
2025-08-30 22:46:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.73e-04
2025-08-30 22:46:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:47:07 - pico-train - INFO - Step 25400 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:47:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0548
2025-08-30 22:47:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.73e-04
2025-08-30 22:47:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:47:59 - pico-train - INFO - Step 25500 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:47:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0383
2025-08-30 22:47:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.73e-04
2025-08-30 22:47:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:48:51 - pico-train - INFO - Step 25600 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:48:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0622
2025-08-30 22:48:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.73e-04
2025-08-30 22:48:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:49:43 - pico-train - INFO - Step 25700 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:49:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.1004
2025-08-30 22:49:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.73e-04
2025-08-30 22:49:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:50:35 - pico-train - INFO - Step 25800 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:50:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0557
2025-08-30 22:50:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.72e-04
2025-08-30 22:50:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:51:26 - pico-train - INFO - Step 25900 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:51:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0435
2025-08-30 22:51:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.72e-04
2025-08-30 22:51:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:52:18 - pico-train - INFO - Step 26000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 22:54:07 - pico-train - INFO - Step 26000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 22:54:07 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 22:54:07 - pico-train - INFO - Step 26000 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:54:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0616
2025-08-30 22:54:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.72e-04
2025-08-30 22:54:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:54:07 - pico-train - INFO - Step 26000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 22:54:59 - pico-train - INFO - Step 26100 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:54:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0612
2025-08-30 22:54:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.72e-04
2025-08-30 22:54:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:55:51 - pico-train - INFO - Step 26200 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:55:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9843
2025-08-30 22:55:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.71e-04
2025-08-30 22:55:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:56:43 - pico-train - INFO - Step 26300 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:56:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0666
2025-08-30 22:56:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.71e-04
2025-08-30 22:56:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:57:35 - pico-train - INFO - Step 26400 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:57:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0759
2025-08-30 22:57:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.71e-04
2025-08-30 22:57:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:58:27 - pico-train - INFO - Step 26500 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:58:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0495
2025-08-30 22:58:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.71e-04
2025-08-30 22:58:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 22:59:19 - pico-train - INFO - Step 26600 -- ๐Ÿ”„ Training Metrics
2025-08-30 22:59:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0772
2025-08-30 22:59:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.70e-04
2025-08-30 22:59:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:00:11 - pico-train - INFO - Step 26700 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:00:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9182
2025-08-30 23:00:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.70e-04
2025-08-30 23:00:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:01:02 - pico-train - INFO - Step 26800 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:01:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0919
2025-08-30 23:01:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.70e-04
2025-08-30 23:01:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:01:54 - pico-train - INFO - Step 26900 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:01:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0713
2025-08-30 23:01:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.70e-04
2025-08-30 23:01:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:02:46 - pico-train - INFO - Step 27000 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:02:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0032
2025-08-30 23:02:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.70e-04
2025-08-30 23:02:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:03:38 - pico-train - INFO - Step 27100 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:03:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0434
2025-08-30 23:03:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.69e-04
2025-08-30 23:03:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:04:30 - pico-train - INFO - Step 27200 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:04:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0721
2025-08-30 23:04:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.69e-04
2025-08-30 23:04:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:05:22 - pico-train - INFO - Step 27300 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:05:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0265
2025-08-30 23:05:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.69e-04
2025-08-30 23:05:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:06:14 - pico-train - INFO - Step 27400 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:06:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0055
2025-08-30 23:06:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.69e-04
2025-08-30 23:06:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:07:06 - pico-train - INFO - Step 27500 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:07:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9898
2025-08-30 23:07:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.68e-04
2025-08-30 23:07:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:07:57 - pico-train - INFO - Step 27600 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:07:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8553
2025-08-30 23:07:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.68e-04
2025-08-30 23:07:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:08:49 - pico-train - INFO - Step 27700 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:08:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9803
2025-08-30 23:08:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.68e-04
2025-08-30 23:08:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:09:41 - pico-train - INFO - Step 27800 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:09:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0268
2025-08-30 23:09:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.68e-04
2025-08-30 23:09:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:10:33 - pico-train - INFO - Step 27900 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:10:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9910
2025-08-30 23:10:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.67e-04
2025-08-30 23:10:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:11:25 - pico-train - INFO - Step 28000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 23:13:14 - pico-train - INFO - Step 28000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 23:13:14 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 23:13:14 - pico-train - INFO - Step 28000 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:13:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9920
2025-08-30 23:13:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.67e-04
2025-08-30 23:13:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:13:14 - pico-train - INFO - Step 28000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 23:14:07 - pico-train - INFO - Step 28100 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:14:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0400
2025-08-30 23:14:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.67e-04
2025-08-30 23:14:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:14:59 - pico-train - INFO - Step 28200 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:14:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9727
2025-08-30 23:14:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.67e-04
2025-08-30 23:14:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:15:51 - pico-train - INFO - Step 28300 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:15:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0073
2025-08-30 23:15:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.67e-04
2025-08-30 23:15:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:16:43 - pico-train - INFO - Step 28400 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:16:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0681
2025-08-30 23:16:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.66e-04
2025-08-30 23:16:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:17:35 - pico-train - INFO - Step 28500 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:17:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0500
2025-08-30 23:17:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.66e-04
2025-08-30 23:17:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:18:27 - pico-train - INFO - Step 28600 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:18:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0144
2025-08-30 23:18:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.66e-04
2025-08-30 23:18:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:19:19 - pico-train - INFO - Step 28700 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:19:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0618
2025-08-30 23:19:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.66e-04
2025-08-30 23:19:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:20:10 - pico-train - INFO - Step 28800 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:20:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0330
2025-08-30 23:20:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.65e-04
2025-08-30 23:20:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:21:02 - pico-train - INFO - Step 28900 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:21:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9992
2025-08-30 23:21:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.65e-04
2025-08-30 23:21:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:21:55 - pico-train - INFO - Step 29000 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:21:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9424
2025-08-30 23:21:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.65e-04
2025-08-30 23:21:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:22:46 - pico-train - INFO - Step 29100 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:22:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9886
2025-08-30 23:22:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.65e-04
2025-08-30 23:22:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:23:38 - pico-train - INFO - Step 29200 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:23:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9621
2025-08-30 23:23:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.64e-04
2025-08-30 23:23:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:24:30 - pico-train - INFO - Step 29300 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:24:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9392
2025-08-30 23:24:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.64e-04
2025-08-30 23:24:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:25:22 - pico-train - INFO - Step 29400 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:25:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0059
2025-08-30 23:25:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.64e-04
2025-08-30 23:25:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:26:14 - pico-train - INFO - Step 29500 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:26:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9028
2025-08-30 23:26:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.64e-04
2025-08-30 23:26:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:27:06 - pico-train - INFO - Step 29600 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:27:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9401
2025-08-30 23:27:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.63e-04
2025-08-30 23:27:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:27:57 - pico-train - INFO - Step 29700 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:27:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8644
2025-08-30 23:27:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.63e-04
2025-08-30 23:27:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:28:49 - pico-train - INFO - Step 29800 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:28:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9997
2025-08-30 23:28:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.63e-04
2025-08-30 23:28:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:29:41 - pico-train - INFO - Step 29900 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:29:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9959
2025-08-30 23:29:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.63e-04
2025-08-30 23:29:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:30:33 - pico-train - INFO - Step 30000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 23:32:32 - pico-train - INFO - Step 30000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 23:32:32 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 23:32:32 - pico-train - INFO - Step 30000 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:32:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6933
2025-08-30 23:32:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.62e-04
2025-08-30 23:32:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:32:32 - pico-train - INFO - Step 30000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 23:33:25 - pico-train - INFO - Step 30100 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:33:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.0656
2025-08-30 23:33:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.62e-04
2025-08-30 23:33:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:34:17 - pico-train - INFO - Step 30200 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:34:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9761
2025-08-30 23:34:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.62e-04
2025-08-30 23:34:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:35:09 - pico-train - INFO - Step 30300 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:35:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9614
2025-08-30 23:35:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.62e-04
2025-08-30 23:35:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:36:01 - pico-train - INFO - Step 30400 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:36:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9599
2025-08-30 23:36:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.61e-04
2025-08-30 23:36:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:36:53 - pico-train - INFO - Step 30500 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:36:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0080
2025-08-30 23:36:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.61e-04
2025-08-30 23:36:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:37:45 - pico-train - INFO - Step 30600 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:37:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9963
2025-08-30 23:37:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.61e-04
2025-08-30 23:37:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:38:37 - pico-train - INFO - Step 30700 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:38:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7991
2025-08-30 23:38:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.61e-04
2025-08-30 23:38:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:39:29 - pico-train - INFO - Step 30800 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:39:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9226
2025-08-30 23:39:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.60e-04
2025-08-30 23:39:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:40:20 - pico-train - INFO - Step 30900 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:40:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9592
2025-08-30 23:40:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.60e-04
2025-08-30 23:40:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:41:13 - pico-train - INFO - Step 31000 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:41:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9497
2025-08-30 23:41:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.60e-04
2025-08-30 23:41:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:42:04 - pico-train - INFO - Step 31100 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:42:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9682
2025-08-30 23:42:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.60e-04
2025-08-30 23:42:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:42:57 - pico-train - INFO - Step 31200 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:42:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0640
2025-08-30 23:42:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.59e-04
2025-08-30 23:42:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:43:48 - pico-train - INFO - Step 31300 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:43:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0062
2025-08-30 23:43:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.59e-04
2025-08-30 23:43:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:44:40 - pico-train - INFO - Step 31400 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:44:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9914
2025-08-30 23:44:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.59e-04
2025-08-30 23:44:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:45:33 - pico-train - INFO - Step 31500 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:45:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9742
2025-08-30 23:45:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.59e-04
2025-08-30 23:45:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:46:25 - pico-train - INFO - Step 31600 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:46:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9519
2025-08-30 23:46:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.58e-04
2025-08-30 23:46:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:47:18 - pico-train - INFO - Step 31700 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:47:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0267
2025-08-30 23:47:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.58e-04
2025-08-30 23:47:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:48:10 - pico-train - INFO - Step 31800 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:48:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9511
2025-08-30 23:48:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.58e-04
2025-08-30 23:48:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:49:02 - pico-train - INFO - Step 31900 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:49:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9648
2025-08-30 23:49:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.57e-04
2025-08-30 23:49:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:49:54 - pico-train - INFO - Step 32000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-30 23:51:43 - pico-train - INFO - Step 32000 -- ๐Ÿ“Š Evaluation Results
2025-08-30 23:51:43 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-30 23:51:43 - pico-train - INFO - Step 32000 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:51:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9717
2025-08-30 23:51:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.57e-04
2025-08-30 23:51:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:51:43 - pico-train - INFO - Step 32000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-30 23:52:36 - pico-train - INFO - Step 32100 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:52:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9565
2025-08-30 23:52:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.57e-04
2025-08-30 23:52:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:53:28 - pico-train - INFO - Step 32200 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:53:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9479
2025-08-30 23:53:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.57e-04
2025-08-30 23:53:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:54:20 - pico-train - INFO - Step 32300 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:54:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9513
2025-08-30 23:54:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.56e-04
2025-08-30 23:54:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:55:12 - pico-train - INFO - Step 32400 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:55:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9405
2025-08-30 23:55:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.56e-04
2025-08-30 23:55:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:56:04 - pico-train - INFO - Step 32500 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:56:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9576
2025-08-30 23:56:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.56e-04
2025-08-30 23:56:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:56:56 - pico-train - INFO - Step 32600 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:56:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7705
2025-08-30 23:56:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.56e-04
2025-08-30 23:56:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:57:48 - pico-train - INFO - Step 32700 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:57:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8987
2025-08-30 23:57:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.55e-04
2025-08-30 23:57:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:58:40 - pico-train - INFO - Step 32800 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:58:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0154
2025-08-30 23:58:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.55e-04
2025-08-30 23:58:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-30 23:59:32 - pico-train - INFO - Step 32900 -- ๐Ÿ”„ Training Metrics
2025-08-30 23:59:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9710
2025-08-30 23:59:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.55e-04
2025-08-30 23:59:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:00:24 - pico-train - INFO - Step 33000 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:00:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9653
2025-08-31 00:00:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.55e-04
2025-08-31 00:00:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:01:16 - pico-train - INFO - Step 33100 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:01:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9613
2025-08-31 00:01:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.54e-04
2025-08-31 00:01:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:02:08 - pico-train - INFO - Step 33200 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:02:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9135
2025-08-31 00:02:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.54e-04
2025-08-31 00:02:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:03:00 - pico-train - INFO - Step 33300 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:03:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0232
2025-08-31 00:03:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.54e-04
2025-08-31 00:03:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:03:52 - pico-train - INFO - Step 33400 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:03:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9169
2025-08-31 00:03:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.53e-04
2025-08-31 00:03:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:04:44 - pico-train - INFO - Step 33500 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:04:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 5.0064
2025-08-31 00:04:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.53e-04
2025-08-31 00:04:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:05:36 - pico-train - INFO - Step 33600 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:05:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8591
2025-08-31 00:05:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.53e-04
2025-08-31 00:05:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:06:29 - pico-train - INFO - Step 33700 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:06:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8708
2025-08-31 00:06:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.53e-04
2025-08-31 00:06:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:07:21 - pico-train - INFO - Step 33800 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:07:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9443
2025-08-31 00:07:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.52e-04
2025-08-31 00:07:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:08:12 - pico-train - INFO - Step 33900 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:08:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8950
2025-08-31 00:08:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.52e-04
2025-08-31 00:08:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:09:05 - pico-train - INFO - Step 34000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 00:10:53 - pico-train - INFO - Step 34000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 00:10:53 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 00:10:54 - pico-train - INFO - Step 34000 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:10:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9473
2025-08-31 00:10:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.52e-04
2025-08-31 00:10:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:10:54 - pico-train - INFO - Step 34000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 00:11:47 - pico-train - INFO - Step 34100 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:11:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9341
2025-08-31 00:11:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.52e-04
2025-08-31 00:11:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:12:39 - pico-train - INFO - Step 34200 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:12:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9262
2025-08-31 00:12:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.51e-04
2025-08-31 00:12:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:13:30 - pico-train - INFO - Step 34300 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:13:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9611
2025-08-31 00:13:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.51e-04
2025-08-31 00:13:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:14:22 - pico-train - INFO - Step 34400 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:14:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9589
2025-08-31 00:14:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.51e-04
2025-08-31 00:14:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:15:15 - pico-train - INFO - Step 34500 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:15:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9880
2025-08-31 00:15:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.50e-04
2025-08-31 00:15:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:16:07 - pico-train - INFO - Step 34600 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:16:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9131
2025-08-31 00:16:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.50e-04
2025-08-31 00:16:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:16:58 - pico-train - INFO - Step 34700 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:16:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9326
2025-08-31 00:16:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.50e-04
2025-08-31 00:16:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:17:49 - pico-train - INFO - Step 34800 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:17:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9564
2025-08-31 00:17:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.50e-04
2025-08-31 00:17:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:18:41 - pico-train - INFO - Step 34900 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:18:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9996
2025-08-31 00:18:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.49e-04
2025-08-31 00:18:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:19:34 - pico-train - INFO - Step 35000 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:19:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9842
2025-08-31 00:19:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.49e-04
2025-08-31 00:19:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:20:25 - pico-train - INFO - Step 35100 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:20:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9394
2025-08-31 00:20:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.49e-04
2025-08-31 00:20:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:21:17 - pico-train - INFO - Step 35200 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:21:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9387
2025-08-31 00:21:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.49e-04
2025-08-31 00:21:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:22:09 - pico-train - INFO - Step 35300 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:22:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8411
2025-08-31 00:22:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.48e-04
2025-08-31 00:22:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:23:00 - pico-train - INFO - Step 35400 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:23:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8955
2025-08-31 00:23:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.48e-04
2025-08-31 00:23:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:23:53 - pico-train - INFO - Step 35500 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:23:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8802
2025-08-31 00:23:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.48e-04
2025-08-31 00:23:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:24:44 - pico-train - INFO - Step 35600 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:24:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8399
2025-08-31 00:24:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.47e-04
2025-08-31 00:24:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:25:36 - pico-train - INFO - Step 35700 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:25:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9055
2025-08-31 00:25:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.47e-04
2025-08-31 00:25:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:26:27 - pico-train - INFO - Step 35800 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:26:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8051
2025-08-31 00:26:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.47e-04
2025-08-31 00:26:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:27:19 - pico-train - INFO - Step 35900 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:27:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8222
2025-08-31 00:27:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.47e-04
2025-08-31 00:27:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:28:11 - pico-train - INFO - Step 36000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 00:29:59 - pico-train - INFO - Step 36000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 00:29:59 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 00:30:00 - pico-train - INFO - Step 36000 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:30:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9235
2025-08-31 00:30:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.46e-04
2025-08-31 00:30:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:30:00 - pico-train - INFO - Step 36000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 00:30:52 - pico-train - INFO - Step 36100 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:30:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8898
2025-08-31 00:30:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.46e-04
2025-08-31 00:30:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:31:44 - pico-train - INFO - Step 36200 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:31:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9274
2025-08-31 00:31:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.46e-04
2025-08-31 00:31:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:32:35 - pico-train - INFO - Step 36300 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:32:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8847
2025-08-31 00:32:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.45e-04
2025-08-31 00:32:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:33:27 - pico-train - INFO - Step 36400 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:33:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8662
2025-08-31 00:33:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.45e-04
2025-08-31 00:33:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:34:19 - pico-train - INFO - Step 36500 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:34:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9214
2025-08-31 00:34:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.45e-04
2025-08-31 00:34:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:35:11 - pico-train - INFO - Step 36600 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:35:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8951
2025-08-31 00:35:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.45e-04
2025-08-31 00:35:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:36:03 - pico-train - INFO - Step 36700 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:36:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9194
2025-08-31 00:36:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.44e-04
2025-08-31 00:36:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:36:54 - pico-train - INFO - Step 36800 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:36:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8769
2025-08-31 00:36:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.44e-04
2025-08-31 00:36:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:37:46 - pico-train - INFO - Step 36900 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:37:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9548
2025-08-31 00:37:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.44e-04
2025-08-31 00:37:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:38:39 - pico-train - INFO - Step 37000 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:38:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9128
2025-08-31 00:38:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.43e-04
2025-08-31 00:38:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:39:31 - pico-train - INFO - Step 37100 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:39:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8547
2025-08-31 00:39:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.43e-04
2025-08-31 00:39:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:40:22 - pico-train - INFO - Step 37200 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:40:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9243
2025-08-31 00:40:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.43e-04
2025-08-31 00:40:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:41:14 - pico-train - INFO - Step 37300 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:41:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9263
2025-08-31 00:41:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.43e-04
2025-08-31 00:41:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:42:06 - pico-train - INFO - Step 37400 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:42:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9288
2025-08-31 00:42:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.42e-04
2025-08-31 00:42:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:42:58 - pico-train - INFO - Step 37500 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:42:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9187
2025-08-31 00:42:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.42e-04
2025-08-31 00:42:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:43:49 - pico-train - INFO - Step 37600 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:43:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8727
2025-08-31 00:43:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.42e-04
2025-08-31 00:43:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:44:41 - pico-train - INFO - Step 37700 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:44:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8757
2025-08-31 00:44:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.41e-04
2025-08-31 00:44:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:45:32 - pico-train - INFO - Step 37800 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:45:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9217
2025-08-31 00:45:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.41e-04
2025-08-31 00:45:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:46:24 - pico-train - INFO - Step 37900 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:46:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7568
2025-08-31 00:46:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.41e-04
2025-08-31 00:46:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:47:16 - pico-train - INFO - Step 38000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 00:49:04 - pico-train - INFO - Step 38000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 00:49:04 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 00:49:05 - pico-train - INFO - Step 38000 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:49:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8588
2025-08-31 00:49:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.40e-04
2025-08-31 00:49:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:49:05 - pico-train - INFO - Step 38000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 00:49:57 - pico-train - INFO - Step 38100 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:49:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8652
2025-08-31 00:49:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.40e-04
2025-08-31 00:49:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:50:48 - pico-train - INFO - Step 38200 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:50:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9169
2025-08-31 00:50:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.40e-04
2025-08-31 00:50:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:51:40 - pico-train - INFO - Step 38300 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:51:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8703
2025-08-31 00:51:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.40e-04
2025-08-31 00:51:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:52:32 - pico-train - INFO - Step 38400 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:52:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8989
2025-08-31 00:52:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.39e-04
2025-08-31 00:52:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:53:24 - pico-train - INFO - Step 38500 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:53:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8944
2025-08-31 00:53:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.39e-04
2025-08-31 00:53:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:54:16 - pico-train - INFO - Step 38600 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:54:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9530
2025-08-31 00:54:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.39e-04
2025-08-31 00:54:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:55:07 - pico-train - INFO - Step 38700 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:55:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9454
2025-08-31 00:55:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.38e-04
2025-08-31 00:55:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:55:59 - pico-train - INFO - Step 38800 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:55:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9611
2025-08-31 00:55:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.38e-04
2025-08-31 00:55:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:56:50 - pico-train - INFO - Step 38900 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:56:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8250
2025-08-31 00:56:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.38e-04
2025-08-31 00:56:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:57:42 - pico-train - INFO - Step 39000 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:57:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8227
2025-08-31 00:57:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.38e-04
2025-08-31 00:57:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:58:34 - pico-train - INFO - Step 39100 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:58:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9350
2025-08-31 00:58:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.37e-04
2025-08-31 00:58:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 00:59:26 - pico-train - INFO - Step 39200 -- ๐Ÿ”„ Training Metrics
2025-08-31 00:59:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9102
2025-08-31 00:59:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.37e-04
2025-08-31 00:59:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:00:17 - pico-train - INFO - Step 39300 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:00:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7694
2025-08-31 01:00:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.37e-04
2025-08-31 01:00:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:01:08 - pico-train - INFO - Step 39400 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:01:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9689
2025-08-31 01:01:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.36e-04
2025-08-31 01:01:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:02:01 - pico-train - INFO - Step 39500 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:02:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9675
2025-08-31 01:02:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.36e-04
2025-08-31 01:02:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:02:52 - pico-train - INFO - Step 39600 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:02:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9184
2025-08-31 01:02:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.36e-04
2025-08-31 01:02:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:03:44 - pico-train - INFO - Step 39700 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:03:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9596
2025-08-31 01:03:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.35e-04
2025-08-31 01:03:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:04:36 - pico-train - INFO - Step 39800 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:04:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9584
2025-08-31 01:04:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.35e-04
2025-08-31 01:04:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:05:28 - pico-train - INFO - Step 39900 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:05:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8758
2025-08-31 01:05:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.35e-04
2025-08-31 01:05:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:06:19 - pico-train - INFO - Step 40000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 01:08:08 - pico-train - INFO - Step 40000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 01:08:08 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 01:08:09 - pico-train - INFO - Step 40000 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:08:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8921
2025-08-31 01:08:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.35e-04
2025-08-31 01:08:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:08:09 - pico-train - INFO - Step 40000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 01:09:01 - pico-train - INFO - Step 40100 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:09:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9123
2025-08-31 01:09:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.34e-04
2025-08-31 01:09:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:09:52 - pico-train - INFO - Step 40200 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:09:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9111
2025-08-31 01:09:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.34e-04
2025-08-31 01:09:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:10:44 - pico-train - INFO - Step 40300 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:10:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8833
2025-08-31 01:10:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.34e-04
2025-08-31 01:10:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:11:36 - pico-train - INFO - Step 40400 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:11:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7673
2025-08-31 01:11:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.33e-04
2025-08-31 01:11:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:12:28 - pico-train - INFO - Step 40500 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:12:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9048
2025-08-31 01:12:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.33e-04
2025-08-31 01:12:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:13:20 - pico-train - INFO - Step 40600 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:13:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8952
2025-08-31 01:13:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.33e-04
2025-08-31 01:13:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:14:11 - pico-train - INFO - Step 40700 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:14:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9022
2025-08-31 01:14:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.32e-04
2025-08-31 01:14:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:15:03 - pico-train - INFO - Step 40800 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:15:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9242
2025-08-31 01:15:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.32e-04
2025-08-31 01:15:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:15:55 - pico-train - INFO - Step 40900 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:15:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8794
2025-08-31 01:15:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.32e-04
2025-08-31 01:15:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:16:47 - pico-train - INFO - Step 41000 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:16:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8925
2025-08-31 01:16:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.32e-04
2025-08-31 01:16:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:17:39 - pico-train - INFO - Step 41100 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:17:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8677
2025-08-31 01:17:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.31e-04
2025-08-31 01:17:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:18:30 - pico-train - INFO - Step 41200 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:18:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8106
2025-08-31 01:18:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.31e-04
2025-08-31 01:18:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:19:23 - pico-train - INFO - Step 41300 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:19:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7647
2025-08-31 01:19:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.31e-04
2025-08-31 01:19:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:20:15 - pico-train - INFO - Step 41400 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:20:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8469
2025-08-31 01:20:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.30e-04
2025-08-31 01:20:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:21:07 - pico-train - INFO - Step 41500 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:21:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8299
2025-08-31 01:21:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.30e-04
2025-08-31 01:21:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:21:59 - pico-train - INFO - Step 41600 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:21:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7820
2025-08-31 01:21:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.30e-04
2025-08-31 01:21:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:22:51 - pico-train - INFO - Step 41700 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:22:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7469
2025-08-31 01:22:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.29e-04
2025-08-31 01:22:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:23:42 - pico-train - INFO - Step 41800 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:23:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8483
2025-08-31 01:23:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.29e-04
2025-08-31 01:23:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:24:34 - pico-train - INFO - Step 41900 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:24:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8249
2025-08-31 01:24:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.29e-04
2025-08-31 01:24:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:25:26 - pico-train - INFO - Step 42000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 01:27:14 - pico-train - INFO - Step 42000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 01:27:14 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 01:27:15 - pico-train - INFO - Step 42000 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:27:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6586
2025-08-31 01:27:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.28e-04
2025-08-31 01:27:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:27:15 - pico-train - INFO - Step 42000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 01:28:07 - pico-train - INFO - Step 42100 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:28:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.9614
2025-08-31 01:28:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.28e-04
2025-08-31 01:28:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:28:59 - pico-train - INFO - Step 42200 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:28:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4052
2025-08-31 01:28:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.28e-04
2025-08-31 01:28:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:29:50 - pico-train - INFO - Step 42300 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:29:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.1839
2025-08-31 01:29:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.28e-04
2025-08-31 01:29:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:30:42 - pico-train - INFO - Step 42400 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:30:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.2521
2025-08-31 01:30:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.27e-04
2025-08-31 01:30:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:31:35 - pico-train - INFO - Step 42500 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:31:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8687
2025-08-31 01:31:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.27e-04
2025-08-31 01:31:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:32:26 - pico-train - INFO - Step 42600 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:32:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8525
2025-08-31 01:32:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.27e-04
2025-08-31 01:32:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:33:18 - pico-train - INFO - Step 42700 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:33:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5913
2025-08-31 01:33:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.26e-04
2025-08-31 01:33:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:34:09 - pico-train - INFO - Step 42800 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:34:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.9309
2025-08-31 01:34:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.26e-04
2025-08-31 01:34:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:35:01 - pico-train - INFO - Step 42900 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:35:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.6904
2025-08-31 01:35:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.26e-04
2025-08-31 01:35:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:35:54 - pico-train - INFO - Step 43000 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:35:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.8896
2025-08-31 01:35:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.25e-04
2025-08-31 01:35:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:36:45 - pico-train - INFO - Step 43100 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:36:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.9036
2025-08-31 01:36:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.25e-04
2025-08-31 01:36:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:37:37 - pico-train - INFO - Step 43200 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:37:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.7300
2025-08-31 01:37:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.25e-04
2025-08-31 01:37:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:38:29 - pico-train - INFO - Step 43300 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:38:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.6678
2025-08-31 01:38:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.24e-04
2025-08-31 01:38:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:39:21 - pico-train - INFO - Step 43400 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:39:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 2.7509
2025-08-31 01:39:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.24e-04
2025-08-31 01:39:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:40:13 - pico-train - INFO - Step 43500 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:40:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.2958
2025-08-31 01:40:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.24e-04
2025-08-31 01:40:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:41:05 - pico-train - INFO - Step 43600 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:41:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.8729
2025-08-31 01:41:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.24e-04
2025-08-31 01:41:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:41:58 - pico-train - INFO - Step 43700 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:41:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.9046
2025-08-31 01:41:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.23e-04
2025-08-31 01:41:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:42:50 - pico-train - INFO - Step 43800 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:42:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 3.7078
2025-08-31 01:42:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.23e-04
2025-08-31 01:42:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:43:42 - pico-train - INFO - Step 43900 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:43:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.2522
2025-08-31 01:43:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.23e-04
2025-08-31 01:43:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:44:34 - pico-train - INFO - Step 44000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 01:46:22 - pico-train - INFO - Step 44000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 01:46:22 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 01:46:23 - pico-train - INFO - Step 44000 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:46:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9518
2025-08-31 01:46:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.22e-04
2025-08-31 01:46:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:46:23 - pico-train - INFO - Step 44000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 01:47:15 - pico-train - INFO - Step 44100 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:47:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9398
2025-08-31 01:47:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.22e-04
2025-08-31 01:47:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:48:07 - pico-train - INFO - Step 44200 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:48:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8995
2025-08-31 01:48:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.22e-04
2025-08-31 01:48:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:48:59 - pico-train - INFO - Step 44300 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:48:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8545
2025-08-31 01:48:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.21e-04
2025-08-31 01:48:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:49:50 - pico-train - INFO - Step 44400 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:49:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.3091
2025-08-31 01:49:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.21e-04
2025-08-31 01:49:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:50:42 - pico-train - INFO - Step 44500 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:50:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9417
2025-08-31 01:50:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.21e-04
2025-08-31 01:50:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:51:34 - pico-train - INFO - Step 44600 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:51:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8857
2025-08-31 01:51:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.20e-04
2025-08-31 01:51:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:52:25 - pico-train - INFO - Step 44700 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:52:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8884
2025-08-31 01:52:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.20e-04
2025-08-31 01:52:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:53:17 - pico-train - INFO - Step 44800 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:53:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8784
2025-08-31 01:53:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.20e-04
2025-08-31 01:53:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:54:08 - pico-train - INFO - Step 44900 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:54:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9107
2025-08-31 01:54:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.19e-04
2025-08-31 01:54:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:55:01 - pico-train - INFO - Step 45000 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:55:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9012
2025-08-31 01:55:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.19e-04
2025-08-31 01:55:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:55:53 - pico-train - INFO - Step 45100 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:55:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8593
2025-08-31 01:55:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.19e-04
2025-08-31 01:55:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:56:45 - pico-train - INFO - Step 45200 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:56:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8602
2025-08-31 01:56:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.18e-04
2025-08-31 01:56:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:57:36 - pico-train - INFO - Step 45300 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:57:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8273
2025-08-31 01:57:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.18e-04
2025-08-31 01:57:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:58:28 - pico-train - INFO - Step 45400 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:58:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7291
2025-08-31 01:58:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.18e-04
2025-08-31 01:58:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 01:59:21 - pico-train - INFO - Step 45500 -- ๐Ÿ”„ Training Metrics
2025-08-31 01:59:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8598
2025-08-31 01:59:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.18e-04
2025-08-31 01:59:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:00:12 - pico-train - INFO - Step 45600 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:00:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8709
2025-08-31 02:00:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.17e-04
2025-08-31 02:00:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:01:04 - pico-train - INFO - Step 45700 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:01:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8223
2025-08-31 02:01:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.17e-04
2025-08-31 02:01:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:01:56 - pico-train - INFO - Step 45800 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:01:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8057
2025-08-31 02:01:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.17e-04
2025-08-31 02:01:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:02:47 - pico-train - INFO - Step 45900 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:02:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8073
2025-08-31 02:02:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.16e-04
2025-08-31 02:02:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:03:39 - pico-train - INFO - Step 46000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 02:05:32 - pico-train - INFO - Step 46000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 02:05:32 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 02:05:32 - pico-train - INFO - Step 46000 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:05:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8024
2025-08-31 02:05:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.16e-04
2025-08-31 02:05:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:05:32 - pico-train - INFO - Step 46000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 02:06:25 - pico-train - INFO - Step 46100 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:06:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8004
2025-08-31 02:06:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.16e-04
2025-08-31 02:06:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:07:16 - pico-train - INFO - Step 46200 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:07:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6862
2025-08-31 02:07:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.15e-04
2025-08-31 02:07:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:08:08 - pico-train - INFO - Step 46300 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:08:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8325
2025-08-31 02:08:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.15e-04
2025-08-31 02:08:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:08:59 - pico-train - INFO - Step 46400 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:08:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8486
2025-08-31 02:08:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.15e-04
2025-08-31 02:08:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:09:51 - pico-train - INFO - Step 46500 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:09:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7909
2025-08-31 02:09:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.14e-04
2025-08-31 02:09:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:10:43 - pico-train - INFO - Step 46600 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:10:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7458
2025-08-31 02:10:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.14e-04
2025-08-31 02:10:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:11:35 - pico-train - INFO - Step 46700 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:11:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7350
2025-08-31 02:11:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.14e-04
2025-08-31 02:11:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:12:27 - pico-train - INFO - Step 46800 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:12:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8766
2025-08-31 02:12:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.13e-04
2025-08-31 02:12:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:13:18 - pico-train - INFO - Step 46900 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:13:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8978
2025-08-31 02:13:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.13e-04
2025-08-31 02:13:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:14:11 - pico-train - INFO - Step 47000 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:14:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8512
2025-08-31 02:14:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.13e-04
2025-08-31 02:14:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:15:02 - pico-train - INFO - Step 47100 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:15:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8459
2025-08-31 02:15:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.12e-04
2025-08-31 02:15:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:15:54 - pico-train - INFO - Step 47200 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:15:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8797
2025-08-31 02:15:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.12e-04
2025-08-31 02:15:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:16:46 - pico-train - INFO - Step 47300 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:16:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.9021
2025-08-31 02:16:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.12e-04
2025-08-31 02:16:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:17:38 - pico-train - INFO - Step 47400 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:17:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8815
2025-08-31 02:17:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.12e-04
2025-08-31 02:17:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:18:30 - pico-train - INFO - Step 47500 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:18:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8223
2025-08-31 02:18:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.11e-04
2025-08-31 02:18:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:19:22 - pico-train - INFO - Step 47600 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:19:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7840
2025-08-31 02:19:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.11e-04
2025-08-31 02:19:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:20:14 - pico-train - INFO - Step 47700 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:20:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7924
2025-08-31 02:20:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.11e-04
2025-08-31 02:20:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:21:07 - pico-train - INFO - Step 47800 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:21:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8607
2025-08-31 02:21:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.10e-04
2025-08-31 02:21:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:21:58 - pico-train - INFO - Step 47900 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:21:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7786
2025-08-31 02:21:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.10e-04
2025-08-31 02:21:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:22:50 - pico-train - INFO - Step 48000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 02:24:40 - pico-train - INFO - Step 48000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 02:24:40 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 02:24:40 - pico-train - INFO - Step 48000 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:24:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7870
2025-08-31 02:24:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.10e-04
2025-08-31 02:24:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:24:40 - pico-train - INFO - Step 48000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 02:25:32 - pico-train - INFO - Step 48100 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:25:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8513
2025-08-31 02:25:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.09e-04
2025-08-31 02:25:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:26:24 - pico-train - INFO - Step 48200 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:26:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8859
2025-08-31 02:26:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.09e-04
2025-08-31 02:26:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:27:17 - pico-train - INFO - Step 48300 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:27:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8814
2025-08-31 02:27:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.09e-04
2025-08-31 02:27:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:28:09 - pico-train - INFO - Step 48400 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:28:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8762
2025-08-31 02:28:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.08e-04
2025-08-31 02:28:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:29:01 - pico-train - INFO - Step 48500 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:29:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7832
2025-08-31 02:29:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.08e-04
2025-08-31 02:29:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:29:52 - pico-train - INFO - Step 48600 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:29:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8735
2025-08-31 02:29:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.08e-04
2025-08-31 02:29:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:30:44 - pico-train - INFO - Step 48700 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:30:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8643
2025-08-31 02:30:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.07e-04
2025-08-31 02:30:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:31:35 - pico-train - INFO - Step 48800 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:31:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8452
2025-08-31 02:31:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.07e-04
2025-08-31 02:31:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:32:27 - pico-train - INFO - Step 48900 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:32:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8968
2025-08-31 02:32:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.07e-04
2025-08-31 02:32:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:33:20 - pico-train - INFO - Step 49000 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:33:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8301
2025-08-31 02:33:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.06e-04
2025-08-31 02:33:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:34:12 - pico-train - INFO - Step 49100 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:34:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5497
2025-08-31 02:34:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.06e-04
2025-08-31 02:34:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:35:03 - pico-train - INFO - Step 49200 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:35:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4657
2025-08-31 02:35:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.06e-04
2025-08-31 02:35:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:35:55 - pico-train - INFO - Step 49300 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:35:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8406
2025-08-31 02:35:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.05e-04
2025-08-31 02:35:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:36:46 - pico-train - INFO - Step 49400 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:36:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7300
2025-08-31 02:36:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.05e-04
2025-08-31 02:36:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:37:39 - pico-train - INFO - Step 49500 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:37:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6906
2025-08-31 02:37:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.05e-04
2025-08-31 02:37:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:38:30 - pico-train - INFO - Step 49600 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:38:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7507
2025-08-31 02:38:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.04e-04
2025-08-31 02:38:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:39:22 - pico-train - INFO - Step 49700 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:39:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8010
2025-08-31 02:39:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.04e-04
2025-08-31 02:39:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:40:13 - pico-train - INFO - Step 49800 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:40:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7701
2025-08-31 02:40:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.04e-04
2025-08-31 02:40:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:41:05 - pico-train - INFO - Step 49900 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:41:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7618
2025-08-31 02:41:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.04e-04
2025-08-31 02:41:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:41:56 - pico-train - INFO - Step 50000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 02:43:45 - pico-train - INFO - Step 50000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 02:43:45 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 02:43:45 - pico-train - INFO - Step 50000 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:43:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7503
2025-08-31 02:43:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.03e-04
2025-08-31 02:43:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:43:45 - pico-train - INFO - Step 50000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 02:44:38 - pico-train - INFO - Step 50100 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:44:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7940
2025-08-31 02:44:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.03e-04
2025-08-31 02:44:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:45:29 - pico-train - INFO - Step 50200 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:45:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7831
2025-08-31 02:45:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.03e-04
2025-08-31 02:45:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:46:21 - pico-train - INFO - Step 50300 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:46:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7918
2025-08-31 02:46:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.02e-04
2025-08-31 02:46:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:47:13 - pico-train - INFO - Step 50400 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:47:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6934
2025-08-31 02:47:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.02e-04
2025-08-31 02:47:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:48:06 - pico-train - INFO - Step 50500 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:48:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8227
2025-08-31 02:48:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.02e-04
2025-08-31 02:48:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:48:58 - pico-train - INFO - Step 50600 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:48:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8425
2025-08-31 02:48:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.01e-04
2025-08-31 02:48:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:49:49 - pico-train - INFO - Step 50700 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:49:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8425
2025-08-31 02:49:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.01e-04
2025-08-31 02:49:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:50:41 - pico-train - INFO - Step 50800 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:50:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8135
2025-08-31 02:50:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.01e-04
2025-08-31 02:50:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:51:32 - pico-train - INFO - Step 50900 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:51:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7762
2025-08-31 02:51:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.00e-04
2025-08-31 02:51:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:52:24 - pico-train - INFO - Step 51000 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:52:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7735
2025-08-31 02:52:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 1.00e-04
2025-08-31 02:52:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:53:16 - pico-train - INFO - Step 51100 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:53:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7769
2025-08-31 02:53:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.97e-05
2025-08-31 02:53:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:54:07 - pico-train - INFO - Step 51200 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:54:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7809
2025-08-31 02:54:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.94e-05
2025-08-31 02:54:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:54:59 - pico-train - INFO - Step 51300 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:54:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8016
2025-08-31 02:54:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.90e-05
2025-08-31 02:54:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:55:51 - pico-train - INFO - Step 51400 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:55:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7868
2025-08-31 02:55:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.87e-05
2025-08-31 02:55:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:56:44 - pico-train - INFO - Step 51500 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:56:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8385
2025-08-31 02:56:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.84e-05
2025-08-31 02:56:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:57:35 - pico-train - INFO - Step 51600 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:57:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8252
2025-08-31 02:57:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.81e-05
2025-08-31 02:57:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:58:27 - pico-train - INFO - Step 51700 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:58:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8419
2025-08-31 02:58:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.78e-05
2025-08-31 02:58:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 02:59:18 - pico-train - INFO - Step 51800 -- ๐Ÿ”„ Training Metrics
2025-08-31 02:59:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7630
2025-08-31 02:59:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.74e-05
2025-08-31 02:59:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:00:10 - pico-train - INFO - Step 51900 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:00:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8294
2025-08-31 03:00:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.71e-05
2025-08-31 03:00:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:01:02 - pico-train - INFO - Step 52000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 03:02:50 - pico-train - INFO - Step 52000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 03:02:50 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 03:02:51 - pico-train - INFO - Step 52000 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:02:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8448
2025-08-31 03:02:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.68e-05
2025-08-31 03:02:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:02:51 - pico-train - INFO - Step 52000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 03:03:43 - pico-train - INFO - Step 52100 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:03:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7965
2025-08-31 03:03:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.65e-05
2025-08-31 03:03:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:04:35 - pico-train - INFO - Step 52200 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:04:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8062
2025-08-31 03:04:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.62e-05
2025-08-31 03:04:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:05:27 - pico-train - INFO - Step 52300 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:05:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7954
2025-08-31 03:05:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.58e-05
2025-08-31 03:05:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:06:19 - pico-train - INFO - Step 52400 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:06:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8452
2025-08-31 03:06:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.55e-05
2025-08-31 03:06:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:07:11 - pico-train - INFO - Step 52500 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:07:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7621
2025-08-31 03:07:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.52e-05
2025-08-31 03:07:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:08:03 - pico-train - INFO - Step 52600 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:08:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7518
2025-08-31 03:08:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.49e-05
2025-08-31 03:08:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:08:54 - pico-train - INFO - Step 52700 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:08:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7219
2025-08-31 03:08:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.46e-05
2025-08-31 03:08:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:09:46 - pico-train - INFO - Step 52800 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:09:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7477
2025-08-31 03:09:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.42e-05
2025-08-31 03:09:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:10:37 - pico-train - INFO - Step 52900 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:10:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6478
2025-08-31 03:10:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.39e-05
2025-08-31 03:10:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:11:29 - pico-train - INFO - Step 53000 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:11:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.0911
2025-08-31 03:11:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.36e-05
2025-08-31 03:11:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:12:21 - pico-train - INFO - Step 53100 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:12:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6383
2025-08-31 03:12:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.33e-05
2025-08-31 03:12:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:13:13 - pico-train - INFO - Step 53200 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:13:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7310
2025-08-31 03:13:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.30e-05
2025-08-31 03:13:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:14:04 - pico-train - INFO - Step 53300 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:14:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7118
2025-08-31 03:14:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.26e-05
2025-08-31 03:14:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:14:56 - pico-train - INFO - Step 53400 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:14:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7295
2025-08-31 03:14:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.23e-05
2025-08-31 03:14:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:15:48 - pico-train - INFO - Step 53500 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:15:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7496
2025-08-31 03:15:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.20e-05
2025-08-31 03:15:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:16:40 - pico-train - INFO - Step 53600 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:16:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8170
2025-08-31 03:16:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.17e-05
2025-08-31 03:16:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:17:31 - pico-train - INFO - Step 53700 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:17:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6796
2025-08-31 03:17:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.14e-05
2025-08-31 03:17:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:18:24 - pico-train - INFO - Step 53800 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:18:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7291
2025-08-31 03:18:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.10e-05
2025-08-31 03:18:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:19:15 - pico-train - INFO - Step 53900 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:19:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7736
2025-08-31 03:19:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.07e-05
2025-08-31 03:19:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:20:07 - pico-train - INFO - Step 54000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 03:21:55 - pico-train - INFO - Step 54000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 03:21:55 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 03:21:56 - pico-train - INFO - Step 54000 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:21:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5813
2025-08-31 03:21:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.04e-05
2025-08-31 03:21:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:21:56 - pico-train - INFO - Step 54000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 03:22:48 - pico-train - INFO - Step 54100 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:22:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8269
2025-08-31 03:22:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 9.01e-05
2025-08-31 03:22:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:23:40 - pico-train - INFO - Step 54200 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:23:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8171
2025-08-31 03:23:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.98e-05
2025-08-31 03:23:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:24:31 - pico-train - INFO - Step 54300 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:24:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7910
2025-08-31 03:24:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.94e-05
2025-08-31 03:24:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:25:23 - pico-train - INFO - Step 54400 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:25:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7473
2025-08-31 03:25:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.91e-05
2025-08-31 03:25:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:26:15 - pico-train - INFO - Step 54500 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:26:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6026
2025-08-31 03:26:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.88e-05
2025-08-31 03:26:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:27:07 - pico-train - INFO - Step 54600 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:27:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7512
2025-08-31 03:27:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.85e-05
2025-08-31 03:27:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:27:59 - pico-train - INFO - Step 54700 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:27:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8267
2025-08-31 03:27:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.82e-05
2025-08-31 03:27:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:28:50 - pico-train - INFO - Step 54800 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:28:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8168
2025-08-31 03:28:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.78e-05
2025-08-31 03:28:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:29:42 - pico-train - INFO - Step 54900 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:29:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7894
2025-08-31 03:29:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.75e-05
2025-08-31 03:29:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:30:34 - pico-train - INFO - Step 55000 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:30:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7688
2025-08-31 03:30:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.72e-05
2025-08-31 03:30:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:31:26 - pico-train - INFO - Step 55100 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:31:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7408
2025-08-31 03:31:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.69e-05
2025-08-31 03:31:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:32:17 - pico-train - INFO - Step 55200 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:32:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8037
2025-08-31 03:32:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.66e-05
2025-08-31 03:32:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:33:09 - pico-train - INFO - Step 55300 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:33:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7878
2025-08-31 03:33:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.63e-05
2025-08-31 03:33:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:34:01 - pico-train - INFO - Step 55400 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:34:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7474
2025-08-31 03:34:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.59e-05
2025-08-31 03:34:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:34:53 - pico-train - INFO - Step 55500 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:34:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7180
2025-08-31 03:34:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.56e-05
2025-08-31 03:34:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:35:45 - pico-train - INFO - Step 55600 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:35:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6669
2025-08-31 03:35:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.53e-05
2025-08-31 03:35:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:36:37 - pico-train - INFO - Step 55700 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:36:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7121
2025-08-31 03:36:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.50e-05
2025-08-31 03:36:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:37:28 - pico-train - INFO - Step 55800 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:37:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6817
2025-08-31 03:37:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.47e-05
2025-08-31 03:37:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:38:20 - pico-train - INFO - Step 55900 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:38:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6449
2025-08-31 03:38:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.44e-05
2025-08-31 03:38:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:39:12 - pico-train - INFO - Step 56000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 03:41:00 - pico-train - INFO - Step 56000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 03:41:00 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 03:41:00 - pico-train - INFO - Step 56000 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:41:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7752
2025-08-31 03:41:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.40e-05
2025-08-31 03:41:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:41:00 - pico-train - INFO - Step 56000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 03:41:52 - pico-train - INFO - Step 56100 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:41:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7332
2025-08-31 03:41:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.37e-05
2025-08-31 03:41:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:42:44 - pico-train - INFO - Step 56200 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:42:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7442
2025-08-31 03:42:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.34e-05
2025-08-31 03:42:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:43:36 - pico-train - INFO - Step 56300 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:43:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7683
2025-08-31 03:43:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.31e-05
2025-08-31 03:43:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:44:27 - pico-train - INFO - Step 56400 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:44:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7436
2025-08-31 03:44:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.28e-05
2025-08-31 03:44:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:45:20 - pico-train - INFO - Step 56500 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:45:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7703
2025-08-31 03:45:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.25e-05
2025-08-31 03:45:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:46:11 - pico-train - INFO - Step 56600 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:46:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6823
2025-08-31 03:46:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.21e-05
2025-08-31 03:46:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:47:03 - pico-train - INFO - Step 56700 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:47:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5874
2025-08-31 03:47:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.18e-05
2025-08-31 03:47:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:47:54 - pico-train - INFO - Step 56800 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:47:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6526
2025-08-31 03:47:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.15e-05
2025-08-31 03:47:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:48:46 - pico-train - INFO - Step 56900 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:48:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7713
2025-08-31 03:48:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.12e-05
2025-08-31 03:48:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:49:38 - pico-train - INFO - Step 57000 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:49:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7954
2025-08-31 03:49:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.09e-05
2025-08-31 03:49:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:50:30 - pico-train - INFO - Step 57100 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:50:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7338
2025-08-31 03:50:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.06e-05
2025-08-31 03:50:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:51:21 - pico-train - INFO - Step 57200 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:51:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5513
2025-08-31 03:51:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 8.03e-05
2025-08-31 03:51:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:52:13 - pico-train - INFO - Step 57300 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:52:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6619
2025-08-31 03:52:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.99e-05
2025-08-31 03:52:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:53:05 - pico-train - INFO - Step 57400 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:53:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7497
2025-08-31 03:53:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.96e-05
2025-08-31 03:53:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:53:57 - pico-train - INFO - Step 57500 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:53:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7734
2025-08-31 03:53:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.93e-05
2025-08-31 03:53:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:54:49 - pico-train - INFO - Step 57600 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:54:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7634
2025-08-31 03:54:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.90e-05
2025-08-31 03:54:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:55:40 - pico-train - INFO - Step 57700 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:55:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7525
2025-08-31 03:55:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.87e-05
2025-08-31 03:55:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:56:32 - pico-train - INFO - Step 57800 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:56:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7636
2025-08-31 03:56:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.84e-05
2025-08-31 03:56:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:57:23 - pico-train - INFO - Step 57900 -- ๐Ÿ”„ Training Metrics
2025-08-31 03:57:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7354
2025-08-31 03:57:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.81e-05
2025-08-31 03:57:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 03:58:15 - pico-train - INFO - Step 58000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 04:00:04 - pico-train - INFO - Step 58000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 04:00:04 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 04:00:05 - pico-train - INFO - Step 58000 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:00:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6258
2025-08-31 04:00:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.77e-05
2025-08-31 04:00:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:00:05 - pico-train - INFO - Step 58000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 04:00:57 - pico-train - INFO - Step 58100 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:00:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6990
2025-08-31 04:00:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.74e-05
2025-08-31 04:00:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:01:49 - pico-train - INFO - Step 58200 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:01:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6225
2025-08-31 04:01:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.71e-05
2025-08-31 04:01:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:02:41 - pico-train - INFO - Step 58300 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:02:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7347
2025-08-31 04:02:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.68e-05
2025-08-31 04:02:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:03:33 - pico-train - INFO - Step 58400 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:03:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7528
2025-08-31 04:03:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.65e-05
2025-08-31 04:03:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:04:25 - pico-train - INFO - Step 58500 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:04:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7280
2025-08-31 04:04:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.62e-05
2025-08-31 04:04:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:05:17 - pico-train - INFO - Step 58600 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:05:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7135
2025-08-31 04:05:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.59e-05
2025-08-31 04:05:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:06:09 - pico-train - INFO - Step 58700 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:06:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8126
2025-08-31 04:06:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.56e-05
2025-08-31 04:06:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:07:00 - pico-train - INFO - Step 58800 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:07:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7505
2025-08-31 04:07:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.53e-05
2025-08-31 04:07:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:07:52 - pico-train - INFO - Step 58900 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:07:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7376
2025-08-31 04:07:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.49e-05
2025-08-31 04:07:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:08:44 - pico-train - INFO - Step 59000 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:08:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8413
2025-08-31 04:08:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.46e-05
2025-08-31 04:08:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:09:36 - pico-train - INFO - Step 59100 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:09:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7368
2025-08-31 04:09:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.43e-05
2025-08-31 04:09:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:10:28 - pico-train - INFO - Step 59200 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:10:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7792
2025-08-31 04:10:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.40e-05
2025-08-31 04:10:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:11:19 - pico-train - INFO - Step 59300 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:11:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7737
2025-08-31 04:11:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.37e-05
2025-08-31 04:11:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:12:11 - pico-train - INFO - Step 59400 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:12:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5704
2025-08-31 04:12:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.34e-05
2025-08-31 04:12:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:13:03 - pico-train - INFO - Step 59500 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:13:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7184
2025-08-31 04:13:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.31e-05
2025-08-31 04:13:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:13:54 - pico-train - INFO - Step 59600 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:13:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8264
2025-08-31 04:13:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.28e-05
2025-08-31 04:13:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:14:46 - pico-train - INFO - Step 59700 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:14:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7104
2025-08-31 04:14:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.25e-05
2025-08-31 04:14:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:15:38 - pico-train - INFO - Step 59800 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:15:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7607
2025-08-31 04:15:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.22e-05
2025-08-31 04:15:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:16:30 - pico-train - INFO - Step 59900 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:16:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6433
2025-08-31 04:16:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.19e-05
2025-08-31 04:16:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:17:22 - pico-train - INFO - Step 60000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 04:19:11 - pico-train - INFO - Step 60000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 04:19:11 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 04:19:11 - pico-train - INFO - Step 60000 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:19:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7643
2025-08-31 04:19:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.15e-05
2025-08-31 04:19:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:19:11 - pico-train - INFO - Step 60000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 04:20:04 - pico-train - INFO - Step 60100 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:20:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7230
2025-08-31 04:20:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.12e-05
2025-08-31 04:20:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:20:55 - pico-train - INFO - Step 60200 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:20:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7552
2025-08-31 04:20:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.09e-05
2025-08-31 04:20:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:21:47 - pico-train - INFO - Step 60300 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:21:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7716
2025-08-31 04:21:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.06e-05
2025-08-31 04:21:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:22:38 - pico-train - INFO - Step 60400 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:22:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8298
2025-08-31 04:22:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.03e-05
2025-08-31 04:22:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:23:31 - pico-train - INFO - Step 60500 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:23:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7631
2025-08-31 04:23:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 7.00e-05
2025-08-31 04:23:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:24:22 - pico-train - INFO - Step 60600 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:24:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7056
2025-08-31 04:24:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.97e-05
2025-08-31 04:24:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:25:14 - pico-train - INFO - Step 60700 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:25:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7684
2025-08-31 04:25:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.94e-05
2025-08-31 04:25:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:26:06 - pico-train - INFO - Step 60800 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:26:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7622
2025-08-31 04:26:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.91e-05
2025-08-31 04:26:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:26:57 - pico-train - INFO - Step 60900 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:26:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6733
2025-08-31 04:26:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.88e-05
2025-08-31 04:26:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:27:49 - pico-train - INFO - Step 61000 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:27:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7075
2025-08-31 04:27:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.85e-05
2025-08-31 04:27:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:28:41 - pico-train - INFO - Step 61100 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:28:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6605
2025-08-31 04:28:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.82e-05
2025-08-31 04:28:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:29:32 - pico-train - INFO - Step 61200 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:29:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7365
2025-08-31 04:29:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.79e-05
2025-08-31 04:29:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:30:24 - pico-train - INFO - Step 61300 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:30:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6952
2025-08-31 04:30:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.76e-05
2025-08-31 04:30:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:31:15 - pico-train - INFO - Step 61400 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:31:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7439
2025-08-31 04:31:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.73e-05
2025-08-31 04:31:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:32:07 - pico-train - INFO - Step 61500 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:32:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7678
2025-08-31 04:32:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.70e-05
2025-08-31 04:32:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:32:59 - pico-train - INFO - Step 61600 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:32:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7163
2025-08-31 04:32:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.67e-05
2025-08-31 04:32:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:33:50 - pico-train - INFO - Step 61700 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:33:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7610
2025-08-31 04:33:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.64e-05
2025-08-31 04:33:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:34:42 - pico-train - INFO - Step 61800 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:34:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7427
2025-08-31 04:34:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.61e-05
2025-08-31 04:34:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:35:34 - pico-train - INFO - Step 61900 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:35:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7452
2025-08-31 04:35:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.58e-05
2025-08-31 04:35:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:36:26 - pico-train - INFO - Step 62000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 04:38:14 - pico-train - INFO - Step 62000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 04:38:14 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 04:38:15 - pico-train - INFO - Step 62000 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:38:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7605
2025-08-31 04:38:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.55e-05
