CoolFace
Modelpublic

UI-Simulator/UI_Simulator_Grow_Android_Step1

sourceHugging Facemitupdated 11mo agoView on Hugging Face
0likes11downloads
trainer_state.json141 linesDownload Raw Back to root
1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 0.9925925925925926,5  "eval_steps": 500,6  "global_step": 67,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.014814814814814815,13      "grad_norm": 0.13149102014428649,14      "learning_rate": 1.4285714285714286e-06,15      "loss": 0.0831,16      "step": 117    },18    {19      "epoch": 0.07407407407407407,20      "grad_norm": 0.0648243838618961,21      "learning_rate": 7.1428571428571436e-06,22      "loss": 0.0773,23      "step": 524    },25    {26      "epoch": 0.14814814814814814,27      "grad_norm": 0.12634669899371723,28      "learning_rate": 9.938441702975689e-06,29      "loss": 0.0692,30      "step": 1031    },32    {33      "epoch": 0.2222222222222222,34      "grad_norm": 0.11103203868763059,35      "learning_rate": 9.567727288213005e-06,36      "loss": 0.0623,37      "step": 1538    },39    {40      "epoch": 0.2962962962962963,41      "grad_norm": 0.08559439689483059,42      "learning_rate": 8.885729807284855e-06,43      "loss": 0.0589,44      "step": 2045    },46    {47      "epoch": 0.37037037037037035,48      "grad_norm": 0.05908430257437008,49      "learning_rate": 7.938926261462366e-06,50      "loss": 0.0427,51      "step": 2552    },53    {54      "epoch": 0.4444444444444444,55      "grad_norm": 0.043413213669282774,56      "learning_rate": 6.7918397477265e-06,57      "loss": 0.0427,58      "step": 3059    },60    {61      "epoch": 0.5185185185185185,62      "grad_norm": 0.04867781195090588,63      "learning_rate": 5.522642316338268e-06,64      "loss": 0.0437,65      "step": 3566    },67    {68      "epoch": 0.5925925925925926,69      "grad_norm": 0.04647862489770088,70      "learning_rate": 4.217827674798845e-06,71      "loss": 0.0428,72      "step": 4073    },74    {75      "epoch": 0.6666666666666666,76      "grad_norm": 0.03906049277069991,77      "learning_rate": 2.966316784621e-06,78      "loss": 0.0367,79      "step": 4580    },81    {82      "epoch": 0.7407407407407407,83      "grad_norm": 0.03242620502990518,84      "learning_rate": 1.8533980447508138e-06,85      "loss": 0.0318,86      "step": 5087    },88    {89      "epoch": 0.8148148148148148,90      "grad_norm": 0.03928624653755023,91      "learning_rate": 9.549150281252633e-07,92      "loss": 0.0326,93      "step": 5594    },95    {96      "epoch": 0.8888888888888888,97      "grad_norm": 0.04074437315257584,98      "learning_rate": 3.320978675139919e-07,99      "loss": 0.0339,100      "step": 60101    },102    {103      "epoch": 0.9629629629629629,104      "grad_norm": 0.04399843384947704,105      "learning_rate": 2.7390523158633552e-08,106      "loss": 0.0393,107      "step": 65108    },109    {110      "epoch": 0.9925925925925926,111      "step": 67,112      "total_flos": 1.64379520235733e+17,113      "train_loss": 0.0467690047043473,114      "train_runtime": 743.4434,115      "train_samples_per_second": 2.179,116      "train_steps_per_second": 0.09117    }118  ],119  "logging_steps": 5,120  "max_steps": 67,121  "num_input_tokens_seen": 0,122  "num_train_epochs": 1,123  "save_steps": 500,124  "stateful_callbacks": {125    "TrainerControl": {126      "args": {127        "should_epoch_stop": false,128        "should_evaluate": false,129        "should_log": false,130        "should_save": true,131        "should_training_stop": true132      },133      "attributes": {}134    }135  },136  "total_flos": 1.64379520235733e+17,137  "train_batch_size": 1,138  "trial_name": null,139  "trial_params": null140}141