RedCaesar/bert-sensitive-data

1{2  "best_metric": 0.09755547344684601,3  "best_model_checkpoint": "dslim/bert-base-NER-model/checkpoint-4390",4  "epoch": 2.0,5  "eval_steps": 500,6  "global_step": 4390,7  "is_hyper_param_search": false,8  "is_local_process_zero": true,9  "is_world_process_zero": true,10  "log_history": [11    {12      "epoch": 0.22779043280182232,13      "grad_norm": 1.933945894241333,14      "learning_rate": 1.7722095671981778e-05,15      "loss": 0.6767,16      "step": 50017    },18    {19      "epoch": 0.45558086560364464,20      "grad_norm": 2.780022144317627,21      "learning_rate": 1.5444191343963555e-05,22      "loss": 0.2153,23      "step": 100024    },25    {26      "epoch": 0.683371298405467,27      "grad_norm": 1.4999059438705444,28      "learning_rate": 1.3166287015945332e-05,29      "loss": 0.1472,30      "step": 150031    },32    {33      "epoch": 0.9111617312072893,34      "grad_norm": 0.7693917155265808,35      "learning_rate": 1.0888382687927108e-05,36      "loss": 0.1308,37      "step": 200038    },39    {40      "epoch": 1.0,41      "eval_accuracy": 0.9589862807506537,42      "eval_f1": 0.8543397844850693,43      "eval_loss": 0.1143401563167572,44      "eval_precision": 0.8349575605155611,45      "eval_recall": 0.8746432491767289,46      "eval_runtime": 105.1757,47      "eval_samples_per_second": 83.451,48      "eval_steps_per_second": 5.22,49      "step": 219550    },51    {52      "epoch": 1.1389521640091116,53      "grad_norm": 0.9619026184082031,54      "learning_rate": 8.610478359908885e-06,55      "loss": 0.1068,56      "step": 250057    },58    {59      "epoch": 1.366742596810934,60      "grad_norm": 0.6502276659011841,61      "learning_rate": 6.3325740318906616e-06,62      "loss": 0.1,63      "step": 300064    },65    {66      "epoch": 1.5945330296127562,67      "grad_norm": 0.8502880930900574,68      "learning_rate": 4.054669703872437e-06,69      "loss": 0.0963,70      "step": 350071    },72    {73      "epoch": 1.8223234624145785,74      "grad_norm": 1.196458101272583,75      "learning_rate": 1.7767653758542143e-06,76      "loss": 0.0965,77      "step": 400078    },79    {80      "epoch": 2.0,81      "eval_accuracy": 0.963877173871149,82      "eval_f1": 0.8823518854209665,83      "eval_loss": 0.09755547344684601,84      "eval_precision": 0.8659245429245781,85      "eval_recall": 0.8994145627515551,86      "eval_runtime": 97.9073,87      "eval_samples_per_second": 89.646,88      "eval_steps_per_second": 5.607,89      "step": 439090    }91  ],92  "logging_steps": 500,93  "max_steps": 4390,94  "num_input_tokens_seen": 0,95  "num_train_epochs": 2,96  "save_steps": 500,97  "stateful_callbacks": {98    "TrainerControl": {99      "args": {100        "should_epoch_stop": false,101        "should_evaluate": false,102        "should_log": false,103        "should_save": true,104        "should_training_stop": true105      },106      "attributes": {}107    }108  },109  "total_flos": 8407997307385200.0,110  "train_batch_size": 16,111  "trial_name": null,112  "trial_params": null113}114