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": 0.0128,6  "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": 0.00064,14      "grad_norm": 1.2594444751739502,15      "learning_rate": 3.840409643695328e-08,16      "loss": 0.7238,17      "step": 1018    },19    {20      "epoch": 0.00128,21      "grad_norm": 1.3807746171951294,22      "learning_rate": 8.10753147002347e-08,23      "loss": 0.7178,24      "step": 2025    },26    {27      "epoch": 0.00192,28      "grad_norm": 0.9590708613395691,29      "learning_rate": 1.2374653296351612e-07,30      "loss": 0.7106,31      "step": 3032    },33    {34      "epoch": 0.00256,35      "grad_norm": 1.2128362655639648,36      "learning_rate": 1.6641775122679754e-07,37      "loss": 0.72,38      "step": 4039    },40    {41      "epoch": 0.0032,42      "grad_norm": 1.0866276025772095,43      "learning_rate": 2.0908896949007894e-07,44      "loss": 0.7108,45      "step": 5046    },47    {48      "epoch": 0.00384,49      "grad_norm": 1.6984202861785889,50      "learning_rate": 2.517601877533604e-07,51      "loss": 0.7149,52      "step": 6053    },54    {55      "epoch": 0.00448,56      "grad_norm": 1.249053716659546,57      "learning_rate": 2.944314060166418e-07,58      "loss": 0.7243,59      "step": 7060    },61    {62      "epoch": 0.00512,63      "grad_norm": 1.8781795501708984,64      "learning_rate": 3.371026242799232e-07,65      "loss": 0.7138,66      "step": 8067    },68    {69      "epoch": 0.00576,70      "grad_norm": 2.162505626678467,71      "learning_rate": 3.7977384254320464e-07,72      "loss": 0.7117,73      "step": 9074    },75    {76      "epoch": 0.0064,77      "grad_norm": 1.0761003494262695,78      "learning_rate": 4.22445060806486e-07,79      "loss": 0.7121,80      "step": 10081    },82    {83      "epoch": 0.00704,84      "grad_norm": 2.104625940322876,85      "learning_rate": 4.651162790697675e-07,86      "loss": 0.7157,87      "step": 11088    },89    {90      "epoch": 0.00768,91      "grad_norm": 1.6532983779907227,92      "learning_rate": 5.077874973330489e-07,93      "loss": 0.7175,94      "step": 12095    },96    {97      "epoch": 0.00832,98      "grad_norm": 1.094260334968567,99      "learning_rate": 5.504587155963304e-07,100      "loss": 0.7142,101      "step": 130102    },103    {104      "epoch": 0.00896,105      "grad_norm": 1.7268928289413452,106      "learning_rate": 5.931299338596117e-07,107      "loss": 0.717,108      "step": 140109    },110    {111      "epoch": 0.0096,112      "grad_norm": 2.225884199142456,113      "learning_rate": 6.358011521228932e-07,114      "loss": 0.7144,115      "step": 150116    },117    {118      "epoch": 0.01024,119      "grad_norm": 1.7743901014328003,120      "learning_rate": 6.784723703861745e-07,121      "loss": 0.7127,122      "step": 160123    },124    {125      "epoch": 0.01088,126      "grad_norm": 1.1327497959136963,127      "learning_rate": 7.21143588649456e-07,128      "loss": 0.7148,129      "step": 170130    },131    {132      "epoch": 0.01152,133      "grad_norm": 1.9613993167877197,134      "learning_rate": 7.638148069127374e-07,135      "loss": 0.711,136      "step": 180137    },138    {139      "epoch": 0.01216,140      "grad_norm": 1.4991788864135742,141      "learning_rate": 8.064860251760189e-07,142      "loss": 0.713,143      "step": 190144    },145    {146      "epoch": 0.0128,147      "grad_norm": 1.3405441045761108,148      "learning_rate": 8.491572434393003e-07,149      "loss": 0.7142,150      "step": 200151    }152  ],153  "logging_steps": 10,154  "max_steps": 46875,155  "num_input_tokens_seen": 0,156  "num_train_epochs": 3,157  "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": 1683335198870400.0,180  "train_batch_size": 32,181  "trial_name": null,182  "trial_params": null183}184