| { |
| "best_global_step": 2676, |
| "best_metric": 0.8785521354799841, |
| "best_model_checkpoint": "outputs/xlm-r-spam-binary/checkpoint-2676", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 2676, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8380592312539382, |
| "eval_f1": 0.7446043097893572, |
| "eval_loss": 0.4673084318637848, |
| "eval_precision": 0.8814136508052441, |
| "eval_recall": 0.7099304536592229, |
| "eval_runtime": 6.2961, |
| "eval_samples_per_second": 252.06, |
| "eval_steps_per_second": 31.607, |
| "step": 446 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8954001260239446, |
| "eval_f1": 0.8581815245478036, |
| "eval_loss": 0.2860272526741028, |
| "eval_precision": 0.8911766356713877, |
| "eval_recall": 0.8362022873912083, |
| "eval_runtime": 6.3092, |
| "eval_samples_per_second": 251.537, |
| "eval_steps_per_second": 31.541, |
| "step": 892 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9017013232514177, |
| "eval_f1": 0.8763134439910312, |
| "eval_loss": 0.2545902132987976, |
| "eval_precision": 0.8741907793554848, |
| "eval_recall": 0.8785170147333722, |
| "eval_runtime": 6.3097, |
| "eval_samples_per_second": 251.517, |
| "eval_steps_per_second": 31.539, |
| "step": 1338 |
| }, |
| { |
| "epoch": 3.9960740325294446, |
| "grad_norm": 6.024568557739258, |
| "learning_rate": 2.98821174647605e-05, |
| "loss": 0.3102, |
| "step": 1782 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8966603654694392, |
| "eval_f1": 0.8620397933999949, |
| "eval_loss": 0.3537818491458893, |
| "eval_precision": 0.8863547186830534, |
| "eval_recall": 0.8443729774275894, |
| "eval_runtime": 6.3034, |
| "eval_samples_per_second": 251.771, |
| "eval_steps_per_second": 31.57, |
| "step": 1784 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8758664146187776, |
| "eval_f1": 0.8526447810662267, |
| "eval_loss": 0.33958056569099426, |
| "eval_precision": 0.8369464036375354, |
| "eval_recall": 0.8783341038371089, |
| "eval_runtime": 6.3052, |
| "eval_samples_per_second": 251.696, |
| "eval_steps_per_second": 31.561, |
| "step": 2230 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.906112161310649, |
| "eval_f1": 0.8785521354799841, |
| "eval_loss": 0.3098773956298828, |
| "eval_precision": 0.8876659531609425, |
| "eval_recall": 0.8705825008542543, |
| "eval_runtime": 6.3101, |
| "eval_samples_per_second": 251.503, |
| "eval_steps_per_second": 31.537, |
| "step": 2676 |
| } |
| ], |
| "logging_steps": 1782, |
| "max_steps": 44600, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "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": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
