| { | |
| "best_metric": 0.8301435406698564, | |
| "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-135", | |
| "epoch": 2.958904109589041, | |
| "eval_steps": 500, | |
| "global_step": 135, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9863013698630136, | |
| "eval_accuracy": 0.777511961722488, | |
| "eval_loss": 0.561026930809021, | |
| "eval_runtime": 1.0204, | |
| "eval_samples_per_second": 409.634, | |
| "eval_steps_per_second": 51.939, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.9945205479452055, | |
| "eval_accuracy": 0.8133971291866029, | |
| "eval_loss": 0.43190622329711914, | |
| "eval_runtime": 1.0273, | |
| "eval_samples_per_second": 406.884, | |
| "eval_steps_per_second": 51.591, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 2.958904109589041, | |
| "eval_accuracy": 0.8301435406698564, | |
| "eval_loss": 0.40697425603866577, | |
| "eval_runtime": 1.063, | |
| "eval_samples_per_second": 393.225, | |
| "eval_steps_per_second": 49.859, | |
| "step": 135 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 135, | |
| "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": 1.964476902528e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |