| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07804878048780488, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015609756097560976, | |
| "grad_norm": 2.372922897338867, | |
| "learning_rate": 1e-05, | |
| "loss": 177.875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015609756097560976, | |
| "eval_loss": 11.116898536682129, | |
| "eval_runtime": 10.6495, | |
| "eval_samples_per_second": 10.141, | |
| "eval_steps_per_second": 5.071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03121951219512195, | |
| "grad_norm": 2.5859663486480713, | |
| "learning_rate": 2e-05, | |
| "loss": 178.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03121951219512195, | |
| "eval_loss": 11.116898536682129, | |
| "eval_runtime": 0.2085, | |
| "eval_samples_per_second": 518.024, | |
| "eval_steps_per_second": 259.012, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04682926829268293, | |
| "grad_norm": 2.388425588607788, | |
| "learning_rate": 3e-05, | |
| "loss": 178.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0624390243902439, | |
| "grad_norm": 2.5343129634857178, | |
| "learning_rate": 4e-05, | |
| "loss": 177.9375, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0624390243902439, | |
| "eval_loss": 11.115740776062012, | |
| "eval_runtime": 0.2282, | |
| "eval_samples_per_second": 473.198, | |
| "eval_steps_per_second": 236.599, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 2.585353374481201, | |
| "learning_rate": 5e-05, | |
| "loss": 178.0, | |
| "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": 221830447104.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |