| { | |
| "best_metric": 0.2145923674106598, | |
| "best_model_checkpoint": "./resultTraining5/checkpoint-126", | |
| "epoch": 10.5, | |
| "eval_steps": 18, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 728.242919921875, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 1.8847, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_Accuracy": 0.5388888888888889, | |
| "eval_Cross_Entropy_Loss": 1.7277253663296708, | |
| "eval_F1": 0.35018050541516244, | |
| "eval_Precision": 0.26944444444444443, | |
| "eval_Recall": 0.5, | |
| "eval_loss": 1.7277655601501465, | |
| "eval_runtime": 23.884, | |
| "eval_samples_per_second": 7.536, | |
| "eval_steps_per_second": 0.377, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 297.9496765136719, | |
| "learning_rate": 1.9333333333333333e-05, | |
| "loss": 1.4535, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_Accuracy": 0.5666666666666667, | |
| "eval_Cross_Entropy_Loss": 0.7339681547135115, | |
| "eval_F1": 0.5125, | |
| "eval_Precision": 0.567000567000567, | |
| "eval_Recall": 0.5440317972922618, | |
| "eval_loss": 0.734002947807312, | |
| "eval_runtime": 24.1886, | |
| "eval_samples_per_second": 7.442, | |
| "eval_steps_per_second": 0.372, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 192.5962371826172, | |
| "learning_rate": 2.9998194895940213e-05, | |
| "loss": 0.6789, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_Accuracy": 0.7666666666666667, | |
| "eval_Cross_Entropy_Loss": 0.5086390532967117, | |
| "eval_F1": 0.7664071190211346, | |
| "eval_Precision": 0.7671317446598345, | |
| "eval_Recall": 0.7687243820643399, | |
| "eval_loss": 0.5086456537246704, | |
| "eval_runtime": 22.8477, | |
| "eval_samples_per_second": 7.878, | |
| "eval_steps_per_second": 0.394, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 69.82402801513672, | |
| "learning_rate": 2.981984774215214e-05, | |
| "loss": 0.4986, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_Accuracy": 0.7944444444444444, | |
| "eval_Cross_Entropy_Loss": 0.40525681872645186, | |
| "eval_F1": 0.7941331025316065, | |
| "eval_Precision": 0.7944444444444445, | |
| "eval_Recall": 0.7962364923611973, | |
| "eval_loss": 0.4052683413028717, | |
| "eval_runtime": 23.7394, | |
| "eval_samples_per_second": 7.582, | |
| "eval_steps_per_second": 0.379, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 14.14302921295166, | |
| "learning_rate": 2.935304910939002e-05, | |
| "loss": 0.3813, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_Accuracy": 0.8888888888888888, | |
| "eval_Cross_Entropy_Loss": 0.29074438542399245, | |
| "eval_F1": 0.8872039102644442, | |
| "eval_Precision": 0.8933333333333333, | |
| "eval_Recall": 0.8847348155508632, | |
| "eval_loss": 0.29075339436531067, | |
| "eval_runtime": 24.5928, | |
| "eval_samples_per_second": 7.319, | |
| "eval_steps_per_second": 0.366, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 160.1807403564453, | |
| "learning_rate": 2.860688470206501e-05, | |
| "loss": 0.2684, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_Accuracy": 0.8944444444444445, | |
| "eval_Cross_Entropy_Loss": 0.24539544933520827, | |
| "eval_F1": 0.8920147769252629, | |
| "eval_Precision": 0.9058441558441559, | |
| "eval_Recall": 0.8881505403055521, | |
| "eval_loss": 0.2453812062740326, | |
| "eval_runtime": 23.6027, | |
| "eval_samples_per_second": 7.626, | |
| "eval_steps_per_second": 0.381, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "grad_norm": 59.56110382080078, | |
| "learning_rate": 2.7595877761616246e-05, | |
| "loss": 0.1486, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "eval_Accuracy": 0.9166666666666666, | |
| "eval_Cross_Entropy_Loss": 0.21460228119083746, | |
| "eval_F1": 0.9163542860683416, | |
| "eval_Precision": 0.9157595249876299, | |
| "eval_Recall": 0.9174636691094273, | |
| "eval_loss": 0.2145923674106598, | |
| "eval_runtime": 23.8953, | |
| "eval_samples_per_second": 7.533, | |
| "eval_steps_per_second": 0.377, | |
| "step": 126 | |
| } | |
| ], | |
| "logging_steps": 18, | |
| "max_steps": 450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 38, | |
| "save_steps": 18, | |
| "stateful_callbacks": { | |
| "CustomEarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 6.827331953465856e+16, | |
| "train_batch_size": 20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |