CoolFace
Modelpublic

UI-Simulator/UI_Simulator_Grow_Android_Step2

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": 1.0,5  "eval_steps": 500,6  "global_step": 65,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.015384615384615385,13      "grad_norm": 0.04046085175171661,14      "learning_rate": 1.4285714285714286e-06,15      "loss": 0.0353,16      "step": 117    },18    {19      "epoch": 0.07692307692307693,20      "grad_norm": 0.05091567032743089,21      "learning_rate": 7.1428571428571436e-06,22      "loss": 0.0465,23      "step": 524    },25    {26      "epoch": 0.15384615384615385,27      "grad_norm": 0.05619972708251679,28      "learning_rate": 9.934132612707631e-06,29      "loss": 0.0404,30      "step": 1031    },32    {33      "epoch": 0.23076923076923078,34      "grad_norm": 0.04566156246255052,35      "learning_rate": 9.537877098354787e-06,36      "loss": 0.0407,37      "step": 1538    },39    {40      "epoch": 0.3076923076923077,41      "grad_norm": 0.04721473521715762,42      "learning_rate": 8.810810275638183e-06,43      "loss": 0.0382,44      "step": 2045    },46    {47      "epoch": 0.38461538461538464,48      "grad_norm": 0.04788500668846418,49      "learning_rate": 7.805935326811913e-06,50      "loss": 0.0355,51      "step": 2552    },53    {54      "epoch": 0.46153846153846156,55      "grad_norm": 0.0368771022335887,56      "learning_rate": 6.5965076506799e-06,57      "loss": 0.0324,58      "step": 3059    },60    {61      "epoch": 0.5384615384615384,62      "grad_norm": 0.042181867254456516,63      "learning_rate": 5.270694542927089e-06,64      "loss": 0.0377,65      "step": 3566    },67    {68      "epoch": 0.6153846153846154,69      "grad_norm": 0.03765669549965176,70      "learning_rate": 3.92514779894488e-06,71      "loss": 0.03,72      "step": 4073    },74    {75      "epoch": 0.6923076923076923,76      "grad_norm": 0.036952508227801856,77      "learning_rate": 2.65795779650105e-06,78      "loss": 0.0293,79      "step": 4580    },81    {82      "epoch": 0.7692307692307693,83      "grad_norm": 0.031901793604600534,84      "learning_rate": 1.561502705732883e-06,85      "loss": 0.0272,86      "step": 5087    },88    {89      "epoch": 0.8461538461538461,90      "grad_norm": 0.03100270332790572,91      "learning_rate": 7.157141191620548e-07,92      "loss": 0.0245,93      "step": 5594    },95    {96      "epoch": 0.9230769230769231,97      "grad_norm": 0.028704808369762864,98      "learning_rate": 1.8225003740388546e-07,99      "loss": 0.0266,100      "step": 60101    },102    {103      "epoch": 1.0,104      "grad_norm": 0.030439422147218023,105      "learning_rate": 0.0,106      "loss": 0.0257,107      "step": 65108    },109    {110      "epoch": 1.0,111      "step": 65,112      "total_flos": 1.5254199041471283e+17,113      "train_loss": 0.033259428751010164,114      "train_runtime": 698.6653,115      "train_samples_per_second": 2.233,116      "train_steps_per_second": 0.093117    }118  ],119  "logging_steps": 5,120  "max_steps": 65,121  "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": 1.5254199041471283e+17,137  "train_batch_size": 1,138  "trial_name": null,139  "trial_params": null140}141