| { | |
| "best_metric": 1.2436659336090088, | |
| "best_model_checkpoint": "./results_v1/checkpoint-585", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 585, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 16204.2978515625, | |
| "learning_rate": 0.00041452991452991454, | |
| "loss": 1.2355, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3050023317337036, | |
| "eval_runtime": 35.7149, | |
| "eval_samples_per_second": 416.885, | |
| "eval_steps_per_second": 3.276, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.7094017094017095, | |
| "grad_norm": 21855.40625, | |
| "learning_rate": 0.00032905982905982907, | |
| "loss": 1.2163, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2828969955444336, | |
| "eval_runtime": 34.9809, | |
| "eval_samples_per_second": 425.632, | |
| "eval_steps_per_second": 3.345, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 17783.169921875, | |
| "learning_rate": 0.0002435897435897436, | |
| "loss": 1.2163, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.2669651508331299, | |
| "eval_runtime": 34.8672, | |
| "eval_samples_per_second": 427.02, | |
| "eval_steps_per_second": 3.356, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 3.4188034188034186, | |
| "grad_norm": 15218.6376953125, | |
| "learning_rate": 0.0001581196581196581, | |
| "loss": 1.216, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.251606822013855, | |
| "eval_runtime": 34.7427, | |
| "eval_samples_per_second": 428.551, | |
| "eval_steps_per_second": 3.368, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 4.273504273504273, | |
| "grad_norm": 16033.8818359375, | |
| "learning_rate": 7.264957264957266e-05, | |
| "loss": 1.2226, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.2436659336090088, | |
| "eval_runtime": 35.678, | |
| "eval_samples_per_second": 417.316, | |
| "eval_steps_per_second": 3.279, | |
| "step": 585 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 585, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2518964691271680.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |