| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.01067615658363, | |
| "eval_steps": 50, | |
| "global_step": 71, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014234875444839857, | |
| "eval_loss": 11.935325622558594, | |
| "eval_runtime": 3.1175, | |
| "eval_samples_per_second": 38.172, | |
| "eval_steps_per_second": 9.623, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1423487544483986, | |
| "grad_norm": 0.2997051775455475, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2846975088967972, | |
| "grad_norm": 0.25467944145202637, | |
| "learning_rate": 9.351426205150777e-05, | |
| "loss": 11.9323, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42704626334519574, | |
| "grad_norm": 0.4586544632911682, | |
| "learning_rate": 7.573964007549155e-05, | |
| "loss": 11.9242, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5693950177935944, | |
| "grad_norm": 0.3594238758087158, | |
| "learning_rate": 5.128739568274944e-05, | |
| "loss": 11.9164, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7117437722419929, | |
| "grad_norm": 0.7964053153991699, | |
| "learning_rate": 2.650116284863402e-05, | |
| "loss": 11.9088, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7117437722419929, | |
| "eval_loss": 11.90546703338623, | |
| "eval_runtime": 3.0895, | |
| "eval_samples_per_second": 38.517, | |
| "eval_steps_per_second": 9.71, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8540925266903915, | |
| "grad_norm": 0.3602689802646637, | |
| "learning_rate": 7.81122200884072e-06, | |
| "loss": 11.9098, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99644128113879, | |
| "grad_norm": 0.5998196601867676, | |
| "learning_rate": 6.629550575847354e-08, | |
| "loss": 11.901, | |
| "step": 70 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 71, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 73952160251904.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |