| { | |
| "best_metric": 0.1422930359840393, | |
| "best_model_checkpoint": "/content/drive/MyDrive/RoBERTa/checkpoint-11636", | |
| "epoch": 4.0, | |
| "eval_steps": 100, | |
| "global_step": 11636, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.20160436630249, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.2335, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8119305483926422, | |
| "eval_f1": 0.8125438936194447, | |
| "eval_loss": 0.15657220780849457, | |
| "eval_precision": 0.8148818865641057, | |
| "eval_recall": 0.8119305483926422, | |
| "eval_runtime": 99.4857, | |
| "eval_samples_per_second": 58.471, | |
| "eval_steps_per_second": 3.659, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.025620937347412, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1564, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8196664947567475, | |
| "eval_f1": 0.819601210384621, | |
| "eval_loss": 0.14257530868053436, | |
| "eval_precision": 0.8231443904443204, | |
| "eval_recall": 0.8196664947567475, | |
| "eval_runtime": 99.334, | |
| "eval_samples_per_second": 58.56, | |
| "eval_steps_per_second": 3.664, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.3682355880737305, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.1403, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8134777376654633, | |
| "eval_f1": 0.8103113366034572, | |
| "eval_loss": 0.14786231517791748, | |
| "eval_precision": 0.8253242439784585, | |
| "eval_recall": 0.8134777376654633, | |
| "eval_runtime": 99.221, | |
| "eval_samples_per_second": 58.627, | |
| "eval_steps_per_second": 3.669, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 24.70423126220703, | |
| "learning_rate": 3e-06, | |
| "loss": 0.13, | |
| "step": 11636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8201822245143545, | |
| "eval_f1": 0.8192565062099832, | |
| "eval_loss": 0.1422930359840393, | |
| "eval_precision": 0.8239091740579143, | |
| "eval_recall": 0.8201822245143545, | |
| "eval_runtime": 99.1112, | |
| "eval_samples_per_second": 58.692, | |
| "eval_steps_per_second": 3.673, | |
| "step": 11636 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 29090, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.897619828740915e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |