| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.12, |
| "eval_steps": 50, |
| "global_step": 700, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "learning_rate": 2.3869346733668342e-05, |
| "loss": 1.2058, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_loss": 0.9411209225654602, |
| "eval_runtime": 405.7571, |
| "eval_samples_per_second": 12.323, |
| "eval_steps_per_second": 1.54, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 2.2613065326633167e-05, |
| "loss": 0.9065, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_loss": 0.8835591673851013, |
| "eval_runtime": 405.6798, |
| "eval_samples_per_second": 12.325, |
| "eval_steps_per_second": 1.541, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 2.135678391959799e-05, |
| "loss": 0.8612, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_loss": 0.8560027480125427, |
| "eval_runtime": 405.7296, |
| "eval_samples_per_second": 12.323, |
| "eval_steps_per_second": 1.54, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 2.0100502512562815e-05, |
| "loss": 0.8536, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_loss": 0.8348749876022339, |
| "eval_runtime": 405.5958, |
| "eval_samples_per_second": 12.328, |
| "eval_steps_per_second": 1.541, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 1.884422110552764e-05, |
| "loss": 0.8195, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 0.8201740384101868, |
| "eval_runtime": 405.604, |
| "eval_samples_per_second": 12.327, |
| "eval_steps_per_second": 1.541, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 1.7587939698492464e-05, |
| "loss": 0.8272, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_loss": 0.807165801525116, |
| "eval_runtime": 405.5942, |
| "eval_samples_per_second": 12.328, |
| "eval_steps_per_second": 1.541, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 1.6331658291457288e-05, |
| "loss": 0.8132, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_loss": 0.7971442341804504, |
| "eval_runtime": 405.5887, |
| "eval_samples_per_second": 12.328, |
| "eval_steps_per_second": 1.541, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 1.507537688442211e-05, |
| "loss": 0.8124, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_loss": 0.7893713116645813, |
| "eval_runtime": 405.5093, |
| "eval_samples_per_second": 12.33, |
| "eval_steps_per_second": 1.541, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 1.3819095477386935e-05, |
| "loss": 0.7823, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_loss": 0.7817508578300476, |
| "eval_runtime": 405.5623, |
| "eval_samples_per_second": 12.329, |
| "eval_steps_per_second": 1.541, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 1.2562814070351759e-05, |
| "loss": 0.772, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.7751882672309875, |
| "eval_runtime": 405.5365, |
| "eval_samples_per_second": 12.329, |
| "eval_steps_per_second": 1.541, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 1.1306532663316583e-05, |
| "loss": 0.7668, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_loss": 0.7704442143440247, |
| "eval_runtime": 405.5551, |
| "eval_samples_per_second": 12.329, |
| "eval_steps_per_second": 1.541, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 1.0050251256281408e-05, |
| "loss": 0.7827, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 0.7652014493942261, |
| "eval_runtime": 405.6401, |
| "eval_samples_per_second": 12.326, |
| "eval_steps_per_second": 1.541, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 8.793969849246232e-06, |
| "loss": 0.7248, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.04, |
| "eval_loss": 0.7625133991241455, |
| "eval_runtime": 405.4991, |
| "eval_samples_per_second": 12.33, |
| "eval_steps_per_second": 1.541, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 7.537688442211055e-06, |
| "loss": 0.7107, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_loss": 0.7591288089752197, |
| "eval_runtime": 405.5072, |
| "eval_samples_per_second": 12.33, |
| "eval_steps_per_second": 1.541, |
| "step": 700 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "total_flos": 1.226918527500288e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
