| { | |
| "best_metric": 0.1498371809720993, | |
| "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": 4.700385093688965, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.2418, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7959429259068248, | |
| "eval_f1": 0.7966197926671241, | |
| "eval_loss": 0.16391175985336304, | |
| "eval_precision": 0.7991994510166862, | |
| "eval_recall": 0.7959429259068248, | |
| "eval_runtime": 100.4073, | |
| "eval_samples_per_second": 57.934, | |
| "eval_steps_per_second": 3.625, | |
| "step": 2909 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 8.463471412658691, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1604, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8064294309781674, | |
| "eval_f1": 0.8053608258865061, | |
| "eval_loss": 0.15333504974842072, | |
| "eval_precision": 0.8052697458077352, | |
| "eval_recall": 0.8064294309781674, | |
| "eval_runtime": 100.3134, | |
| "eval_samples_per_second": 57.988, | |
| "eval_steps_per_second": 3.629, | |
| "step": 5818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.2503557205200195, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.1439, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8090080797662025, | |
| "eval_f1": 0.8076490839502344, | |
| "eval_loss": 0.15068580210208893, | |
| "eval_precision": 0.8146301569598754, | |
| "eval_recall": 0.8090080797662025, | |
| "eval_runtime": 100.118, | |
| "eval_samples_per_second": 58.101, | |
| "eval_steps_per_second": 3.636, | |
| "step": 8727 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 16.41270637512207, | |
| "learning_rate": 3e-06, | |
| "loss": 0.1334, | |
| "step": 11636 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8157125666150937, | |
| "eval_f1": 0.8149260377068153, | |
| "eval_loss": 0.1498371809720993, | |
| "eval_precision": 0.8182217344166064, | |
| "eval_recall": 0.8157125666150937, | |
| "eval_runtime": 100.6661, | |
| "eval_samples_per_second": 57.785, | |
| "eval_steps_per_second": 3.616, | |
| "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 | |
| } | |