| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007002368448151581, | |
| "eval_steps": 5, | |
| "global_step": 17, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004119040263618577, | |
| "eval_loss": NaN, | |
| "eval_runtime": 214.2249, | |
| "eval_samples_per_second": 4.775, | |
| "eval_steps_per_second": 2.39, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001235712079085573, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0020595201318092883, | |
| "eval_loss": NaN, | |
| "eval_runtime": 214.3037, | |
| "eval_samples_per_second": 4.774, | |
| "eval_steps_per_second": 2.389, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002471424158171146, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.058823529411765e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037071362372567192, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010588235294117647, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004119040263618577, | |
| "eval_loss": NaN, | |
| "eval_runtime": 214.1599, | |
| "eval_samples_per_second": 4.777, | |
| "eval_steps_per_second": 2.391, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004942848316342292, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001411764705882353, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006178560395427865, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006178560395427865, | |
| "eval_loss": NaN, | |
| "eval_runtime": 214.295, | |
| "eval_samples_per_second": 4.774, | |
| "eval_steps_per_second": 2.389, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.209408939884544e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |