| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0638297872340425, | |
| "eval_steps": 50, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.1404, | |
| "eval_samples_per_second": 142.441, | |
| "eval_steps_per_second": 35.61, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.425531914893617, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5957446808510638, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9361702127659575, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.981772185245135e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.927354543565131e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1063829787234043, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.837540606713538e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1914893617021276, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7136400641330245e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5574596647341414e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3617021276595744, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3712768704277535e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4468085106382977, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1578066456019885e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5319148936170213, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.92016186682789e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6170212765957448, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.661807930109422e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.702127659574468, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.386512217606339e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7872340425531914, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0982891607188948e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.872340425531915, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8013417006383078e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9574468085106385, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1986582993616926e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9017108392811065e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2127659574468086, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.613487782393661e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3381920698905788e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.382978723404255, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.079838133172111e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.4680851063829787, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.421933543980126e-07, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.28723129572247e-07, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.6382978723404253, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4254033526585917e-07, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.723404255319149, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8635993586697555e-07, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.8085106382978724, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6245939328646322e-07, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.8936170212765955, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.264545643486997e-08, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.978723404255319, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.822781475486507e-08, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0638297872340425, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 44392513536.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |