| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006696241734326609, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.696241734326609e-05, | |
| "grad_norm": 0.027403464540839195, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.696241734326609e-05, | |
| "eval_loss": 11.901374816894531, | |
| "eval_runtime": 31.8568, | |
| "eval_samples_per_second": 197.383, | |
| "eval_steps_per_second": 98.692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013392483468653219, | |
| "grad_norm": 0.0280409324914217, | |
| "learning_rate": 4e-05, | |
| "loss": 11.8909, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00020088725202979828, | |
| "grad_norm": 0.024528177455067635, | |
| "learning_rate": 6e-05, | |
| "loss": 11.8884, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00020088725202979828, | |
| "eval_loss": 11.901350021362305, | |
| "eval_runtime": 31.7724, | |
| "eval_samples_per_second": 197.908, | |
| "eval_steps_per_second": 98.954, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00026784966937306437, | |
| "grad_norm": 0.029763467609882355, | |
| "learning_rate": 8e-05, | |
| "loss": 11.8967, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00033481208671633044, | |
| "grad_norm": 0.025384953245520592, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8964, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00040177450405959656, | |
| "grad_norm": 0.023972490802407265, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9083, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00040177450405959656, | |
| "eval_loss": 11.901265144348145, | |
| "eval_runtime": 31.8162, | |
| "eval_samples_per_second": 197.635, | |
| "eval_steps_per_second": 98.818, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004687369214028626, | |
| "grad_norm": 0.028946492820978165, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9034, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005356993387461287, | |
| "grad_norm": 0.024441702291369438, | |
| "learning_rate": 0.00016, | |
| "loss": 11.901, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006026617560893949, | |
| "grad_norm": 0.030110890045762062, | |
| "learning_rate": 0.00018, | |
| "loss": 11.8924, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006026617560893949, | |
| "eval_loss": 11.901101112365723, | |
| "eval_runtime": 31.8617, | |
| "eval_samples_per_second": 197.353, | |
| "eval_steps_per_second": 98.676, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006696241734326609, | |
| "grad_norm": 0.028159966692328453, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9059, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1979203584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |