| { | |
| "best_metric": 0.8691275167785235, | |
| "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-126", | |
| "epoch": 6.76510067114094, | |
| "eval_steps": 500, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9664429530201343, | |
| "eval_accuracy": 0.7583892617449665, | |
| "eval_loss": 0.686046838760376, | |
| "eval_runtime": 3.2977, | |
| "eval_samples_per_second": 90.365, | |
| "eval_steps_per_second": 11.523, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.9865771812080537, | |
| "eval_accuracy": 0.802013422818792, | |
| "eval_loss": 0.46226799488067627, | |
| "eval_runtime": 3.2911, | |
| "eval_samples_per_second": 90.546, | |
| "eval_steps_per_second": 11.546, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.953020134228188, | |
| "eval_accuracy": 0.8187919463087249, | |
| "eval_loss": 0.4068666100502014, | |
| "eval_runtime": 3.2466, | |
| "eval_samples_per_second": 91.789, | |
| "eval_steps_per_second": 11.705, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.9731543624161074, | |
| "eval_accuracy": 0.8355704697986577, | |
| "eval_loss": 0.3811332583427429, | |
| "eval_runtime": 3.297, | |
| "eval_samples_per_second": 90.386, | |
| "eval_steps_per_second": 11.526, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.993288590604027, | |
| "eval_accuracy": 0.8355704697986577, | |
| "eval_loss": 0.3542439937591553, | |
| "eval_runtime": 3.2411, | |
| "eval_samples_per_second": 91.944, | |
| "eval_steps_per_second": 11.724, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 5.959731543624161, | |
| "eval_accuracy": 0.8657718120805369, | |
| "eval_loss": 0.33795884251594543, | |
| "eval_runtime": 3.2596, | |
| "eval_samples_per_second": 91.423, | |
| "eval_steps_per_second": 11.658, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 6.76510067114094, | |
| "eval_accuracy": 0.8691275167785235, | |
| "eval_loss": 0.33603718876838684, | |
| "eval_runtime": 3.2413, | |
| "eval_samples_per_second": 91.938, | |
| "eval_steps_per_second": 11.724, | |
| "step": 126 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 126, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 1.831207226112e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |