| { | |
| "best_metric": 0.14547553658485413, | |
| "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": 5.2063212394714355, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.2387, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7930204572803851, | |
| "eval_f1": 0.7932853926441528, | |
| "eval_loss": 0.16649502515792847, | |
| "eval_precision": 0.794902013008092, | |
| "eval_recall": 0.7930204572803851, | |
| "eval_runtime": 101.0115, | |
| "eval_samples_per_second": 57.588, | |
| "eval_steps_per_second": 3.604, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.03398060798645, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1631, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8064294309781674, | |
| "eval_f1": 0.8062676902833994, | |
| "eval_loss": 0.15255120396614075, | |
| "eval_precision": 0.80643078360253, | |
| "eval_recall": 0.8064294309781674, | |
| "eval_runtime": 100.8655, | |
| "eval_samples_per_second": 57.671, | |
| "eval_steps_per_second": 3.609, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 3.4921460151672363, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.1468, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8071170706549768, | |
| "eval_f1": 0.8049004964803439, | |
| "eval_loss": 0.15074454247951508, | |
| "eval_precision": 0.8111961473199412, | |
| "eval_recall": 0.8071170706549768, | |
| "eval_runtime": 100.8595, | |
| "eval_samples_per_second": 57.674, | |
| "eval_steps_per_second": 3.609, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 11.993130683898926, | |
| "learning_rate": 3e-06, | |
| "loss": 0.1356, | |
| "step": 11636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.814337287261475, | |
| "eval_f1": 0.8140919299662062, | |
| "eval_loss": 0.14547553658485413, | |
| "eval_precision": 0.8174255151026747, | |
| "eval_recall": 0.814337287261475, | |
| "eval_runtime": 100.7001, | |
| "eval_samples_per_second": 57.766, | |
| "eval_steps_per_second": 3.615, | |
| "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 | |
| } | |