| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.289308176100629, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6825806451612904, |
| "eval_loss": 0.10565969347953796, |
| "eval_runtime": 1.1019, |
| "eval_samples_per_second": 2813.278, |
| "eval_steps_per_second": 58.988, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.5723270440251573, |
| "grad_norm": 0.42095282673835754, |
| "learning_rate": 1.6512928022361987e-05, |
| "loss": 0.2152, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8448387096774194, |
| "eval_loss": 0.03441493213176727, |
| "eval_runtime": 1.1184, |
| "eval_samples_per_second": 2771.792, |
| "eval_steps_per_second": 58.118, |
| "step": 636 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8696774193548387, |
| "eval_loss": 0.016895057633519173, |
| "eval_runtime": 1.104, |
| "eval_samples_per_second": 2807.917, |
| "eval_steps_per_second": 58.876, |
| "step": 954 |
| }, |
| { |
| "epoch": 3.1446540880503147, |
| "grad_norm": 0.2212529331445694, |
| "learning_rate": 1.3018867924528303e-05, |
| "loss": 0.0593, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8825806451612903, |
| "eval_loss": 0.010781311430037022, |
| "eval_runtime": 1.3232, |
| "eval_samples_per_second": 2342.828, |
| "eval_steps_per_second": 49.124, |
| "step": 1272 |
| }, |
| { |
| "epoch": 4.716981132075472, |
| "grad_norm": 0.1644132286310196, |
| "learning_rate": 9.52480782669462e-06, |
| "loss": 0.0387, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8935483870967742, |
| "eval_loss": 0.008324305526912212, |
| "eval_runtime": 1.3144, |
| "eval_samples_per_second": 2358.523, |
| "eval_steps_per_second": 49.453, |
| "step": 1590 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.895483870967742, |
| "eval_loss": 0.0069857933558523655, |
| "eval_runtime": 1.1202, |
| "eval_samples_per_second": 2767.413, |
| "eval_steps_per_second": 58.026, |
| "step": 1908 |
| }, |
| { |
| "epoch": 6.289308176100629, |
| "grad_norm": 0.1462177038192749, |
| "learning_rate": 6.030747728860937e-06, |
| "loss": 0.0325, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2862, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 780995662024872.0, |
| "train_batch_size": 48, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.5786410356798017, |
| "num_train_epochs": 9, |
| "temperature": 11 |
| } |
| } |
|
|
