trainer_state.json

{
  "best_global_step": 870,
  "best_metric": 0.7589469053789701,
  "best_model_checkpoint": "/content/drive/MyDrive/Colab_Policy_Classifier/models/clause_classifier/checkpoint-870",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 3.4654626846313477,
      "learning_rate": 2.2241799789345004e-05,
      "loss": 1.4292,
      "step": 100
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 2.985247850418091,
      "learning_rate": 1.935325436215734e-05,
      "loss": 0.9887,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7372278508299203,
      "eval_f1": 0.7321217976470575,
      "eval_loss": 0.789239227771759,
      "eval_precision": 0.7474557284898623,
      "eval_recall": 0.7372278508299203,
      "eval_runtime": 3.3237,
      "eval_samples_per_second": 1395.735,
      "eval_steps_per_second": 21.963,
      "step": 290
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 3.3700387477874756,
      "learning_rate": 1.6464708934969675e-05,
      "loss": 0.8142,
      "step": 300
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 2.9865570068359375,
      "learning_rate": 1.3576163507782014e-05,
      "loss": 0.754,
      "step": 400
    },
    {
      "epoch": 1.7241379310344827,
      "grad_norm": 3.4569103717803955,
      "learning_rate": 1.0687618080594351e-05,
      "loss": 0.7182,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7622332399223971,
      "eval_f1": 0.756081866353382,
      "eval_loss": 0.7054521441459656,
      "eval_precision": 0.7641530421389079,
      "eval_recall": 0.7622332399223971,
      "eval_runtime": 3.3179,
      "eval_samples_per_second": 1398.193,
      "eval_steps_per_second": 22.002,
      "step": 580
    },
    {
      "epoch": 2.0689655172413794,
      "grad_norm": 3.4565210342407227,
      "learning_rate": 7.799072653406689e-06,
      "loss": 0.7063,
      "step": 600
    },
    {
      "epoch": 2.413793103448276,
      "grad_norm": 3.1291258335113525,
      "learning_rate": 4.910527226219027e-06,
      "loss": 0.6467,
      "step": 700
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 3.1852426528930664,
      "learning_rate": 2.021981799031364e-06,
      "loss": 0.6372,
      "step": 800
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7633110584177625,
      "eval_f1": 0.7589469053789701,
      "eval_loss": 0.6927562355995178,
      "eval_precision": 0.7643222340640288,
      "eval_recall": 0.7633110584177625,
      "eval_runtime": 3.3108,
      "eval_samples_per_second": 1401.186,
      "eval_steps_per_second": 22.049,
      "step": 870
    }
  ],
  "logging_steps": 100,
  "max_steps": 870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7374849755904000.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}