| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 5268, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2847380410022779, | |
| "grad_norm": 7.928560256958008, | |
| "learning_rate": 1.810174639331815e-05, | |
| "loss": 0.2906, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5694760820045558, | |
| "grad_norm": 0.12530961632728577, | |
| "learning_rate": 1.6203492786636296e-05, | |
| "loss": 0.1285, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8542141230068337, | |
| "grad_norm": 2.731761932373047, | |
| "learning_rate": 1.4305239179954442e-05, | |
| "loss": 0.0912, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9761288043798199, | |
| "eval_f1": 0.8952098276857119, | |
| "eval_loss": 0.08535858988761902, | |
| "eval_precision": 0.8774850492969128, | |
| "eval_recall": 0.913665432514305, | |
| "eval_runtime": 6.7803, | |
| "eval_samples_per_second": 479.332, | |
| "eval_steps_per_second": 60.027, | |
| "step": 1756 | |
| }, | |
| { | |
| "epoch": 1.1389521640091116, | |
| "grad_norm": 0.34379810094833374, | |
| "learning_rate": 1.240698557327259e-05, | |
| "loss": 0.0756, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.4236902050113895, | |
| "grad_norm": 0.34557342529296875, | |
| "learning_rate": 1.0508731966590738e-05, | |
| "loss": 0.055, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.7084282460136673, | |
| "grad_norm": 0.9085732102394104, | |
| "learning_rate": 8.610478359908885e-06, | |
| "loss": 0.0546, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.9931662870159452, | |
| "grad_norm": 2.8519742488861084, | |
| "learning_rate": 6.712224753227031e-06, | |
| "loss": 0.0464, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9827367987284394, | |
| "eval_f1": 0.9272848565710473, | |
| "eval_loss": 0.06802816689014435, | |
| "eval_precision": 0.9190082644628099, | |
| "eval_recall": 0.9357118815213733, | |
| "eval_runtime": 6.6043, | |
| "eval_samples_per_second": 492.101, | |
| "eval_steps_per_second": 61.626, | |
| "step": 3512 | |
| }, | |
| { | |
| "epoch": 2.277904328018223, | |
| "grad_norm": 2.584799289703369, | |
| "learning_rate": 4.8139711465451785e-06, | |
| "loss": 0.0312, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.562642369020501, | |
| "grad_norm": 0.4364319145679474, | |
| "learning_rate": 2.9157175398633257e-06, | |
| "loss": 0.0278, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.847380410022779, | |
| "grad_norm": 0.10701252520084381, | |
| "learning_rate": 1.0174639331814731e-06, | |
| "loss": 0.0292, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.983354918467063, | |
| "eval_f1": 0.9289044289044289, | |
| "eval_loss": 0.07014655321836472, | |
| "eval_precision": 0.9191103789126853, | |
| "eval_recall": 0.9389094580949175, | |
| "eval_runtime": 6.9523, | |
| "eval_samples_per_second": 467.471, | |
| "eval_steps_per_second": 58.542, | |
| "step": 5268 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5268, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 460431563935266.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |