CoolFace
Modelpublic

en1ak/ygo-lua-coder

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes
trainer_state.json174 linesDownload Raw Back to checkpoint-2000
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 2.4984384759525295,5  "eval_steps": 500,6  "global_step": 2000,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.12492192379762648,13      "grad_norm": 0.27754032611846924,14      "learning_rate": 2e-05,15      "loss": 0.1442,16      "step": 10017    },18    {19      "epoch": 0.24984384759525297,20      "grad_norm": 0.2751781642436981,21      "learning_rate": 2e-05,22      "loss": 0.088,23      "step": 20024    },25    {26      "epoch": 0.3747657713928795,27      "grad_norm": 0.23674216866493225,28      "learning_rate": 2e-05,29      "loss": 0.0738,30      "step": 30031    },32    {33      "epoch": 0.49968769519050593,34      "grad_norm": 0.23040202260017395,35      "learning_rate": 2e-05,36      "loss": 0.0643,37      "step": 40038    },39    {40      "epoch": 0.6246096189881324,41      "grad_norm": 0.26208606362342834,42      "learning_rate": 2e-05,43      "loss": 0.0584,44      "step": 50045    },46    {47      "epoch": 0.749531542785759,48      "grad_norm": 0.2172231376171112,49      "learning_rate": 2e-05,50      "loss": 0.0534,51      "step": 60052    },53    {54      "epoch": 0.8744534665833854,55      "grad_norm": 0.21661953628063202,56      "learning_rate": 2e-05,57      "loss": 0.0502,58      "step": 70059    },60    {61      "epoch": 0.9993753903810119,62      "grad_norm": 0.186213880777359,63      "learning_rate": 2e-05,64      "loss": 0.0471,65      "step": 80066    },67    {68      "epoch": 1.1242973141786383,69      "grad_norm": 0.2086647003889084,70      "learning_rate": 2e-05,71      "loss": 0.0373,72      "step": 90073    },74    {75      "epoch": 1.2492192379762648,76      "grad_norm": 0.1900208592414856,77      "learning_rate": 2e-05,78      "loss": 0.0351,79      "step": 100080    },81    {82      "epoch": 1.3741411617738915,83      "grad_norm": 0.21206732094287872,84      "learning_rate": 2e-05,85      "loss": 0.0349,86      "step": 110087    },88    {89      "epoch": 1.499063085571518,90      "grad_norm": 0.20564615726470947,91      "learning_rate": 2e-05,92      "loss": 0.0332,93      "step": 120094    },95    {96      "epoch": 1.6239850093691444,97      "grad_norm": 0.2596442997455597,98      "learning_rate": 2e-05,99      "loss": 0.0313,100      "step": 1300101    },102    {103      "epoch": 1.7489069331667708,104      "grad_norm": 0.18866442143917084,105      "learning_rate": 2e-05,106      "loss": 0.0309,107      "step": 1400108    },109    {110      "epoch": 1.8738288569643973,111      "grad_norm": 0.19815115630626678,112      "learning_rate": 2e-05,113      "loss": 0.0298,114      "step": 1500115    },116    {117      "epoch": 1.9987507807620237,118      "grad_norm": 0.21096043288707733,119      "learning_rate": 2e-05,120      "loss": 0.0281,121      "step": 1600122    },123    {124      "epoch": 2.12367270455965,125      "grad_norm": 0.1663718819618225,126      "learning_rate": 2e-05,127      "loss": 0.0191,128      "step": 1700129    },130    {131      "epoch": 2.2485946283572766,132      "grad_norm": 0.1737908571958542,133      "learning_rate": 2e-05,134      "loss": 0.0191,135      "step": 1800136    },137    {138      "epoch": 2.373516552154903,139      "grad_norm": 0.21257372200489044,140      "learning_rate": 2e-05,141      "loss": 0.0191,142      "step": 1900143    },144    {145      "epoch": 2.4984384759525295,146      "grad_norm": 0.21343937516212463,147      "learning_rate": 2e-05,148      "loss": 0.0185,149      "step": 2000150    }151  ],152  "logging_steps": 100,153  "max_steps": 2400,154  "num_input_tokens_seen": 0,155  "num_train_epochs": 3,156  "save_steps": 1000,157  "stateful_callbacks": {158    "TrainerControl": {159      "args": {160        "should_epoch_stop": false,161        "should_evaluate": false,162        "should_log": false,163        "should_save": true,164        "should_training_stop": false165      },166      "attributes": {}167    }168  },169  "total_flos": 94237318184960.0,170  "train_batch_size": 8,171  "trial_name": null,172  "trial_params": null173}174