| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5369127516778524, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": 0.11191753298044205, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "eval_loss": 6.9437174797058105, | |
| "eval_runtime": 17.4509, | |
| "eval_samples_per_second": 0.917, | |
| "eval_steps_per_second": 0.458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21476510067114093, | |
| "grad_norm": 0.11362311989068985, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21476510067114093, | |
| "eval_loss": 6.943667411804199, | |
| "eval_runtime": 0.1387, | |
| "eval_samples_per_second": 115.359, | |
| "eval_steps_per_second": 57.68, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3221476510067114, | |
| "grad_norm": 0.13812898099422455, | |
| "learning_rate": 3e-05, | |
| "loss": 6.9385, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.42953020134228187, | |
| "grad_norm": 0.10893705487251282, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9449, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.42953020134228187, | |
| "eval_loss": 6.943561553955078, | |
| "eval_runtime": 0.1234, | |
| "eval_samples_per_second": 129.644, | |
| "eval_steps_per_second": 64.822, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5369127516778524, | |
| "grad_norm": 0.12917304039001465, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9411, | |
| "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": 36254085120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |