| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012649821321273837, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025299642642547676, | |
| "grad_norm": 9.439708709716797, | |
| "learning_rate": 1e-05, | |
| "loss": 8.1032, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025299642642547676, | |
| "eval_loss": 9.136134147644043, | |
| "eval_runtime": 740.2114, | |
| "eval_samples_per_second": 8.995, | |
| "eval_steps_per_second": 4.497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005059928528509535, | |
| "grad_norm": 8.242989540100098, | |
| "learning_rate": 2e-05, | |
| "loss": 9.1475, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005059928528509535, | |
| "eval_loss": 9.0488920211792, | |
| "eval_runtime": 711.3234, | |
| "eval_samples_per_second": 9.36, | |
| "eval_steps_per_second": 4.68, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007589892792764302, | |
| "grad_norm": 9.145167350769043, | |
| "learning_rate": 3e-05, | |
| "loss": 8.3588, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001011985705701907, | |
| "grad_norm": 9.1289701461792, | |
| "learning_rate": 4e-05, | |
| "loss": 8.948, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001011985705701907, | |
| "eval_loss": 8.780791282653809, | |
| "eval_runtime": 742.2713, | |
| "eval_samples_per_second": 8.97, | |
| "eval_steps_per_second": 4.485, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012649821321273837, | |
| "grad_norm": 10.919492721557617, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1054, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3822182832537600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |