coreset-selection/mix_diff_5

1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 0.5770895450610753,6  "eval_steps": 500,7  "global_step": 1500,8  "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  "logging_steps": 500,35  "max_steps": 2600,36  "num_input_tokens_seen": 0,37  "num_train_epochs": 1,38  "save_steps": 500,39  "stateful_callbacks": {40    "TrainerControl": {41      "args": {42        "should_epoch_stop": false,43        "should_evaluate": false,44        "should_log": false,45        "should_save": true,46        "should_training_stop": false47      },48      "attributes": {}49    }50  },51  "total_flos": 0.0,52  "train_batch_size": 2,53  "trial_name": null,54  "trial_params": null55}56