| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 2220, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0, | |
| "eval_f1": 0.6600234466588512, | |
| "eval_loss": 0.7671048641204834, | |
| "eval_precision": 0.5101948346171273, | |
| "eval_recall": 0.9344398340248963, | |
| "eval_runtime": 51.027, | |
| "eval_samples_per_second": 91.579, | |
| "eval_steps_per_second": 11.465, | |
| "step": 0 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 15.12405776977539, | |
| "learning_rate": 3.998194945848376e-05, | |
| "loss": 0.4466, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.853844648796713, | |
| "eval_loss": 0.3588806986808777, | |
| "eval_precision": 0.8078489448352462, | |
| "eval_recall": 0.9053941908713693, | |
| "eval_runtime": 50.9684, | |
| "eval_samples_per_second": 91.684, | |
| "eval_steps_per_second": 11.478, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 23.096698760986328, | |
| "learning_rate": 2.996389891696751e-05, | |
| "loss": 0.301, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.8517921868707209, | |
| "eval_loss": 0.3814432919025421, | |
| "eval_precision": 0.8274647887323944, | |
| "eval_recall": 0.8775933609958506, | |
| "eval_runtime": 39.2431, | |
| "eval_samples_per_second": 119.078, | |
| "eval_steps_per_second": 14.907, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 24.367385864257812, | |
| "learning_rate": 1.9945848375451266e-05, | |
| "loss": 0.1689, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.8443708609271523, | |
| "eval_loss": 0.4720623791217804, | |
| "eval_precision": 0.8422791081750619, | |
| "eval_recall": 0.8464730290456431, | |
| "eval_runtime": 38.3517, | |
| "eval_samples_per_second": 121.846, | |
| "eval_steps_per_second": 15.254, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 16.34662437438965, | |
| "learning_rate": 9.927797833935018e-06, | |
| "loss": 0.0831, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.8335074159181115, | |
| "eval_loss": 0.7186992168426514, | |
| "eval_precision": 0.8392932267564156, | |
| "eval_recall": 0.8278008298755186, | |
| "eval_runtime": 38.6473, | |
| "eval_samples_per_second": 120.914, | |
| "eval_steps_per_second": 15.137, | |
| "step": 2220 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2770, | |
| "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": 7.717028512353485e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |