trainer_state.json

{
  "best_metric": 1.0495396852493286,
  "best_model_checkpoint": "test_/checkpoint-1125",
  "epoch": 5.0,
  "global_step": 1875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.001,
      "loss": 1.1181,
      "step": 375
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1535536050796509,
      "eval_micro_f1": 0.6113333333333333,
      "eval_runtime": 126.2386,
      "eval_samples_per_second": 23.765,
      "eval_steps_per_second": 0.372,
      "eval_unavg_f1": [
        0.0,
        0.0,
        0.0,
        0.0,
        0.7587918907736864
      ],
      "step": 375
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.001,
      "loss": 1.0798,
      "step": 750
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0706086158752441,
      "eval_micro_f1": 0.6136666666666667,
      "eval_runtime": 122.9816,
      "eval_samples_per_second": 24.394,
      "eval_steps_per_second": 0.382,
      "eval_unavg_f1": [
        0.006644518272425249,
        0.0,
        0.028985507246376815,
        0.058577405857740586,
        0.7663512092534175
      ],
      "step": 750
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.001,
      "loss": 1.0675,
      "step": 1125
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0495396852493286,
      "eval_micro_f1": 0.624,
      "eval_runtime": 131.2327,
      "eval_samples_per_second": 22.86,
      "eval_steps_per_second": 0.358,
      "eval_unavg_f1": [
        0.1888888888888889,
        0.0,
        0.015936254980079684,
        0.1500815660685155,
        0.7806367204535543
      ],
      "step": 1125
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.001,
      "loss": 1.0589,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0587749481201172,
      "eval_micro_f1": 0.613,
      "eval_runtime": 124.3983,
      "eval_samples_per_second": 24.116,
      "eval_steps_per_second": 0.378,
      "eval_unavg_f1": [
        0.025889967637540454,
        0.0,
        0.0,
        0.21601016518424399,
        0.7831729693443723
      ],
      "step": 1500
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.001,
      "loss": 1.046,
      "step": 1875
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.053810715675354,
      "eval_micro_f1": 0.6356666666666667,
      "eval_runtime": 131.9922,
      "eval_samples_per_second": 22.729,
      "eval_steps_per_second": 0.356,
      "eval_unavg_f1": [
        0.4607046070460704,
        0.0,
        0.0,
        0.1947449768160742,
        0.801148600143575
      ],
      "step": 1875
    }
  ],
  "max_steps": 3750,
  "num_train_epochs": 10,
  "total_flos": 1.2524308467099072e+16,
  "trial_name": null,
  "trial_params": null
}