CoolFace
Modelpublic

nluai/test_format

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes7downloads
trainer_state.json104 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 10.0,5  "eval_steps": 500,6  "global_step": 330,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 1.0,13      "grad_norm": 2.0112204551696777,14      "learning_rate": 9.769776049884563e-05,15      "loss": 1.9353,16      "step": 3317    },18    {19      "epoch": 2.0,20      "grad_norm": 1.6668552160263062,21      "learning_rate": 9.072879760251679e-05,22      "loss": 0.7608,23      "step": 6624    },25    {26      "epoch": 3.0,27      "grad_norm": 2.5093536376953125,28      "learning_rate": 7.97730162226344e-05,29      "loss": 0.4369,30      "step": 9931    },32    {33      "epoch": 4.0,34      "grad_norm": 2.4672605991363525,35      "learning_rate": 6.590284457407876e-05,36      "loss": 0.2519,37      "step": 13238    },39    {40      "epoch": 5.0,41      "grad_norm": 2.61997652053833,42      "learning_rate": 5.047599169697884e-05,43      "loss": 0.1368,44      "step": 16545    },46    {47      "epoch": 6.0,48      "grad_norm": 2.740408182144165,49      "learning_rate": 3.5002545436149474e-05,50      "loss": 0.0935,51      "step": 19852    },53    {54      "epoch": 7.0,55      "grad_norm": 1.2550326585769653,56      "learning_rate": 2.09971545214401e-05,57      "loss": 0.0549,58      "step": 23159    },60    {61      "epoch": 8.0,62      "grad_norm": 1.0139986276626587,63      "learning_rate": 9.830764196878872e-06,64      "loss": 0.0364,65      "step": 26466    },67    {68      "epoch": 9.0,69      "grad_norm": 0.5114002823829651,70      "learning_rate": 2.596418548250029e-06,71      "loss": 0.0314,72      "step": 29773    },74    {75      "epoch": 10.0,76      "grad_norm": 0.26823389530181885,77      "learning_rate": 2.265732291356626e-09,78      "loss": 0.0295,79      "step": 33080    }81  ],82  "logging_steps": 500,83  "max_steps": 330,84  "num_input_tokens_seen": 0,85  "num_train_epochs": 10,86  "save_steps": 500,87  "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": 2301871990210560.0,100  "train_batch_size": 1,101  "trial_name": null,102  "trial_params": null103}104