trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.444444444444445,
  "eval_steps": 1,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 1.6399296522140503,
      "eval_runtime": 32.6957,
      "eval_samples_per_second": 1.285,
      "eval_steps_per_second": 0.642,
      "step": 1
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 1.6294206380844116,
      "eval_runtime": 33.1948,
      "eval_samples_per_second": 1.265,
      "eval_steps_per_second": 0.633,
      "step": 2
    },
    {
      "epoch": 1.2222222222222223,
      "eval_loss": 1.5771300792694092,
      "eval_runtime": 33.2928,
      "eval_samples_per_second": 1.262,
      "eval_steps_per_second": 0.631,
      "step": 3
    },
    {
      "epoch": 1.6666666666666665,
      "eval_loss": 1.4016178846359253,
      "eval_runtime": 33.3433,
      "eval_samples_per_second": 1.26,
      "eval_steps_per_second": 0.63,
      "step": 4
    },
    {
      "epoch": 2.111111111111111,
      "eval_loss": 1.0657567977905273,
      "eval_runtime": 33.3475,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 5
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 1.2109375,
      "learning_rate": 0.00012,
      "loss": 1.2932,
      "step": 6
    },
    {
      "epoch": 2.4444444444444446,
      "eval_loss": 0.7291149497032166,
      "eval_runtime": 33.3499,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 6
    },
    {
      "epoch": 2.888888888888889,
      "eval_loss": 0.46378064155578613,
      "eval_runtime": 33.3669,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 7
    },
    {
      "epoch": 3.2222222222222223,
      "eval_loss": 0.34250253438949585,
      "eval_runtime": 33.3609,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 8
    },
    {
      "epoch": 3.6666666666666665,
      "eval_loss": 0.3101094663143158,
      "eval_runtime": 33.3668,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 9
    },
    {
      "epoch": 4.111111111111111,
      "eval_loss": 0.25341325998306274,
      "eval_runtime": 33.3681,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.629,
      "step": 10
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 0.20539742708206177,
      "eval_runtime": 33.3531,
      "eval_samples_per_second": 1.259,
      "eval_steps_per_second": 0.63,
      "step": 11
    }
  ],
  "logging_steps": 6,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.52759145644032e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}