| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011422044545973729, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001142204454597373, | |
| "grad_norm": 3.724656198755838e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001142204454597373, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 6.2068, | |
| "eval_samples_per_second": 59.451, | |
| "eval_steps_per_second": 29.806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002284408909194746, | |
| "grad_norm": 3.100448157056235e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034266133637921186, | |
| "grad_norm": 4.16081165894866e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034266133637921186, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 6.2127, | |
| "eval_samples_per_second": 59.395, | |
| "eval_steps_per_second": 29.778, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004568817818389492, | |
| "grad_norm": 4.106858978047967e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0057110222729868645, | |
| "grad_norm": 4.247162723913789e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006853226727584237, | |
| "grad_norm": 2.866815702873282e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006853226727584237, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 6.3693, | |
| "eval_samples_per_second": 57.934, | |
| "eval_steps_per_second": 29.046, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00799543118218161, | |
| "grad_norm": 3.8237645640037954e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009137635636778984, | |
| "grad_norm": 5.321361459209584e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010279840091376356, | |
| "grad_norm": 3.755135912797414e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010279840091376356, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 6.4012, | |
| "eval_samples_per_second": 57.645, | |
| "eval_steps_per_second": 28.901, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011422044545973729, | |
| "grad_norm": 5.7479541283100843e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 224132382720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |