| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0020195492366103887, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.039098473220777e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 152.782, | |
| "eval_samples_per_second": 34.121, | |
| "eval_steps_per_second": 17.064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004039098473220777, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000525082801518701, | |
| "eval_loss": NaN, | |
| "eval_runtime": 151.3073, | |
| "eval_samples_per_second": 34.453, | |
| "eval_steps_per_second": 17.23, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008078196946441554, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001050165603037402, | |
| "eval_loss": NaN, | |
| "eval_runtime": 151.4461, | |
| "eval_samples_per_second": 34.421, | |
| "eval_steps_per_second": 17.214, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001211729541966233, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001575248404556103, | |
| "eval_loss": NaN, | |
| "eval_runtime": 151.2802, | |
| "eval_samples_per_second": 34.459, | |
| "eval_steps_per_second": 17.233, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0016156393892883109, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020195492366103887, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4206637174751232.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |