Rakhman16/code-synthesis-java-codet5

1{2  "best_metric": null,3  "best_model_checkpoint": null,4  "epoch": 1.6625103906899419,5  "eval_steps": 500,6  "global_step": 4000,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.20781379883624274,13      "grad_norm": 0.7872959971427917,14      "learning_rate": 1.917206982543641e-05,15      "loss": 0.7834,16      "step": 50017    },18    {19      "epoch": 0.41562759767248547,20      "grad_norm": 0.9406130313873291,21      "learning_rate": 1.834081463009144e-05,22      "loss": 0.4895,23      "step": 100024    },25    {26      "epoch": 0.6234413965087282,27      "grad_norm": 0.4806763529777527,28      "learning_rate": 1.7509559434746467e-05,29      "loss": 0.4473,30      "step": 150031    },32    {33      "epoch": 0.8312551953449709,34      "grad_norm": 0.5443118214607239,35      "learning_rate": 1.6678304239401496e-05,36      "loss": 0.4326,37      "step": 200038    },39    {40      "epoch": 1.0,41      "eval_loss": 0.33564111590385437,42      "eval_runtime": 26.4357,43      "eval_samples_per_second": 18.687,44      "eval_steps_per_second": 4.691,45      "step": 240646    },47    {48      "epoch": 1.0390689941812137,49      "grad_norm": 0.7427258491516113,50      "learning_rate": 1.5847049044056525e-05,51      "loss": 0.4225,52      "step": 250053    },54    {55      "epoch": 1.2468827930174564,56      "grad_norm": 0.4491533637046814,57      "learning_rate": 1.5015793848711555e-05,58      "loss": 0.3857,59      "step": 300060    },61    {62      "epoch": 1.4546965918536992,63      "grad_norm": 0.4072982668876648,64      "learning_rate": 1.4184538653366584e-05,65      "loss": 0.3754,66      "step": 350067    },68    {69      "epoch": 1.6625103906899419,70      "grad_norm": 0.8853089213371277,71      "learning_rate": 1.3353283458021613e-05,72      "loss": 0.3765,73      "step": 400074    }75  ],76  "logging_steps": 500,77  "max_steps": 12030,78  "num_input_tokens_seen": 0,79  "num_train_epochs": 5,80  "save_steps": 500,81  "stateful_callbacks": {82    "TrainerControl": {83      "args": {84        "should_epoch_stop": false,85        "should_evaluate": false,86        "should_log": false,87        "should_save": true,88        "should_training_stop": false89      },90      "attributes": {}91    }92  },93  "total_flos": 9742717291069440.0,94  "train_batch_size": 4,95  "trial_name": null,96  "trial_params": null97}98