| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021324234993069624, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00042648469986139245, | |
| "eval_loss": 1.3328465223312378, | |
| "eval_runtime": 67.3762, | |
| "eval_samples_per_second": 14.664, | |
| "eval_steps_per_second": 7.332, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021324234993069626, | |
| "grad_norm": 1.4511975049972534, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1739, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004264846998613925, | |
| "grad_norm": 2.1678805351257324, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1261, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004264846998613925, | |
| "eval_loss": 0.9592291712760925, | |
| "eval_runtime": 67.5258, | |
| "eval_samples_per_second": 14.631, | |
| "eval_steps_per_second": 7.316, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006397270497920887, | |
| "grad_norm": 2.1636769771575928, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6585, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00852969399722785, | |
| "grad_norm": 1.5922648906707764, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00852969399722785, | |
| "eval_loss": 0.4851472079753876, | |
| "eval_runtime": 67.794, | |
| "eval_samples_per_second": 14.574, | |
| "eval_steps_per_second": 7.287, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010662117496534812, | |
| "grad_norm": 2.100919485092163, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012794540995841774, | |
| "grad_norm": 1.2140564918518066, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3204, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012794540995841774, | |
| "eval_loss": 0.38778889179229736, | |
| "eval_runtime": 67.44, | |
| "eval_samples_per_second": 14.65, | |
| "eval_steps_per_second": 7.325, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014926964495148737, | |
| "grad_norm": 3.0732266902923584, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0170593879944557, | |
| "grad_norm": 4.373198986053467, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3335, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0170593879944557, | |
| "eval_loss": 0.35587215423583984, | |
| "eval_runtime": 67.6937, | |
| "eval_samples_per_second": 14.595, | |
| "eval_steps_per_second": 7.298, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019191811493762662, | |
| "grad_norm": 1.7283074855804443, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4505, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021324234993069624, | |
| "grad_norm": 1.1647988557815552, | |
| "learning_rate": 0.0, | |
| "loss": 0.4512, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021324234993069624, | |
| "eval_loss": 0.3501424491405487, | |
| "eval_runtime": 68.0406, | |
| "eval_samples_per_second": 14.521, | |
| "eval_steps_per_second": 7.26, | |
| "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": 9294060346933248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |