| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010748065348237317, | |
| "eval_steps": 7, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004299226139294927, | |
| "eval_loss": NaN, | |
| "eval_runtime": 37.904, | |
| "eval_samples_per_second": 25.855, | |
| "eval_steps_per_second": 12.927, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012897678417884782, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025795356835769563, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0030094582975064487, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.097, | |
| "eval_samples_per_second": 27.149, | |
| "eval_steps_per_second": 13.575, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003869303525365434, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005159071367153913, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0060189165950128975, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.6499, | |
| "eval_samples_per_second": 27.49, | |
| "eval_steps_per_second": 13.745, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006448839208942391, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007738607050730868, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009028374892519347, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009028374892519347, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.6565, | |
| "eval_samples_per_second": 27.485, | |
| "eval_steps_per_second": 13.742, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010318142734307825, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 425104626155520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |