| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 624, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.946100094179943, | |
| "eval_f1": 0.7340220626860444, | |
| "eval_loss": 0.14316441118717194, | |
| "eval_precision": 0.6818477553675992, | |
| "eval_recall": 0.7948426241941601, | |
| "eval_runtime": 22.657, | |
| "eval_samples_per_second": 188.286, | |
| "eval_steps_per_second": 23.569, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6025641025641026, | |
| "grad_norm": 1.601723313331604, | |
| "learning_rate": 9.69728805152637e-06, | |
| "loss": 0.2254, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9495906794786515, | |
| "eval_f1": 0.7751245490465556, | |
| "eval_loss": 0.13631665706634521, | |
| "eval_precision": 0.7085427135678392, | |
| "eval_recall": 0.8555176336746303, | |
| "eval_runtime": 22.5415, | |
| "eval_samples_per_second": 189.251, | |
| "eval_steps_per_second": 23.69, | |
| "step": 624 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1560, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 1773155225219268.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 1.4271480528661449e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 64, | |
| "seed": 2 | |
| } | |
| } | |