2025-08-31 04:38:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:38:15 - pico-train - INFO - Step 62000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 04:39:07 - pico-train - INFO - Step 62100 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:39:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7000
2025-08-31 04:39:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.52e-05
2025-08-31 04:39:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:39:59 - pico-train - INFO - Step 62200 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:39:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7021
2025-08-31 04:39:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.49e-05
2025-08-31 04:39:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:40:50 - pico-train - INFO - Step 62300 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:40:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7187
2025-08-31 04:40:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.46e-05
2025-08-31 04:40:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:41:42 - pico-train - INFO - Step 62400 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:41:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7618
2025-08-31 04:41:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.43e-05
2025-08-31 04:41:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:42:34 - pico-train - INFO - Step 62500 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:42:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6404
2025-08-31 04:42:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.40e-05
2025-08-31 04:42:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:43:26 - pico-train - INFO - Step 62600 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:43:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5798
2025-08-31 04:43:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.37e-05
2025-08-31 04:43:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:44:18 - pico-train - INFO - Step 62700 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:44:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6632
2025-08-31 04:44:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.34e-05
2025-08-31 04:44:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:45:09 - pico-train - INFO - Step 62800 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:45:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5843
2025-08-31 04:45:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.31e-05
2025-08-31 04:45:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:46:01 - pico-train - INFO - Step 62900 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:46:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6597
2025-08-31 04:46:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.28e-05
2025-08-31 04:46:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:46:53 - pico-train - INFO - Step 63000 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:46:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6418
2025-08-31 04:46:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.25e-05
2025-08-31 04:46:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:47:45 - pico-train - INFO - Step 63100 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:47:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7716
2025-08-31 04:47:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.22e-05
2025-08-31 04:47:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:48:37 - pico-train - INFO - Step 63200 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:48:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7586
2025-08-31 04:48:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.19e-05
2025-08-31 04:48:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:49:28 - pico-train - INFO - Step 63300 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:49:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6901
2025-08-31 04:49:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.16e-05
2025-08-31 04:49:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:50:20 - pico-train - INFO - Step 63400 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:50:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6636
2025-08-31 04:50:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.13e-05
2025-08-31 04:50:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:51:12 - pico-train - INFO - Step 63500 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:51:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6091
2025-08-31 04:51:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.10e-05
2025-08-31 04:51:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:52:03 - pico-train - INFO - Step 63600 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:52:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6391
2025-08-31 04:52:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.07e-05
2025-08-31 04:52:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:52:55 - pico-train - INFO - Step 63700 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:52:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6842
2025-08-31 04:52:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.04e-05
2025-08-31 04:52:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:53:47 - pico-train - INFO - Step 63800 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:53:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7425
2025-08-31 04:53:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 6.01e-05
2025-08-31 04:53:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:54:38 - pico-train - INFO - Step 63900 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:54:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6382
2025-08-31 04:54:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.98e-05
2025-08-31 04:54:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:55:30 - pico-train - INFO - Step 64000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 04:57:17 - pico-train - INFO - Step 64000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 04:57:17 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 04:57:18 - pico-train - INFO - Step 64000 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:57:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7247
2025-08-31 04:57:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.95e-05
2025-08-31 04:57:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:57:18 - pico-train - INFO - Step 64000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 04:58:10 - pico-train - INFO - Step 64100 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:58:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7745
2025-08-31 04:58:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.92e-05
2025-08-31 04:58:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:59:01 - pico-train - INFO - Step 64200 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:59:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7469
2025-08-31 04:59:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.89e-05
2025-08-31 04:59:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 04:59:53 - pico-train - INFO - Step 64300 -- ๐Ÿ”„ Training Metrics
2025-08-31 04:59:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7574
2025-08-31 04:59:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.86e-05
2025-08-31 04:59:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:00:44 - pico-train - INFO - Step 64400 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:00:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7948
2025-08-31 05:00:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.84e-05
2025-08-31 05:00:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:01:37 - pico-train - INFO - Step 64500 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:01:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7107
2025-08-31 05:01:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.81e-05
2025-08-31 05:01:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:02:29 - pico-train - INFO - Step 64600 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:02:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7752
2025-08-31 05:02:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.78e-05
2025-08-31 05:02:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:03:21 - pico-train - INFO - Step 64700 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:03:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6828
2025-08-31 05:03:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.75e-05
2025-08-31 05:03:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:04:12 - pico-train - INFO - Step 64800 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:04:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7338
2025-08-31 05:04:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.72e-05
2025-08-31 05:04:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:05:04 - pico-train - INFO - Step 64900 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:05:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6559
2025-08-31 05:05:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.69e-05
2025-08-31 05:05:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:05:56 - pico-train - INFO - Step 65000 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:05:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5495
2025-08-31 05:05:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.66e-05
2025-08-31 05:05:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:06:48 - pico-train - INFO - Step 65100 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:06:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6956
2025-08-31 05:06:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.63e-05
2025-08-31 05:06:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:07:39 - pico-train - INFO - Step 65200 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:07:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7201
2025-08-31 05:07:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.60e-05
2025-08-31 05:07:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:08:31 - pico-train - INFO - Step 65300 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:08:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7585
2025-08-31 05:08:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.57e-05
2025-08-31 05:08:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:09:22 - pico-train - INFO - Step 65400 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:09:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7034
2025-08-31 05:09:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.55e-05
2025-08-31 05:09:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:10:14 - pico-train - INFO - Step 65500 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:10:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6977
2025-08-31 05:10:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.52e-05
2025-08-31 05:10:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:11:06 - pico-train - INFO - Step 65600 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:11:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7311
2025-08-31 05:11:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.49e-05
2025-08-31 05:11:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:11:57 - pico-train - INFO - Step 65700 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:11:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7227
2025-08-31 05:11:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.46e-05
2025-08-31 05:11:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:12:49 - pico-train - INFO - Step 65800 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:12:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7637
2025-08-31 05:12:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.43e-05
2025-08-31 05:12:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:13:40 - pico-train - INFO - Step 65900 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:13:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6328
2025-08-31 05:13:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.40e-05
2025-08-31 05:13:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:14:32 - pico-train - INFO - Step 66000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 05:16:20 - pico-train - INFO - Step 66000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 05:16:20 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 05:16:20 - pico-train - INFO - Step 66000 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:16:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6922
2025-08-31 05:16:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.37e-05
2025-08-31 05:16:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:16:20 - pico-train - INFO - Step 66000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 05:17:13 - pico-train - INFO - Step 66100 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:17:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6547
2025-08-31 05:17:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.35e-05
2025-08-31 05:17:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:18:04 - pico-train - INFO - Step 66200 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:18:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6359
2025-08-31 05:18:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.32e-05
2025-08-31 05:18:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:18:56 - pico-train - INFO - Step 66300 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:18:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7213
2025-08-31 05:18:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.29e-05
2025-08-31 05:18:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:19:47 - pico-train - INFO - Step 66400 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:19:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7410
2025-08-31 05:19:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.26e-05
2025-08-31 05:19:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:20:40 - pico-train - INFO - Step 66500 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:20:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6971
2025-08-31 05:20:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.23e-05
2025-08-31 05:20:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:21:31 - pico-train - INFO - Step 66600 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:21:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6825
2025-08-31 05:21:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.20e-05
2025-08-31 05:21:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:22:23 - pico-train - INFO - Step 66700 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:22:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7025
2025-08-31 05:22:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.18e-05
2025-08-31 05:22:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:23:14 - pico-train - INFO - Step 66800 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:23:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6376
2025-08-31 05:23:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.15e-05
2025-08-31 05:23:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:24:06 - pico-train - INFO - Step 66900 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:24:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6858
2025-08-31 05:24:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.12e-05
2025-08-31 05:24:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:24:58 - pico-train - INFO - Step 67000 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:24:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6740
2025-08-31 05:24:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.09e-05
2025-08-31 05:24:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:25:49 - pico-train - INFO - Step 67100 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:25:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6885
2025-08-31 05:25:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.06e-05
2025-08-31 05:25:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:26:41 - pico-train - INFO - Step 67200 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:26:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6838
2025-08-31 05:26:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.04e-05
2025-08-31 05:26:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:27:33 - pico-train - INFO - Step 67300 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:27:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7456
2025-08-31 05:27:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 5.01e-05
2025-08-31 05:27:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:28:25 - pico-train - INFO - Step 67400 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:28:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6889
2025-08-31 05:28:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.98e-05
2025-08-31 05:28:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:29:17 - pico-train - INFO - Step 67500 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:29:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6822
2025-08-31 05:29:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.95e-05
2025-08-31 05:29:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:30:08 - pico-train - INFO - Step 67600 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:30:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7133
2025-08-31 05:30:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.93e-05
2025-08-31 05:30:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:31:00 - pico-train - INFO - Step 67700 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:31:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6865
2025-08-31 05:31:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.90e-05
2025-08-31 05:31:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:31:51 - pico-train - INFO - Step 67800 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:31:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6382
2025-08-31 05:31:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.87e-05
2025-08-31 05:31:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:32:43 - pico-train - INFO - Step 67900 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:32:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6698
2025-08-31 05:32:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.84e-05
2025-08-31 05:32:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:33:34 - pico-train - INFO - Step 68000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 05:35:23 - pico-train - INFO - Step 68000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 05:35:23 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 05:35:23 - pico-train - INFO - Step 68000 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:35:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6390
2025-08-31 05:35:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.82e-05
2025-08-31 05:35:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:35:23 - pico-train - INFO - Step 68000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 05:36:16 - pico-train - INFO - Step 68100 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:36:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7282
2025-08-31 05:36:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.79e-05
2025-08-31 05:36:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:37:08 - pico-train - INFO - Step 68200 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:37:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6266
2025-08-31 05:37:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.76e-05
2025-08-31 05:37:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:37:59 - pico-train - INFO - Step 68300 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:37:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6421
2025-08-31 05:37:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.73e-05
2025-08-31 05:37:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:38:51 - pico-train - INFO - Step 68400 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:38:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6914
2025-08-31 05:38:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.71e-05
2025-08-31 05:38:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:39:43 - pico-train - INFO - Step 68500 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:39:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6940
2025-08-31 05:39:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.68e-05
2025-08-31 05:39:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:40:35 - pico-train - INFO - Step 68600 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:40:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7047
2025-08-31 05:40:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.65e-05
2025-08-31 05:40:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:41:26 - pico-train - INFO - Step 68700 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:41:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6693
2025-08-31 05:41:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.63e-05
2025-08-31 05:41:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:42:17 - pico-train - INFO - Step 68800 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:42:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4842
2025-08-31 05:42:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.60e-05
2025-08-31 05:42:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:43:09 - pico-train - INFO - Step 68900 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:43:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6504
2025-08-31 05:43:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.57e-05
2025-08-31 05:43:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:44:01 - pico-train - INFO - Step 69000 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:44:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6144
2025-08-31 05:44:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.54e-05
2025-08-31 05:44:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:44:53 - pico-train - INFO - Step 69100 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:44:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7140
2025-08-31 05:44:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.52e-05
2025-08-31 05:44:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:45:45 - pico-train - INFO - Step 69200 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:45:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6957
2025-08-31 05:45:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.49e-05
2025-08-31 05:45:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:46:37 - pico-train - INFO - Step 69300 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:46:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7104
2025-08-31 05:46:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.46e-05
2025-08-31 05:46:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:47:28 - pico-train - INFO - Step 69400 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:47:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6734
2025-08-31 05:47:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.44e-05
2025-08-31 05:47:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:48:21 - pico-train - INFO - Step 69500 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:48:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6432
2025-08-31 05:48:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.41e-05
2025-08-31 05:48:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:49:13 - pico-train - INFO - Step 69600 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:49:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6413
2025-08-31 05:49:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.38e-05
2025-08-31 05:49:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:50:04 - pico-train - INFO - Step 69700 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:50:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.3247
2025-08-31 05:50:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.36e-05
2025-08-31 05:50:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:50:56 - pico-train - INFO - Step 69800 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:50:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6143
2025-08-31 05:50:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.33e-05
2025-08-31 05:50:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:51:47 - pico-train - INFO - Step 69900 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:51:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6423
2025-08-31 05:51:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.31e-05
2025-08-31 05:51:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:52:39 - pico-train - INFO - Step 70000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 05:54:28 - pico-train - INFO - Step 70000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 05:54:28 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 05:54:29 - pico-train - INFO - Step 70000 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:54:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5899
2025-08-31 05:54:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.28e-05
2025-08-31 05:54:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:54:29 - pico-train - INFO - Step 70000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 05:55:21 - pico-train - INFO - Step 70100 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:55:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6870
2025-08-31 05:55:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.25e-05
2025-08-31 05:55:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:56:12 - pico-train - INFO - Step 70200 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:56:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7299
2025-08-31 05:56:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.23e-05
2025-08-31 05:56:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:57:04 - pico-train - INFO - Step 70300 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:57:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5664
2025-08-31 05:57:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.20e-05
2025-08-31 05:57:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:57:56 - pico-train - INFO - Step 70400 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:57:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5943
2025-08-31 05:57:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.17e-05
2025-08-31 05:57:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:58:48 - pico-train - INFO - Step 70500 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:58:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6737
2025-08-31 05:58:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.15e-05
2025-08-31 05:58:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 05:59:40 - pico-train - INFO - Step 70600 -- ๐Ÿ”„ Training Metrics
2025-08-31 05:59:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6301
2025-08-31 05:59:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.12e-05
2025-08-31 05:59:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:00:31 - pico-train - INFO - Step 70700 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:00:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6488
2025-08-31 06:00:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.10e-05
2025-08-31 06:00:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:01:23 - pico-train - INFO - Step 70800 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:01:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6588
2025-08-31 06:01:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.07e-05
2025-08-31 06:01:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:02:14 - pico-train - INFO - Step 70900 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:02:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6257
2025-08-31 06:02:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.04e-05
2025-08-31 06:02:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:03:06 - pico-train - INFO - Step 71000 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:03:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6493
2025-08-31 06:03:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 4.02e-05
2025-08-31 06:03:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:03:58 - pico-train - INFO - Step 71100 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:03:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6038
2025-08-31 06:03:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.99e-05
2025-08-31 06:03:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:04:50 - pico-train - INFO - Step 71200 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:04:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6615
2025-08-31 06:04:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.97e-05
2025-08-31 06:04:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:05:41 - pico-train - INFO - Step 71300 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:05:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7068
2025-08-31 06:05:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.94e-05
2025-08-31 06:05:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:06:32 - pico-train - INFO - Step 71400 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:06:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6622
2025-08-31 06:06:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.92e-05
2025-08-31 06:06:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:07:25 - pico-train - INFO - Step 71500 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:07:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7188
2025-08-31 06:07:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.89e-05
2025-08-31 06:07:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:08:16 - pico-train - INFO - Step 71600 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:08:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6602
2025-08-31 06:08:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.87e-05
2025-08-31 06:08:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:09:08 - pico-train - INFO - Step 71700 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:09:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6068
2025-08-31 06:09:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.84e-05
2025-08-31 06:09:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:09:59 - pico-train - INFO - Step 71800 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:09:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7080
2025-08-31 06:09:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.82e-05
2025-08-31 06:09:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:10:51 - pico-train - INFO - Step 71900 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:10:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6023
2025-08-31 06:10:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.79e-05
2025-08-31 06:10:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:11:42 - pico-train - INFO - Step 72000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 06:13:30 - pico-train - INFO - Step 72000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 06:13:30 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 06:13:31 - pico-train - INFO - Step 72000 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:13:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5242
2025-08-31 06:13:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.77e-05
2025-08-31 06:13:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:13:31 - pico-train - INFO - Step 72000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 06:14:23 - pico-train - INFO - Step 72100 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:14:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5232
2025-08-31 06:14:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.74e-05
2025-08-31 06:14:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:15:15 - pico-train - INFO - Step 72200 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:15:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.3945
2025-08-31 06:15:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.72e-05
2025-08-31 06:15:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:16:06 - pico-train - INFO - Step 72300 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:16:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5338
2025-08-31 06:16:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.69e-05
2025-08-31 06:16:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:16:58 - pico-train - INFO - Step 72400 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:16:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4615
2025-08-31 06:16:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.67e-05
2025-08-31 06:16:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:17:51 - pico-train - INFO - Step 72500 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:17:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6405
2025-08-31 06:17:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.64e-05
2025-08-31 06:17:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:18:42 - pico-train - INFO - Step 72600 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:18:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5952
2025-08-31 06:18:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.62e-05
2025-08-31 06:18:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:19:34 - pico-train - INFO - Step 72700 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:19:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4701
2025-08-31 06:19:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.59e-05
2025-08-31 06:19:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:20:25 - pico-train - INFO - Step 72800 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:20:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5874
2025-08-31 06:20:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.57e-05
2025-08-31 06:20:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:21:17 - pico-train - INFO - Step 72900 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:21:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5509
2025-08-31 06:21:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.54e-05
2025-08-31 06:21:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:22:09 - pico-train - INFO - Step 73000 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:22:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5398
2025-08-31 06:22:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.52e-05
2025-08-31 06:22:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:23:00 - pico-train - INFO - Step 73100 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:23:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.3339
2025-08-31 06:23:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.49e-05
2025-08-31 06:23:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:23:52 - pico-train - INFO - Step 73200 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:23:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.3875
2025-08-31 06:23:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.47e-05
2025-08-31 06:23:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:24:43 - pico-train - INFO - Step 73300 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:24:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5318
2025-08-31 06:24:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.44e-05
2025-08-31 06:24:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:25:34 - pico-train - INFO - Step 73400 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:25:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5182
2025-08-31 06:25:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.42e-05
2025-08-31 06:25:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:26:27 - pico-train - INFO - Step 73500 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:26:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5567
2025-08-31 06:26:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.40e-05
2025-08-31 06:26:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:27:19 - pico-train - INFO - Step 73600 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:27:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4407
2025-08-31 06:27:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.37e-05
2025-08-31 06:27:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:28:11 - pico-train - INFO - Step 73700 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:28:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5335
2025-08-31 06:28:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.35e-05
2025-08-31 06:28:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:29:03 - pico-train - INFO - Step 73800 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:29:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6355
2025-08-31 06:29:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.32e-05
2025-08-31 06:29:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:29:54 - pico-train - INFO - Step 73900 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:29:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6095
2025-08-31 06:29:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.30e-05
2025-08-31 06:29:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:30:46 - pico-train - INFO - Step 74000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 06:32:33 - pico-train - INFO - Step 74000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 06:32:33 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 06:32:34 - pico-train - INFO - Step 74000 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:32:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5579
2025-08-31 06:32:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.28e-05
2025-08-31 06:32:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:32:34 - pico-train - INFO - Step 74000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 06:33:26 - pico-train - INFO - Step 74100 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:33:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5207
2025-08-31 06:33:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.25e-05
2025-08-31 06:33:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:34:17 - pico-train - INFO - Step 74200 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:34:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6675
2025-08-31 06:34:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.23e-05
2025-08-31 06:34:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:35:09 - pico-train - INFO - Step 74300 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:35:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.4126
2025-08-31 06:35:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.21e-05
2025-08-31 06:35:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:36:01 - pico-train - INFO - Step 74400 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:36:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7039
2025-08-31 06:36:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.18e-05
2025-08-31 06:36:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:36:53 - pico-train - INFO - Step 74500 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:36:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6828
2025-08-31 06:36:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.16e-05
2025-08-31 06:36:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:37:45 - pico-train - INFO - Step 74600 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:37:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7129
2025-08-31 06:37:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.14e-05
2025-08-31 06:37:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:38:36 - pico-train - INFO - Step 74700 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:38:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5640
2025-08-31 06:38:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.11e-05
2025-08-31 06:38:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:39:28 - pico-train - INFO - Step 74800 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:39:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6214
2025-08-31 06:39:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.09e-05
2025-08-31 06:39:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:40:20 - pico-train - INFO - Step 74900 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:40:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6219
2025-08-31 06:40:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.07e-05
2025-08-31 06:40:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:41:12 - pico-train - INFO - Step 75000 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:41:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6650
2025-08-31 06:41:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.04e-05
2025-08-31 06:41:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:42:03 - pico-train - INFO - Step 75100 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:42:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6657
2025-08-31 06:42:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.02e-05
2025-08-31 06:42:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:42:54 - pico-train - INFO - Step 75200 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:42:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6446
2025-08-31 06:42:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 3.00e-05
2025-08-31 06:42:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:43:46 - pico-train - INFO - Step 75300 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:43:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6650
2025-08-31 06:43:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.97e-05
2025-08-31 06:43:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:44:38 - pico-train - INFO - Step 75400 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:44:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7400
2025-08-31 06:44:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.95e-05
2025-08-31 06:44:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:45:30 - pico-train - INFO - Step 75500 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:45:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7032
2025-08-31 06:45:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.93e-05
2025-08-31 06:45:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:46:21 - pico-train - INFO - Step 75600 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:46:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7058
2025-08-31 06:46:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.91e-05
2025-08-31 06:46:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:47:13 - pico-train - INFO - Step 75700 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:47:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6217
2025-08-31 06:47:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.88e-05
2025-08-31 06:47:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:48:04 - pico-train - INFO - Step 75800 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:48:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.3060
2025-08-31 06:48:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.86e-05
2025-08-31 06:48:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:48:56 - pico-train - INFO - Step 75900 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:48:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6372
2025-08-31 06:48:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.84e-05
2025-08-31 06:48:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:49:47 - pico-train - INFO - Step 76000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 06:51:36 - pico-train - INFO - Step 76000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 06:51:36 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 06:51:36 - pico-train - INFO - Step 76000 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:51:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7263
2025-08-31 06:51:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.82e-05
2025-08-31 06:51:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:51:36 - pico-train - INFO - Step 76000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 06:52:29 - pico-train - INFO - Step 76100 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:52:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5898
2025-08-31 06:52:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.79e-05
2025-08-31 06:52:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:53:20 - pico-train - INFO - Step 76200 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:53:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5457
2025-08-31 06:53:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.77e-05
2025-08-31 06:53:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:54:12 - pico-train - INFO - Step 76300 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:54:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6344
2025-08-31 06:54:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.75e-05
2025-08-31 06:54:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:55:03 - pico-train - INFO - Step 76400 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:55:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7356
2025-08-31 06:55:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.73e-05
2025-08-31 06:55:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:55:55 - pico-train - INFO - Step 76500 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:55:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6593
2025-08-31 06:55:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.71e-05
2025-08-31 06:55:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:56:47 - pico-train - INFO - Step 76600 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:56:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7932
2025-08-31 06:56:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.68e-05
2025-08-31 06:56:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:57:38 - pico-train - INFO - Step 76700 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:57:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7641
2025-08-31 06:57:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.66e-05
2025-08-31 06:57:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:58:30 - pico-train - INFO - Step 76800 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:58:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7706
2025-08-31 06:58:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.64e-05
2025-08-31 06:58:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 06:59:21 - pico-train - INFO - Step 76900 -- ๐Ÿ”„ Training Metrics
2025-08-31 06:59:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7679
2025-08-31 06:59:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.62e-05
2025-08-31 06:59:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:00:14 - pico-train - INFO - Step 77000 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:00:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7579
2025-08-31 07:00:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.60e-05
2025-08-31 07:00:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:01:05 - pico-train - INFO - Step 77100 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:01:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7721
2025-08-31 07:01:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.58e-05
2025-08-31 07:01:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:01:57 - pico-train - INFO - Step 77200 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:01:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7586
2025-08-31 07:01:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.55e-05
2025-08-31 07:01:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:02:48 - pico-train - INFO - Step 77300 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:02:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7567
2025-08-31 07:02:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.53e-05
2025-08-31 07:02:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:03:40 - pico-train - INFO - Step 77400 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:03:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7464
2025-08-31 07:03:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.51e-05
2025-08-31 07:03:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:04:32 - pico-train - INFO - Step 77500 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:04:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7402
2025-08-31 07:04:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.49e-05
2025-08-31 07:04:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:05:23 - pico-train - INFO - Step 77600 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:05:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8047
2025-08-31 07:05:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.47e-05
2025-08-31 07:05:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:06:15 - pico-train - INFO - Step 77700 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:06:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8035
2025-08-31 07:06:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.45e-05
2025-08-31 07:06:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:07:06 - pico-train - INFO - Step 77800 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:07:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7325
2025-08-31 07:07:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.43e-05
2025-08-31 07:07:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:07:58 - pico-train - INFO - Step 77900 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:07:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6718
2025-08-31 07:07:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.41e-05
2025-08-31 07:07:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:08:51 - pico-train - INFO - Step 78000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 07:10:39 - pico-train - INFO - Step 78000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 07:10:39 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 07:10:39 - pico-train - INFO - Step 78000 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:10:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7240
2025-08-31 07:10:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.39e-05
2025-08-31 07:10:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:10:39 - pico-train - INFO - Step 78000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 07:11:31 - pico-train - INFO - Step 78100 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:11:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7809
2025-08-31 07:11:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.36e-05
2025-08-31 07:11:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:12:23 - pico-train - INFO - Step 78200 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:12:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7888
2025-08-31 07:12:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.34e-05
2025-08-31 07:12:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:13:15 - pico-train - INFO - Step 78300 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:13:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7886
2025-08-31 07:13:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.32e-05
2025-08-31 07:13:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:14:07 - pico-train - INFO - Step 78400 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:14:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8433
2025-08-31 07:14:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.30e-05
2025-08-31 07:14:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:14:59 - pico-train - INFO - Step 78500 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:14:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7275
2025-08-31 07:14:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.28e-05
2025-08-31 07:14:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:15:51 - pico-train - INFO - Step 78600 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:15:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7189
2025-08-31 07:15:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.26e-05
2025-08-31 07:15:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:16:43 - pico-train - INFO - Step 78700 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:16:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7776
2025-08-31 07:16:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.24e-05
2025-08-31 07:16:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:17:35 - pico-train - INFO - Step 78800 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:17:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7769
2025-08-31 07:17:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.22e-05
2025-08-31 07:17:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:18:27 - pico-train - INFO - Step 78900 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:18:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7239
2025-08-31 07:18:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.20e-05
2025-08-31 07:18:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:19:19 - pico-train - INFO - Step 79000 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:19:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7447
2025-08-31 07:19:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.18e-05
2025-08-31 07:19:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:20:11 - pico-train - INFO - Step 79100 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:20:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7424
2025-08-31 07:20:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.16e-05
2025-08-31 07:20:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:21:02 - pico-train - INFO - Step 79200 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:21:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7622
2025-08-31 07:21:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.14e-05
2025-08-31 07:21:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:21:54 - pico-train - INFO - Step 79300 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:21:54 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7830
2025-08-31 07:21:54 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.12e-05
2025-08-31 07:21:54 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:22:46 - pico-train - INFO - Step 79400 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:22:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7487
2025-08-31 07:22:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.10e-05
2025-08-31 07:22:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:23:38 - pico-train - INFO - Step 79500 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:23:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7489
2025-08-31 07:23:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.08e-05
2025-08-31 07:23:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:24:30 - pico-train - INFO - Step 79600 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:24:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7076
2025-08-31 07:24:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.06e-05
2025-08-31 07:24:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:25:21 - pico-train - INFO - Step 79700 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:25:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7456
2025-08-31 07:25:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.04e-05
2025-08-31 07:25:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:26:14 - pico-train - INFO - Step 79800 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:26:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7621
2025-08-31 07:26:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.02e-05
2025-08-31 07:26:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:27:05 - pico-train - INFO - Step 79900 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:27:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8204
2025-08-31 07:27:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.01e-05
2025-08-31 07:27:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:27:57 - pico-train - INFO - Step 80000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 07:29:44 - pico-train - INFO - Step 80000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 07:29:44 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 07:29:45 - pico-train - INFO - Step 80000 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:29:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.8223
2025-08-31 07:29:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:29:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:29:45 - pico-train - INFO - Step 80000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 07:30:37 - pico-train - INFO - Step 80100 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:30:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7804
2025-08-31 07:30:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:30:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:31:29 - pico-train - INFO - Step 80200 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:31:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7785
2025-08-31 07:31:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:31:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:32:20 - pico-train - INFO - Step 80300 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:32:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7587
2025-08-31 07:32:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:32:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:33:12 - pico-train - INFO - Step 80400 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:33:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7610
2025-08-31 07:33:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:33:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:34:04 - pico-train - INFO - Step 80500 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:34:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7088
2025-08-31 07:34:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:34:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:34:56 - pico-train - INFO - Step 80600 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:34:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7338
2025-08-31 07:34:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:34:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:35:47 - pico-train - INFO - Step 80700 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:35:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7664
2025-08-31 07:35:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:35:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:36:39 - pico-train - INFO - Step 80800 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:36:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.2818
2025-08-31 07:36:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:36:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:37:30 - pico-train - INFO - Step 80900 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:37:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6346
2025-08-31 07:37:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:37:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:38:22 - pico-train - INFO - Step 81000 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:38:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7401
2025-08-31 07:38:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:38:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:39:14 - pico-train - INFO - Step 81100 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:39:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7133
2025-08-31 07:39:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:39:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:40:05 - pico-train - INFO - Step 81200 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:40:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7280
2025-08-31 07:40:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:40:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:40:57 - pico-train - INFO - Step 81300 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:40:57 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7991
2025-08-31 07:40:57 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:40:57 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:41:48 - pico-train - INFO - Step 81400 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:41:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6982
2025-08-31 07:41:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:41:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:42:40 - pico-train - INFO - Step 81500 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:42:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7575
2025-08-31 07:42:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:42:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:43:32 - pico-train - INFO - Step 81600 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:43:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7485
2025-08-31 07:43:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:43:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:44:23 - pico-train - INFO - Step 81700 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:44:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7542
2025-08-31 07:44:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:44:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:45:18 - pico-train - INFO - Step 81800 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:45:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7250
2025-08-31 07:45:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:45:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:46:09 - pico-train - INFO - Step 81900 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:46:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7202
2025-08-31 07:46:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:46:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:47:00 - pico-train - INFO - Step 82000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 07:48:48 - pico-train - INFO - Step 82000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 07:48:48 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 07:48:48 - pico-train - INFO - Step 82000 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:48:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7742
2025-08-31 07:48:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:48:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:48:48 - pico-train - INFO - Step 82000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 07:49:40 - pico-train - INFO - Step 82100 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:49:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7275
2025-08-31 07:49:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:49:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:50:32 - pico-train - INFO - Step 82200 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:50:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7428
2025-08-31 07:50:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:50:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:51:23 - pico-train - INFO - Step 82300 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:51:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7513
2025-08-31 07:51:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:51:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:52:15 - pico-train - INFO - Step 82400 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:52:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7617
2025-08-31 07:52:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:52:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:53:07 - pico-train - INFO - Step 82500 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:53:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7632
2025-08-31 07:53:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:53:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:53:58 - pico-train - INFO - Step 82600 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:53:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7351
2025-08-31 07:53:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:53:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:54:50 - pico-train - INFO - Step 82700 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:54:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7281
2025-08-31 07:54:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:54:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:55:41 - pico-train - INFO - Step 82800 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:55:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7582
2025-08-31 07:55:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:55:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:56:32 - pico-train - INFO - Step 82900 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:56:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6581
2025-08-31 07:56:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:56:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:57:24 - pico-train - INFO - Step 83000 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:57:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7060
2025-08-31 07:57:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:57:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:58:16 - pico-train - INFO - Step 83100 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:58:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7217
2025-08-31 07:58:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:58:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:59:07 - pico-train - INFO - Step 83200 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:59:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7407
2025-08-31 07:59:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:59:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 07:59:59 - pico-train - INFO - Step 83300 -- ๐Ÿ”„ Training Metrics
2025-08-31 07:59:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7347
2025-08-31 07:59:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 07:59:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:00:50 - pico-train - INFO - Step 83400 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:00:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7371
2025-08-31 08:00:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:00:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:01:42 - pico-train - INFO - Step 83500 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:01:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7134
2025-08-31 08:01:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:01:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:02:34 - pico-train - INFO - Step 83600 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:02:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7324
2025-08-31 08:02:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:02:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:03:25 - pico-train - INFO - Step 83700 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:03:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6926
2025-08-31 08:03:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:03:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:04:16 - pico-train - INFO - Step 83800 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:04:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7118
2025-08-31 08:04:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:04:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:05:08 - pico-train - INFO - Step 83900 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:05:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7378
2025-08-31 08:05:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:05:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:06:00 - pico-train - INFO - Step 84000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 08:07:47 - pico-train - INFO - Step 84000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 08:07:47 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 08:07:48 - pico-train - INFO - Step 84000 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:07:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7013
2025-08-31 08:07:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:07:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:07:48 - pico-train - INFO - Step 84000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 08:08:40 - pico-train - INFO - Step 84100 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:08:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6884
2025-08-31 08:08:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:08:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:09:32 - pico-train - INFO - Step 84200 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:09:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6894
2025-08-31 08:09:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:09:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:10:23 - pico-train - INFO - Step 84300 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:10:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7470
2025-08-31 08:10:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:10:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:11:14 - pico-train - INFO - Step 84400 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:11:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7089
2025-08-31 08:11:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:11:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:12:06 - pico-train - INFO - Step 84500 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:12:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6500
2025-08-31 08:12:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:12:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:12:58 - pico-train - INFO - Step 84600 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:12:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6849
2025-08-31 08:12:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:12:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:13:49 - pico-train - INFO - Step 84700 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:13:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6797
2025-08-31 08:13:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:13:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:14:41 - pico-train - INFO - Step 84800 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:14:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7071
2025-08-31 08:14:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:14:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:15:32 - pico-train - INFO - Step 84900 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:15:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6975
2025-08-31 08:15:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:15:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:16:25 - pico-train - INFO - Step 85000 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:16:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7164
2025-08-31 08:16:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:16:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:17:16 - pico-train - INFO - Step 85100 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:17:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6050
2025-08-31 08:17:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:17:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:18:07 - pico-train - INFO - Step 85200 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:18:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6708
2025-08-31 08:18:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:18:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:18:59 - pico-train - INFO - Step 85300 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:18:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6323
2025-08-31 08:18:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:18:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:19:51 - pico-train - INFO - Step 85400 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:19:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.5546
2025-08-31 08:19:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:19:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:20:43 - pico-train - INFO - Step 85500 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:20:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7022
2025-08-31 08:20:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:20:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:21:34 - pico-train - INFO - Step 85600 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:21:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6936
2025-08-31 08:21:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:21:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:22:26 - pico-train - INFO - Step 85700 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:22:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7058
2025-08-31 08:22:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:22:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:23:17 - pico-train - INFO - Step 85800 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:23:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7049
2025-08-31 08:23:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:23:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:24:09 - pico-train - INFO - Step 85900 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:24:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6506
2025-08-31 08:24:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:24:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:25:00 - pico-train - INFO - Step 86000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 08:26:48 - pico-train - INFO - Step 86000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 08:26:48 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 08:26:49 - pico-train - INFO - Step 86000 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:26:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6790
2025-08-31 08:26:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:26:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:26:49 - pico-train - INFO - Step 86000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 08:27:41 - pico-train - INFO - Step 86100 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:27:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7205
2025-08-31 08:27:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:27:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:28:32 - pico-train - INFO - Step 86200 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:28:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7132
2025-08-31 08:28:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:28:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:29:23 - pico-train - INFO - Step 86300 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:29:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6258
2025-08-31 08:29:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:29:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:30:15 - pico-train - INFO - Step 86400 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:30:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7446
2025-08-31 08:30:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:30:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:31:07 - pico-train - INFO - Step 86500 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:31:07 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6696
2025-08-31 08:31:07 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:31:07 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:31:58 - pico-train - INFO - Step 86600 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:31:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7031
2025-08-31 08:31:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:31:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:32:50 - pico-train - INFO - Step 86700 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:32:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7437
2025-08-31 08:32:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:32:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:33:41 - pico-train - INFO - Step 86800 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:33:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7354
2025-08-31 08:33:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:33:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:34:33 - pico-train - INFO - Step 86900 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:34:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7387
2025-08-31 08:34:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:34:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:35:25 - pico-train - INFO - Step 87000 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:35:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7328
2025-08-31 08:35:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:35:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:36:16 - pico-train - INFO - Step 87100 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:36:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7011
2025-08-31 08:36:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:36:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:37:08 - pico-train - INFO - Step 87200 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:37:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7231
2025-08-31 08:37:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:37:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:38:00 - pico-train - INFO - Step 87300 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:38:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7254
2025-08-31 08:38:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:38:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:38:52 - pico-train - INFO - Step 87400 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:38:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7838
2025-08-31 08:38:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:38:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:39:44 - pico-train - INFO - Step 87500 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:39:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7237
2025-08-31 08:39:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:39:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:40:35 - pico-train - INFO - Step 87600 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:40:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7589
2025-08-31 08:40:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:40:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:41:26 - pico-train - INFO - Step 87700 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:41:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7597
2025-08-31 08:41:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:41:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:42:18 - pico-train - INFO - Step 87800 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:42:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7013
2025-08-31 08:42:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:42:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:43:10 - pico-train - INFO - Step 87900 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:43:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6875
2025-08-31 08:43:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:43:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:44:02 - pico-train - INFO - Step 88000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 08:45:50 - pico-train - INFO - Step 88000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 08:45:50 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 08:45:50 - pico-train - INFO - Step 88000 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:45:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7735
2025-08-31 08:45:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:45:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:45:50 - pico-train - INFO - Step 88000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 08:46:42 - pico-train - INFO - Step 88100 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:46:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7450
2025-08-31 08:46:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:46:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:47:34 - pico-train - INFO - Step 88200 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:47:34 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7223
2025-08-31 08:47:34 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:47:34 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:48:26 - pico-train - INFO - Step 88300 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:48:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7561
2025-08-31 08:48:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:48:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:49:17 - pico-train - INFO - Step 88400 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:49:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7080
2025-08-31 08:49:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:49:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:50:09 - pico-train - INFO - Step 88500 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:50:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6788
2025-08-31 08:50:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:50:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:51:00 - pico-train - INFO - Step 88600 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:51:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6932
2025-08-31 08:51:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:51:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:51:52 - pico-train - INFO - Step 88700 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:51:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7393
2025-08-31 08:51:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:51:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:52:43 - pico-train - INFO - Step 88800 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:52:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7357
2025-08-31 08:52:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:52:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:53:35 - pico-train - INFO - Step 88900 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:53:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7379
2025-08-31 08:53:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:53:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:54:27 - pico-train - INFO - Step 89000 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:54:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7562
2025-08-31 08:54:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:54:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:55:19 - pico-train - INFO - Step 89100 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:55:19 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7427
2025-08-31 08:55:19 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:55:19 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:56:10 - pico-train - INFO - Step 89200 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:56:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7273
2025-08-31 08:56:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:56:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:57:02 - pico-train - INFO - Step 89300 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:57:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7312
2025-08-31 08:57:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:57:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:57:53 - pico-train - INFO - Step 89400 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:57:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6950
2025-08-31 08:57:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:57:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:58:45 - pico-train - INFO - Step 89500 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:58:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6980
2025-08-31 08:58:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:58:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 08:59:37 - pico-train - INFO - Step 89600 -- ๐Ÿ”„ Training Metrics
2025-08-31 08:59:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6993
2025-08-31 08:59:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 08:59:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:00:28 - pico-train - INFO - Step 89700 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:00:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6600
2025-08-31 09:00:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:00:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:01:20 - pico-train - INFO - Step 89800 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:01:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7641
2025-08-31 09:01:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:01:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:02:11 - pico-train - INFO - Step 89900 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:02:11 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7180
2025-08-31 09:02:11 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:02:11 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:03:03 - pico-train - INFO - Step 90000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 09:04:53 - pico-train - INFO - Step 90000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 09:04:53 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 09:04:53 - pico-train - INFO - Step 90000 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:04:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6701
2025-08-31 09:04:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:04:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:04:53 - pico-train - INFO - Step 90000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 09:05:45 - pico-train - INFO - Step 90100 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:05:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7339
2025-08-31 09:05:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:05:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:06:37 - pico-train - INFO - Step 90200 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:06:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7007
2025-08-31 09:06:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:06:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:07:28 - pico-train - INFO - Step 90300 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:07:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7463
