coreset-selection/mix_diff_5

1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 0.9618159084351255,6  "eval_steps": 500,7  "global_step": 2500,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.1923631816870251,14      "grad_norm": 70.2215347290039,15      "learning_rate": 8.080769230769231e-06,16      "loss": -100.6029,17      "step": 50018    },19    {20      "epoch": 0.3847263633740502,21      "grad_norm": 1890.31591796875,22      "learning_rate": 6.157692307692308e-06,23      "loss": -151.516,24      "step": 100025    },26    {27      "epoch": 0.5770895450610753,28      "grad_norm": 258.2842102050781,29      "learning_rate": 4.234615384615385e-06,30      "loss": -154.422,31      "step": 150032    },33    {34      "epoch": 0.7694527267481004,35      "grad_norm": 101.9043197631836,36      "learning_rate": 2.3115384615384617e-06,37      "loss": -157.1482,38      "step": 200039    },40    {41      "epoch": 0.9618159084351255,42      "grad_norm": 66.6363754272461,43      "learning_rate": 3.8846153846153845e-07,44      "loss": -158.2865,45      "step": 250046    }47  ],48  "logging_steps": 500,49  "max_steps": 2600,50  "num_input_tokens_seen": 0,51  "num_train_epochs": 1,52  "save_steps": 500,53  "stateful_callbacks": {54    "TrainerControl": {55      "args": {56        "should_epoch_stop": false,57        "should_evaluate": false,58        "should_log": false,59        "should_save": true,60        "should_training_stop": false61      },62      "attributes": {}63    }64  },65  "total_flos": 0.0,66  "train_batch_size": 2,67  "trial_name": null,68  "trial_params": null69}70