| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03321339606974813, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011071132023249377, | |
| "eval_loss": NaN, | |
| "eval_runtime": 51.6799, | |
| "eval_samples_per_second": 7.372, | |
| "eval_steps_per_second": 3.696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033213396069748133, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005535566011624689, | |
| "eval_loss": NaN, | |
| "eval_runtime": 51.3409, | |
| "eval_samples_per_second": 7.421, | |
| "eval_steps_per_second": 3.72, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0066426792139496265, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00996401882092444, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011071132023249377, | |
| "eval_loss": NaN, | |
| "eval_runtime": 51.7291, | |
| "eval_samples_per_second": 7.365, | |
| "eval_steps_per_second": 3.692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013285358427899253, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016606698034874065, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016606698034874065, | |
| "eval_loss": NaN, | |
| "eval_runtime": 51.8055, | |
| "eval_samples_per_second": 7.354, | |
| "eval_steps_per_second": 3.687, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01992803764184888, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022142264046498755, | |
| "eval_loss": NaN, | |
| "eval_runtime": 51.8339, | |
| "eval_samples_per_second": 7.35, | |
| "eval_steps_per_second": 3.685, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023249377248823692, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026570716855798506, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027677830058123444, | |
| "eval_loss": NaN, | |
| "eval_runtime": 51.8322, | |
| "eval_samples_per_second": 7.351, | |
| "eval_steps_per_second": 3.685, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02989205646277332, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03321339606974813, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03321339606974813, | |
| "eval_loss": NaN, | |
| "eval_runtime": 51.8304, | |
| "eval_samples_per_second": 7.351, | |
| "eval_steps_per_second": 3.685, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": 1.964822671392768e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |