Team Ai
Modelpublic

dzungpham/graphcodebert-code-classification

sourceHugging Facemitupdated 5mo agoView on Hugging Face
0likes
trainer_state.json184 linesDownload Raw Back to checkpoint-200
1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 0.02559836170485089,6  "eval_steps": 1000,7  "global_step": 200,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.0012799180852425445,14      "grad_norm": 89788.1796875,15      "learning_rate": 2.304147465437788e-08,16      "loss": 0.7088,17      "step": 1018    },19    {20      "epoch": 0.002559836170485089,21      "grad_norm": 39479.36328125,22      "learning_rate": 4.86431131592422e-08,23      "loss": 0.7087,24      "step": 2025    },26    {27      "epoch": 0.0038397542557276334,28      "grad_norm": 82478.765625,29      "learning_rate": 7.424475166410652e-08,30      "loss": 0.7074,31      "step": 3032    },33    {34      "epoch": 0.005119672340970178,35      "grad_norm": 58003.75390625,36      "learning_rate": 9.984639016897082e-08,37      "loss": 0.703,38      "step": 4039    },40    {41      "epoch": 0.006399590426212722,42      "grad_norm": 95491.0859375,43      "learning_rate": 1.2544802867383514e-07,44      "loss": 0.7073,45      "step": 5046    },47    {48      "epoch": 0.007679508511455267,49      "grad_norm": 44903.296875,50      "learning_rate": 1.5104966717869944e-07,51      "loss": 0.7061,52      "step": 6053    },54    {55      "epoch": 0.008959426596697812,56      "grad_norm": 142410.484375,57      "learning_rate": 1.7665130568356375e-07,58      "loss": 0.7082,59      "step": 7060    },61    {62      "epoch": 0.010239344681940356,63      "grad_norm": 148763.109375,64      "learning_rate": 2.0225294418842808e-07,65      "loss": 0.707,66      "step": 8067    },68    {69      "epoch": 0.011519262767182901,70      "grad_norm": 62031.30859375,71      "learning_rate": 2.2785458269329238e-07,72      "loss": 0.7036,73      "step": 9074    },75    {76      "epoch": 0.012799180852425445,77      "grad_norm": 135708.875,78      "learning_rate": 2.5345622119815674e-07,79      "loss": 0.7078,80      "step": 10081    },82    {83      "epoch": 0.01407909893766799,84      "grad_norm": 91129.421875,85      "learning_rate": 2.79057859703021e-07,86      "loss": 0.7035,87      "step": 11088    },89    {90      "epoch": 0.015359017022910534,91      "grad_norm": 39290.72265625,92      "learning_rate": 3.0465949820788535e-07,93      "loss": 0.7083,94      "step": 12095    },96    {97      "epoch": 0.016638935108153077,98      "grad_norm": 49473.61328125,99      "learning_rate": 3.302611367127496e-07,100      "loss": 0.7023,101      "step": 130102    },103    {104      "epoch": 0.017918853193395624,105      "grad_norm": 61292.984375,106      "learning_rate": 3.5586277521761395e-07,107      "loss": 0.7014,108      "step": 140109    },110    {111      "epoch": 0.019198771278638168,112      "grad_norm": 79102.0390625,113      "learning_rate": 3.814644137224783e-07,114      "loss": 0.7041,115      "step": 150116    },117    {118      "epoch": 0.02047868936388071,119      "grad_norm": 61779.62890625,120      "learning_rate": 4.0706605222734256e-07,121      "loss": 0.7039,122      "step": 160123    },124    {125      "epoch": 0.021758607449123255,126      "grad_norm": 63492.18359375,127      "learning_rate": 4.326676907322069e-07,128      "loss": 0.7035,129      "step": 170130    },131    {132      "epoch": 0.023038525534365802,133      "grad_norm": 44190.3203125,134      "learning_rate": 4.582693292370712e-07,135      "loss": 0.7019,136      "step": 180137    },138    {139      "epoch": 0.024318443619608346,140      "grad_norm": 67509.15625,141      "learning_rate": 4.838709677419355e-07,142      "loss": 0.6991,143      "step": 190144    },145    {146      "epoch": 0.02559836170485089,147      "grad_norm": 94820.5078125,148      "learning_rate": 5.094726062467999e-07,149      "loss": 0.7011,150      "step": 200151    }152  ],153  "logging_steps": 10,154  "max_steps": 39065,155  "num_input_tokens_seen": 0,156  "num_train_epochs": 5,157  "save_steps": 200,158  "stateful_callbacks": {159    "EarlyStoppingCallback": {160      "args": {161        "early_stopping_patience": 3,162        "early_stopping_threshold": 0.0163      },164      "attributes": {165        "early_stopping_patience_counter": 0166      }167    },168    "TrainerControl": {169      "args": {170        "should_epoch_stop": false,171        "should_evaluate": false,172        "should_log": false,173        "should_save": true,174        "should_training_stop": false175      },176      "attributes": {}177    }178  },179  "total_flos": 3367821508608000.0,180  "train_batch_size": 64,181  "trial_name": null,182  "trial_params": null183}184