| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002391867649990034, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.13299397433342e-05, | |
| "eval_loss": 2.1146581172943115, | |
| "eval_runtime": 271.7079, | |
| "eval_samples_per_second": 25.27, | |
| "eval_steps_per_second": 12.635, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000306649698716671, | |
| "grad_norm": 0.4814217686653137, | |
| "learning_rate": 5e-05, | |
| "loss": 2.122, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000613299397433342, | |
| "grad_norm": 0.4163660407066345, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000613299397433342, | |
| "eval_loss": 2.0929524898529053, | |
| "eval_runtime": 270.9012, | |
| "eval_samples_per_second": 25.345, | |
| "eval_steps_per_second": 12.673, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009199490961500131, | |
| "grad_norm": 0.5417680740356445, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0991, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001226598794866684, | |
| "grad_norm": 0.5770021080970764, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.999, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001226598794866684, | |
| "eval_loss": 2.0414137840270996, | |
| "eval_runtime": 271.3537, | |
| "eval_samples_per_second": 25.303, | |
| "eval_steps_per_second": 12.651, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001533248493583355, | |
| "grad_norm": 0.49637794494628906, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0475, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018398981923000261, | |
| "grad_norm": 0.46430280804634094, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0718, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0018398981923000261, | |
| "eval_loss": 2.013228416442871, | |
| "eval_runtime": 272.1661, | |
| "eval_samples_per_second": 25.227, | |
| "eval_steps_per_second": 12.614, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002146547891016697, | |
| "grad_norm": 0.5618818402290344, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9872, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1483664532701184.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |