| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012571500408573763, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025143000817147524, | |
| "eval_loss": 0.8700311779975891, | |
| "eval_runtime": 65.4686, | |
| "eval_samples_per_second": 25.585, | |
| "eval_steps_per_second": 12.8, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025143000817147527, | |
| "grad_norm": 0.4470396041870117, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.7746, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032685901062291783, | |
| "eval_loss": 0.7245456576347351, | |
| "eval_runtime": 65.5179, | |
| "eval_samples_per_second": 25.566, | |
| "eval_steps_per_second": 12.79, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005028600163429505, | |
| "grad_norm": 0.3252190351486206, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.7329, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0065371802124583565, | |
| "eval_loss": 0.6974729895591736, | |
| "eval_runtime": 65.5131, | |
| "eval_samples_per_second": 25.567, | |
| "eval_steps_per_second": 12.791, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007542900245144258, | |
| "grad_norm": 0.26804718375205994, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.6735, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009805770318687535, | |
| "eval_loss": 0.6861170530319214, | |
| "eval_runtime": 65.5094, | |
| "eval_samples_per_second": 25.569, | |
| "eval_steps_per_second": 12.792, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01005720032685901, | |
| "grad_norm": 0.23028379678726196, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.6795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012571500408573763, | |
| "grad_norm": 0.25149258971214294, | |
| "learning_rate": 0.0, | |
| "loss": 0.6983, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 5000973307084800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |