| { | |
| "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": 509.4549, | |
| "eval_samples_per_second": 20.591, | |
| "eval_steps_per_second": 10.295, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000200692388741157, | |
| "grad_norm": 1.2697672843933105, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1705, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000401384777482314, | |
| "grad_norm": 0.31728145480155945, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1604, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000401384777482314, | |
| "eval_loss": 0.11879906058311462, | |
| "eval_runtime": 665.5063, | |
| "eval_samples_per_second": 15.762, | |
| "eval_steps_per_second": 7.881, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000602077166223471, | |
| "grad_norm": 0.5301271677017212, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0882, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000802769554964628, | |
| "grad_norm": 0.2863863408565521, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1379, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000802769554964628, | |
| "eval_loss": 0.0704035609960556, | |
| "eval_runtime": 387.6466, | |
| "eval_samples_per_second": 27.061, | |
| "eval_steps_per_second": 13.53, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001003461943705785, | |
| "grad_norm": 0.19120042026042938, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001204154332446942, | |
| "grad_norm": 0.5554239749908447, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0619, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001204154332446942, | |
| "eval_loss": 0.058448392897844315, | |
| "eval_runtime": 388.8644, | |
| "eval_samples_per_second": 26.976, | |
| "eval_steps_per_second": 13.488, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001404846721188099, | |
| "grad_norm": 0.6090171933174133, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0787, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001605539109929256, | |
| "grad_norm": 0.1398703008890152, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0869, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001605539109929256, | |
| "eval_loss": 0.05585380643606186, | |
| "eval_runtime": 391.5629, | |
| "eval_samples_per_second": 26.79, | |
| "eval_steps_per_second": 13.395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018062314986704128, | |
| "grad_norm": 0.08646954596042633, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1009, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00200692388741157, | |
| "grad_norm": 0.5224814414978027, | |
| "learning_rate": 0.0, | |
| "loss": 0.0612, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00200692388741157, | |
| "eval_loss": 0.05531559884548187, | |
| "eval_runtime": 392.9164, | |
| "eval_samples_per_second": 26.698, | |
| "eval_steps_per_second": 13.349, | |
| "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 | |
| } | |