vdpappu/lora_scienceqa

1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 5.882352941176471,5  "eval_steps": 500,6  "global_step": 300,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.5882352941176471,13      "grad_norm": 0.39919430017471313,14      "learning_rate": 2.5e-05,15      "loss": 1.4153,16      "step": 3017    },18    {19      "epoch": 1.1764705882352942,20      "grad_norm": 0.6906107664108276,21      "learning_rate": 5e-05,22      "loss": 1.3019,23      "step": 6024    },25    {26      "epoch": 1.7647058823529411,27      "grad_norm": 0.7136546969413757,28      "learning_rate": 4.8096988312782174e-05,29      "loss": 1.0532,30      "step": 9031    },32    {33      "epoch": 2.3529411764705883,34      "grad_norm": 0.979485034942627,35      "learning_rate": 4.267766952966369e-05,36      "loss": 0.7964,37      "step": 12038    },39    {40      "epoch": 2.9411764705882355,41      "grad_norm": 1.1987406015396118,42      "learning_rate": 3.456708580912725e-05,43      "loss": 0.5561,44      "step": 15045    },46    {47      "epoch": 3.5294117647058822,48      "grad_norm": 1.4430248737335205,49      "learning_rate": 2.5e-05,50      "loss": 0.3678,51      "step": 18052    },53    {54      "epoch": 4.117647058823529,55      "grad_norm": 1.415720820426941,56      "learning_rate": 1.5432914190872757e-05,57      "loss": 0.3576,58      "step": 21059    },60    {61      "epoch": 4.705882352941177,62      "grad_norm": 0.9879446625709534,63      "learning_rate": 7.3223304703363135e-06,64      "loss": 0.3174,65      "step": 24066    },67    {68      "epoch": 5.294117647058823,69      "grad_norm": 1.1644922494888306,70      "learning_rate": 1.9030116872178316e-06,71      "loss": 0.2657,72      "step": 27073    },74    {75      "epoch": 5.882352941176471,76      "grad_norm": 1.1767199039459229,77      "learning_rate": 0.0,78      "loss": 0.2573,79      "step": 30080    }81  ],82  "logging_steps": 30,83  "max_steps": 300,84  "num_input_tokens_seen": 0,85  "num_train_epochs": 6,86  "save_steps": 50,87  "stateful_callbacks": {88    "TrainerControl": {89      "args": {90        "should_epoch_stop": false,91        "should_evaluate": false,92        "should_log": false,93        "should_save": true,94        "should_training_stop": true95      },96      "attributes": {}97    }98  },99  "total_flos": 1.1298211097321472e+16,100  "train_batch_size": 8,101  "trial_name": null,102  "trial_params": null103}104