| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1590, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9968553459119497, | |
| "grad_norm": 1.6039808988571167, | |
| "learning_rate": 5.065571746465663e-05, | |
| "loss": 1.6999, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8796774193548387, | |
| "eval_loss": 0.6092725992202759, | |
| "eval_runtime": 1.5297, | |
| "eval_samples_per_second": 2026.511, | |
| "eval_steps_per_second": 42.491, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.9937106918238994, | |
| "grad_norm": 1.3073052167892456, | |
| "learning_rate": 3.804152859089688e-05, | |
| "loss": 0.3649, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9441935483870968, | |
| "eval_loss": 0.26733827590942383, | |
| "eval_runtime": 1.599, | |
| "eval_samples_per_second": 1938.714, | |
| "eval_steps_per_second": 40.65, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.990566037735849, | |
| "grad_norm": 0.9172638654708862, | |
| "learning_rate": 2.5427339717137144e-05, | |
| "loss": 0.17, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9509677419354838, | |
| "eval_loss": 0.21482910215854645, | |
| "eval_runtime": 1.5321, | |
| "eval_samples_per_second": 2023.337, | |
| "eval_steps_per_second": 42.425, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.9874213836477987, | |
| "grad_norm": 0.21971359848976135, | |
| "learning_rate": 1.2813150843377403e-05, | |
| "loss": 0.1257, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9525806451612904, | |
| "eval_loss": 0.19617104530334473, | |
| "eval_runtime": 1.5262, | |
| "eval_samples_per_second": 2031.182, | |
| "eval_steps_per_second": 42.589, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 4.984276729559748, | |
| "grad_norm": 0.26785457134246826, | |
| "learning_rate": 1.9896196961766153e-07, | |
| "loss": 0.1111, | |
| "step": 1585 | |
| } | |
| ], | |
| "logging_steps": 317, | |
| "max_steps": 1590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000000000.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 413645760585204.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.5465581592325828, | |
| "learning_rate": 6.326990633841637e-05, | |
| "num_train_epochs": 5, | |
| "temperature": 10, | |
| "weight_decay": 0.002233921802208827 | |
| } | |
| } | |