2025-08-31 09:07:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:07:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:08:20 - pico-train - INFO - Step 90400 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:08:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7707
2025-08-31 09:08:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:08:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:09:12 - pico-train - INFO - Step 90500 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:09:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7085
2025-08-31 09:09:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:09:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:10:03 - pico-train - INFO - Step 90600 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:10:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7055
2025-08-31 09:10:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:10:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:10:55 - pico-train - INFO - Step 90700 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:10:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7187
2025-08-31 09:10:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:10:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:11:46 - pico-train - INFO - Step 90800 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:11:46 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7100
2025-08-31 09:11:46 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:11:46 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:12:38 - pico-train - INFO - Step 90900 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:12:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7254
2025-08-31 09:12:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:12:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:13:30 - pico-train - INFO - Step 91000 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:13:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7218
2025-08-31 09:13:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:13:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:14:21 - pico-train - INFO - Step 91100 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:14:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7145
2025-08-31 09:14:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:14:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:15:12 - pico-train - INFO - Step 91200 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:15:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7425
2025-08-31 09:15:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:15:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:16:04 - pico-train - INFO - Step 91300 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:16:04 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7399
2025-08-31 09:16:04 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:16:04 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:16:56 - pico-train - INFO - Step 91400 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:16:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7377
2025-08-31 09:16:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:16:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:17:48 - pico-train - INFO - Step 91500 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:17:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7343
2025-08-31 09:17:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:17:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:18:40 - pico-train - INFO - Step 91600 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:18:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7149
2025-08-31 09:18:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:18:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:19:31 - pico-train - INFO - Step 91700 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:19:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7143
2025-08-31 09:19:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:19:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:20:23 - pico-train - INFO - Step 91800 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:20:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7069
2025-08-31 09:20:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:20:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:21:15 - pico-train - INFO - Step 91900 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:21:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6903
2025-08-31 09:21:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:21:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:22:06 - pico-train - INFO - Step 92000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 09:23:55 - pico-train - INFO - Step 92000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 09:23:55 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 09:23:55 - pico-train - INFO - Step 92000 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:23:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7150
2025-08-31 09:23:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:23:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:23:55 - pico-train - INFO - Step 92000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 09:24:48 - pico-train - INFO - Step 92100 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:24:48 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7068
2025-08-31 09:24:48 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:24:48 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:25:40 - pico-train - INFO - Step 92200 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:25:40 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7260
2025-08-31 09:25:40 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:25:40 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:26:32 - pico-train - INFO - Step 92300 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:26:32 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7208
2025-08-31 09:26:32 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:26:32 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:27:24 - pico-train - INFO - Step 92400 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:27:24 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6989
2025-08-31 09:27:24 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:27:24 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:28:16 - pico-train - INFO - Step 92500 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:28:16 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7195
2025-08-31 09:28:16 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:28:16 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:29:08 - pico-train - INFO - Step 92600 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:29:08 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6940
2025-08-31 09:29:08 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:29:08 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:29:59 - pico-train - INFO - Step 92700 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:29:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7561
2025-08-31 09:29:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:29:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:30:51 - pico-train - INFO - Step 92800 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:30:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6793
2025-08-31 09:30:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:30:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:31:42 - pico-train - INFO - Step 92900 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:31:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7148
2025-08-31 09:31:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:31:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:32:35 - pico-train - INFO - Step 93000 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:32:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7254
2025-08-31 09:32:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:32:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:33:26 - pico-train - INFO - Step 93100 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:33:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6995
2025-08-31 09:33:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:33:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:34:17 - pico-train - INFO - Step 93200 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:34:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7255
2025-08-31 09:34:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:34:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:35:09 - pico-train - INFO - Step 93300 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:35:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7238
2025-08-31 09:35:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:35:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:36:00 - pico-train - INFO - Step 93400 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:36:00 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7211
2025-08-31 09:36:00 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:36:00 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:36:52 - pico-train - INFO - Step 93500 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:36:52 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6741
2025-08-31 09:36:52 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:36:52 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:37:43 - pico-train - INFO - Step 93600 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:37:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7281
2025-08-31 09:37:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:37:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:38:35 - pico-train - INFO - Step 93700 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:38:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6642
2025-08-31 09:38:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:38:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:39:27 - pico-train - INFO - Step 93800 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:39:27 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7126
2025-08-31 09:39:27 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:39:27 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:40:18 - pico-train - INFO - Step 93900 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:40:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7402
2025-08-31 09:40:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:40:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:41:09 - pico-train - INFO - Step 94000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 09:42:58 - pico-train - INFO - Step 94000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 09:42:58 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 09:42:59 - pico-train - INFO - Step 94000 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:42:59 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7579
2025-08-31 09:42:59 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:42:59 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:42:59 - pico-train - INFO - Step 94000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 09:43:51 - pico-train - INFO - Step 94100 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:43:51 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7224
2025-08-31 09:43:51 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:43:51 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:44:43 - pico-train - INFO - Step 94200 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:44:43 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7131
2025-08-31 09:44:43 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:44:43 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:45:35 - pico-train - INFO - Step 94300 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:45:35 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6659
2025-08-31 09:45:35 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:45:35 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:46:26 - pico-train - INFO - Step 94400 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:46:26 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6991
2025-08-31 09:46:26 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:46:26 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:47:18 - pico-train - INFO - Step 94500 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:47:18 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7049
2025-08-31 09:47:18 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:47:18 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:48:10 - pico-train - INFO - Step 94600 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:48:10 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6958
2025-08-31 09:48:10 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:48:10 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:49:02 - pico-train - INFO - Step 94700 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:49:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6892
2025-08-31 09:49:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:49:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:49:53 - pico-train - INFO - Step 94800 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:49:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6371
2025-08-31 09:49:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:49:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:50:45 - pico-train - INFO - Step 94900 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:50:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7253
2025-08-31 09:50:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:50:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:51:37 - pico-train - INFO - Step 95000 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:51:37 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7112
2025-08-31 09:51:37 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:51:37 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:52:29 - pico-train - INFO - Step 95100 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:52:29 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7578
2025-08-31 09:52:29 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:52:29 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:53:20 - pico-train - INFO - Step 95200 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:53:20 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7148
2025-08-31 09:53:20 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:53:20 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:54:12 - pico-train - INFO - Step 95300 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:54:12 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6893
2025-08-31 09:54:12 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:54:12 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:55:03 - pico-train - INFO - Step 95400 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:55:03 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6751
2025-08-31 09:55:03 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:55:03 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:55:56 - pico-train - INFO - Step 95500 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:55:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7003
2025-08-31 09:55:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:55:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:56:47 - pico-train - INFO - Step 95600 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:56:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7165
2025-08-31 09:56:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:56:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:57:39 - pico-train - INFO - Step 95700 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:57:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6655
2025-08-31 09:57:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:57:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:58:30 - pico-train - INFO - Step 95800 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:58:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7263
2025-08-31 09:58:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:58:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 09:59:22 - pico-train - INFO - Step 95900 -- ๐Ÿ”„ Training Metrics
2025-08-31 09:59:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6837
2025-08-31 09:59:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 09:59:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:00:13 - pico-train - INFO - Step 96000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 10:02:02 - pico-train - INFO - Step 96000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 10:02:02 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 10:02:02 - pico-train - INFO - Step 96000 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:02:02 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7159
2025-08-31 10:02:02 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:02:02 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:02:02 - pico-train - INFO - Step 96000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 10:02:55 - pico-train - INFO - Step 96100 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:02:55 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7156
2025-08-31 10:02:55 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:02:55 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:03:47 - pico-train - INFO - Step 96200 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:03:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7599
2025-08-31 10:03:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:03:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:04:38 - pico-train - INFO - Step 96300 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:04:38 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7298
2025-08-31 10:04:38 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:04:38 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:05:30 - pico-train - INFO - Step 96400 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:05:30 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7523
2025-08-31 10:05:30 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:05:30 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:06:23 - pico-train - INFO - Step 96500 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:06:23 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7078
2025-08-31 10:06:23 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:06:23 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:07:15 - pico-train - INFO - Step 96600 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:07:15 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6924
2025-08-31 10:07:15 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:07:15 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:08:06 - pico-train - INFO - Step 96700 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:08:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7354
2025-08-31 10:08:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:08:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:08:58 - pico-train - INFO - Step 96800 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:08:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7358
2025-08-31 10:08:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:08:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:09:49 - pico-train - INFO - Step 96900 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:09:49 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7259
2025-08-31 10:09:49 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:09:49 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:10:42 - pico-train - INFO - Step 97000 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:10:42 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7149
2025-08-31 10:10:42 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:10:42 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:11:33 - pico-train - INFO - Step 97100 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:11:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7222
2025-08-31 10:11:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:11:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:12:25 - pico-train - INFO - Step 97200 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:12:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6903
2025-08-31 10:12:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:12:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:13:17 - pico-train - INFO - Step 97300 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:13:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7370
2025-08-31 10:13:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:13:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:14:09 - pico-train - INFO - Step 97400 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:14:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7236
2025-08-31 10:14:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:14:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:15:01 - pico-train - INFO - Step 97500 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:15:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6993
2025-08-31 10:15:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:15:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:15:53 - pico-train - INFO - Step 97600 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:15:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7178
2025-08-31 10:15:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:15:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:16:44 - pico-train - INFO - Step 97700 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:16:44 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6855
2025-08-31 10:16:44 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:16:44 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:17:36 - pico-train - INFO - Step 97800 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:17:36 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6959
2025-08-31 10:17:36 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:17:36 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:18:28 - pico-train - INFO - Step 97900 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:18:28 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6574
2025-08-31 10:18:28 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:18:28 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:19:20 - pico-train - INFO - Step 98000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 10:21:20 - pico-train - INFO - Step 98000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 10:21:20 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 10:21:21 - pico-train - INFO - Step 98000 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:21:21 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6908
2025-08-31 10:21:21 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:21:21 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:21:21 - pico-train - INFO - Step 98000 -- ๐Ÿ“ˆ Saving Learning Dynamics
2025-08-31 10:22:13 - pico-train - INFO - Step 98100 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:22:13 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6721
2025-08-31 10:22:13 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:22:13 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:23:05 - pico-train - INFO - Step 98200 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:23:05 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6259
2025-08-31 10:23:05 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:23:05 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:23:56 - pico-train - INFO - Step 98300 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:23:56 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7160
2025-08-31 10:23:56 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:23:56 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:24:47 - pico-train - INFO - Step 98400 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:24:47 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6780
2025-08-31 10:24:47 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:24:47 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:25:39 - pico-train - INFO - Step 98500 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:25:39 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6724
2025-08-31 10:25:39 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:25:39 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:26:31 - pico-train - INFO - Step 98600 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:26:31 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6849
2025-08-31 10:26:31 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:26:31 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:27:22 - pico-train - INFO - Step 98700 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:27:22 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7412
2025-08-31 10:27:22 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:27:22 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:28:14 - pico-train - INFO - Step 98800 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:28:14 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6764
2025-08-31 10:28:14 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:28:14 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:29:06 - pico-train - INFO - Step 98900 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:29:06 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6885
2025-08-31 10:29:06 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:29:06 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:29:58 - pico-train - INFO - Step 99000 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:29:58 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6226
2025-08-31 10:29:58 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:29:58 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:30:50 - pico-train - INFO - Step 99100 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:30:50 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6555
2025-08-31 10:30:50 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:30:50 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:31:41 - pico-train - INFO - Step 99200 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:31:41 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7045
2025-08-31 10:31:41 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:31:41 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:32:33 - pico-train - INFO - Step 99300 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:32:33 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6697
2025-08-31 10:32:33 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:32:33 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:33:25 - pico-train - INFO - Step 99400 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:33:25 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7305
2025-08-31 10:33:25 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:33:25 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:34:17 - pico-train - INFO - Step 99500 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:34:17 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7240
2025-08-31 10:34:17 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:34:17 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:35:09 - pico-train - INFO - Step 99600 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:35:09 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7108
2025-08-31 10:35:09 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:35:09 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:36:01 - pico-train - INFO - Step 99700 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:36:01 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6812
2025-08-31 10:36:01 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:36:01 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:36:53 - pico-train - INFO - Step 99800 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:36:53 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.6736
2025-08-31 10:36:53 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:36:53 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:37:45 - pico-train - INFO - Step 99900 -- ๐Ÿ”„ Training Metrics
2025-08-31 10:37:45 - pico-train - INFO - โ”œโ”€โ”€ Loss: 4.7339
2025-08-31 10:37:45 - pico-train - INFO - โ”œโ”€โ”€ Learning Rate: 2.00e-05
2025-08-31 10:37:45 - pico-train - INFO - โ””โ”€โ”€ Inf/NaN count: 0
2025-08-31 10:38:36 - pico-train - INFO - Step 100000 -- ๐Ÿ’พ Saving Checkpoint
2025-08-31 10:40:26 - pico-train - INFO - Step 100000 -- ๐Ÿ“Š Evaluation Results
2025-08-31 10:40:26 - pico-train - INFO - โ””โ”€โ”€ paloma: inf
2025-08-31 10:40:26 - pico-train - INFO - ๐ŸŽ‰ Training complete! Final step: 100000