| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00200692388741157, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.01384777482314e-05, | |
| "eval_loss": 0.1897660493850708, | |
| "eval_runtime": 388.528, | |
| "eval_samples_per_second": 26.999, | |
| "eval_steps_per_second": 13.5, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000200692388741157, | |
| "grad_norm": 1.294571876525879, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1704, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000401384777482314, | |
| "grad_norm": 0.31952470541000366, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1604, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000401384777482314, | |
| "eval_loss": 0.11903075873851776, | |
| "eval_runtime": 397.5672, | |
| "eval_samples_per_second": 26.385, | |
| "eval_steps_per_second": 13.193, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000602077166223471, | |
| "grad_norm": 0.5366002917289734, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0885, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000802769554964628, | |
| "grad_norm": 0.29305389523506165, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000802769554964628, | |
| "eval_loss": 0.07055096328258514, | |
| "eval_runtime": 390.8881, | |
| "eval_samples_per_second": 26.836, | |
| "eval_steps_per_second": 13.418, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001003461943705785, | |
| "grad_norm": 0.23707972466945648, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001204154332446942, | |
| "grad_norm": 0.4202684760093689, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0625, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001204154332446942, | |
| "eval_loss": 0.058590423315763474, | |
| "eval_runtime": 390.0396, | |
| "eval_samples_per_second": 26.895, | |
| "eval_steps_per_second": 13.447, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001404846721188099, | |
| "grad_norm": 0.6236194372177124, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0789, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001605539109929256, | |
| "grad_norm": 0.18934212625026703, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0868, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001605539109929256, | |
| "eval_loss": 0.05584266409277916, | |
| "eval_runtime": 390.0591, | |
| "eval_samples_per_second": 26.893, | |
| "eval_steps_per_second": 13.447, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018062314986704128, | |
| "grad_norm": 0.16572099924087524, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1018, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00200692388741157, | |
| "grad_norm": 0.5182934403419495, | |
| "learning_rate": 0.0, | |
| "loss": 0.0613, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00200692388741157, | |
| "eval_loss": 0.055324818938970566, | |
| "eval_runtime": 390.8541, | |
| "eval_samples_per_second": 26.839, | |
| "eval_steps_per_second": 13.419, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 712305310433280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |