| { |
| "best_global_step": 432, |
| "best_metric": 0.8652564474065488, |
| "best_model_checkpoint": "ft_outputs/notebook_model_clf_nickprock/checkpoint-432", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 432, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23148148148148148, |
| "grad_norm": 3.0348520278930664, |
| "learning_rate": 9.845758354755784e-06, |
| "loss": 0.6428804779052735, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.46296296296296297, |
| "grad_norm": 5.743272304534912, |
| "learning_rate": 8.560411311053985e-06, |
| "loss": 0.42671287536621094, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6944444444444444, |
| "grad_norm": 2.8466744422912598, |
| "learning_rate": 7.275064267352185e-06, |
| "loss": 0.3608891677856445, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "grad_norm": 3.8779654502868652, |
| "learning_rate": 5.9897172236503865e-06, |
| "loss": 0.3331611251831055, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.856231884057971, |
| "eval_f1": 0.8501510574018127, |
| "eval_loss": 0.3219049274921417, |
| "eval_precision": 0.8865784499054821, |
| "eval_recall": 0.816598955310505, |
| "eval_roc_auc": 0.940147619606126, |
| "eval_runtime": 1.7687, |
| "eval_samples_per_second": 1950.607, |
| "eval_steps_per_second": 30.531, |
| "step": 216 |
| }, |
| { |
| "epoch": 1.1574074074074074, |
| "grad_norm": 8.527020454406738, |
| "learning_rate": 4.704370179948586e-06, |
| "loss": 0.2864337158203125, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.3888888888888888, |
| "grad_norm": 3.6462957859039307, |
| "learning_rate": 3.4190231362467867e-06, |
| "loss": 0.2874345016479492, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.6203703703703702, |
| "grad_norm": 4.247984409332275, |
| "learning_rate": 2.1336760925449874e-06, |
| "loss": 0.28229310989379885, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.8518518518518519, |
| "grad_norm": 4.753492832183838, |
| "learning_rate": 8.483290488431877e-07, |
| "loss": 0.2811001396179199, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8652173913043478, |
| "eval_f1": 0.8652564474065488, |
| "eval_loss": 0.30229413509368896, |
| "eval_precision": 0.8640046296296297, |
| "eval_recall": 0.8665118978525828, |
| "eval_roc_auc": 0.944837733031189, |
| "eval_runtime": 1.7539, |
| "eval_samples_per_second": 1967.004, |
| "eval_steps_per_second": 30.788, |
| "step": 432 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 432, |
| "total_flos": 1814940059873280.0, |
| "train_loss": 0.35564997019591155, |
| "train_runtime": 50.1435, |
| "train_samples_per_second": 550.261, |
| "train_steps_per_second": 8.615 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8652173913043478, |
| "eval_f1": 0.8652564474065488, |
| "eval_loss": 0.30229413509368896, |
| "eval_precision": 0.8640046296296297, |
| "eval_recall": 0.8665118978525828, |
| "eval_roc_auc": 0.944837733031189, |
| "eval_runtime": 1.7883, |
| "eval_samples_per_second": 1929.226, |
| "eval_steps_per_second": 30.197, |
| "step": 432 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 432, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1814940059873280.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
