trainer_state.json

{
  "best_metric": 0.6900000000000001,
  "best_model_checkpoint": "/content/drive/Shareddrives/Data Science Team folder-open/Clients/Rhenus Documents/attachments_batch7_20231027_SELECTED/0-60 EEB/model27Nov2023/checkpoint-1000",
  "epoch": 8.333333333333334,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.83,
      "eval_accuracy": 0.8110336081166772,
      "eval_f1": 0.008733624454148471,
      "eval_loss": 1.0222280025482178,
      "eval_precision": 0.09523809523809523,
      "eval_recall": 0.004576659038901602,
      "eval_runtime": 2.0715,
      "eval_samples_per_second": 10.138,
      "eval_steps_per_second": 5.31,
      "step": 100
    },
    {
      "epoch": 1.67,
      "eval_accuracy": 0.8570069752694991,
      "eval_f1": 0.1957585644371941,
      "eval_loss": 0.7151871919631958,
      "eval_precision": 0.3409090909090909,
      "eval_recall": 0.13729977116704806,
      "eval_runtime": 2.0823,
      "eval_samples_per_second": 10.085,
      "eval_steps_per_second": 5.283,
      "step": 200
    },
    {
      "epoch": 2.5,
      "eval_accuracy": 0.8877615726062144,
      "eval_f1": 0.3781388478581979,
      "eval_loss": 0.5312886238098145,
      "eval_precision": 0.5333333333333333,
      "eval_recall": 0.2929061784897025,
      "eval_runtime": 2.1019,
      "eval_samples_per_second": 9.991,
      "eval_steps_per_second": 5.233,
      "step": 300
    },
    {
      "epoch": 3.33,
      "eval_accuracy": 0.9254914394419784,
      "eval_f1": 0.5301204819277108,
      "eval_loss": 0.4247725009918213,
      "eval_precision": 0.6387096774193548,
      "eval_recall": 0.45308924485125857,
      "eval_runtime": 2.0912,
      "eval_samples_per_second": 10.042,
      "eval_steps_per_second": 5.26,
      "step": 400
    },
    {
      "epoch": 4.17,
      "learning_rate": 5e-06,
      "loss": 0.7345,
      "step": 500
    },
    {
      "epoch": 4.17,
      "eval_accuracy": 0.9337349397590361,
      "eval_f1": 0.5687331536388139,
      "eval_loss": 0.38867324590682983,
      "eval_precision": 0.6918032786885245,
      "eval_recall": 0.482837528604119,
      "eval_runtime": 2.1036,
      "eval_samples_per_second": 9.983,
      "eval_steps_per_second": 5.229,
      "step": 500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9441978440076094,
      "eval_f1": 0.6261319534282018,
      "eval_loss": 0.32258301973342896,
      "eval_precision": 0.7202380952380952,
      "eval_recall": 0.5537757437070938,
      "eval_runtime": 2.1312,
      "eval_samples_per_second": 9.853,
      "eval_steps_per_second": 5.161,
      "step": 600
    },
    {
      "epoch": 5.83,
      "eval_accuracy": 0.9461001902346227,
      "eval_f1": 0.6352040816326532,
      "eval_loss": 0.3062755763530731,
      "eval_precision": 0.7175792507204611,
      "eval_recall": 0.5697940503432495,
      "eval_runtime": 2.1053,
      "eval_samples_per_second": 9.975,
      "eval_steps_per_second": 5.225,
      "step": 700
    },
    {
      "epoch": 6.67,
      "eval_accuracy": 0.9530754597336716,
      "eval_f1": 0.6816479400749065,
      "eval_loss": 0.2806844115257263,
      "eval_precision": 0.75,
      "eval_recall": 0.6247139588100686,
      "eval_runtime": 2.0942,
      "eval_samples_per_second": 10.028,
      "eval_steps_per_second": 5.253,
      "step": 800
    },
    {
      "epoch": 7.5,
      "eval_accuracy": 0.9514901712111604,
      "eval_f1": 0.6866416978776528,
      "eval_loss": 0.2825845777988434,
      "eval_precision": 0.7554945054945055,
      "eval_recall": 0.6292906178489702,
      "eval_runtime": 2.1184,
      "eval_samples_per_second": 9.913,
      "eval_steps_per_second": 5.193,
      "step": 900
    },
    {
      "epoch": 8.33,
      "learning_rate": 0.0,
      "loss": 0.2879,
      "step": 1000
    },
    {
      "epoch": 8.33,
      "eval_accuracy": 0.9530754597336716,
      "eval_f1": 0.6900000000000001,
      "eval_loss": 0.27494579553604126,
      "eval_precision": 0.7603305785123967,
      "eval_recall": 0.631578947368421,
      "eval_runtime": 2.0941,
      "eval_samples_per_second": 10.028,
      "eval_steps_per_second": 5.253,
      "step": 1000
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 9,
  "total_flos": 528847690014720.0,
  "trial_name": null,
  "trial_params": null
}