| { |
| "best_global_step": 200, |
| "best_metric": 0.9943516121440339, |
| "best_model_checkpoint": "/content/drive/MyDrive/model/roberta_model/checkpoint-200", |
| "epoch": 0.3651300775901415, |
| "eval_steps": 200, |
| "global_step": 800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00045641259698767686, |
| "grad_norm": 10.173584938049316, |
| "learning_rate": 0.0, |
| "loss": 1.9445, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.045641259698767686, |
| "grad_norm": 1.0232760906219482, |
| "learning_rate": 5.5872291904218926e-06, |
| "loss": 1.2613, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09128251939753537, |
| "grad_norm": 0.08294256031513214, |
| "learning_rate": 1.1288483466362599e-05, |
| "loss": 0.0782, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.09128251939753537, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.041581232100725174, |
| "eval_runtime": 27.4281, |
| "eval_samples_per_second": 154.914, |
| "eval_steps_per_second": 9.698, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.13692377909630304, |
| "grad_norm": 0.3370012044906616, |
| "learning_rate": 1.6875712656784493e-05, |
| "loss": 0.0881, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.18256503879507074, |
| "grad_norm": 0.047330956906080246, |
| "learning_rate": 2.2576966932725198e-05, |
| "loss": 0.0638, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.18256503879507074, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.04604693129658699, |
| "eval_runtime": 26.999, |
| "eval_samples_per_second": 157.376, |
| "eval_steps_per_second": 9.852, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.22820629849383842, |
| "grad_norm": 0.10343942046165466, |
| "learning_rate": 2.8278221208665906e-05, |
| "loss": 0.0685, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2738475581926061, |
| "grad_norm": 1.5386130809783936, |
| "learning_rate": 3.397947548460662e-05, |
| "loss": 0.0983, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2738475581926061, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.038662198930978775, |
| "eval_runtime": 26.7411, |
| "eval_samples_per_second": 158.894, |
| "eval_steps_per_second": 9.947, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3194888178913738, |
| "grad_norm": 0.0841965451836586, |
| "learning_rate": 3.9680729760547326e-05, |
| "loss": 0.0629, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.3651300775901415, |
| "grad_norm": 0.15497300028800964, |
| "learning_rate": 4.538198403648803e-05, |
| "loss": 0.0914, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3651300775901415, |
| "eval_accuracy": 0.9943516121440339, |
| "eval_f1_macro": 0.24929195185272598, |
| "eval_f1_weighted": 0.9915354168771638, |
| "eval_loss": 0.039651524275541306, |
| "eval_runtime": 26.6349, |
| "eval_samples_per_second": 159.528, |
| "eval_steps_per_second": 9.987, |
| "step": 800 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 8764, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2525934167654400.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
