| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004248088360237893, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004248088360237893, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2415, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004248088360237893, | |
| "eval_loss": NaN, | |
| "eval_runtime": 77.4685, | |
| "eval_samples_per_second": 12.805, | |
| "eval_steps_per_second": 6.403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008496176720475786, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001274426508071368, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3758, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001274426508071368, | |
| "eval_loss": NaN, | |
| "eval_runtime": 76.2425, | |
| "eval_samples_per_second": 13.011, | |
| "eval_steps_per_second": 6.506, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016992353440951572, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4657, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021240441801189465, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002548853016142736, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002548853016142736, | |
| "eval_loss": NaN, | |
| "eval_runtime": 76.2886, | |
| "eval_samples_per_second": 13.003, | |
| "eval_steps_per_second": 6.502, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002973661852166525, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0033984706881903144, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0038232795242141037, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.6305, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0038232795242141037, | |
| "eval_loss": NaN, | |
| "eval_runtime": 76.165, | |
| "eval_samples_per_second": 13.024, | |
| "eval_steps_per_second": 6.512, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004248088360237893, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "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": 5256672555565056.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |