trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 17.810282459441467,
      "learning_rate": 1e-05,
      "loss": 1.1097,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1095243692398071,
      "eval_runtime": 2.8023,
      "eval_samples_per_second": 17.843,
      "eval_steps_per_second": 0.357,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.2839607000350952,
      "eval_runtime": 2.6692,
      "eval_samples_per_second": 18.732,
      "eval_steps_per_second": 0.375,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0814800262451172,
      "eval_runtime": 2.6746,
      "eval_samples_per_second": 18.695,
      "eval_steps_per_second": 0.374,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.874021053314209,
      "eval_runtime": 2.6724,
      "eval_samples_per_second": 18.71,
      "eval_steps_per_second": 0.374,
      "step": 4
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.20399999295951,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 1.0878,
      "step": 5
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7459021210670471,
      "eval_runtime": 2.6898,
      "eval_samples_per_second": 18.589,
      "eval_steps_per_second": 0.372,
      "step": 5
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6033510565757751,
      "eval_runtime": 2.6879,
      "eval_samples_per_second": 18.602,
      "eval_steps_per_second": 0.372,
      "step": 6
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.5201848745346069,
      "eval_runtime": 2.6772,
      "eval_samples_per_second": 18.676,
      "eval_steps_per_second": 0.374,
      "step": 7
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.4572071433067322,
      "eval_runtime": 2.6696,
      "eval_samples_per_second": 18.73,
      "eval_steps_per_second": 0.375,
      "step": 8
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.4221082031726837,
      "eval_runtime": 2.677,
      "eval_samples_per_second": 18.677,
      "eval_steps_per_second": 0.374,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.0214434738231213,
      "learning_rate": 0.0,
      "loss": 0.5493,
      "step": 10
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.41154685616493225,
      "eval_runtime": 2.6558,
      "eval_samples_per_second": 18.827,
      "eval_steps_per_second": 0.377,
      "step": 10
    },
    {
      "epoch": 10.0,
      "step": 10,
      "total_flos": 8375186227200.0,
      "train_loss": 0.8207268595695496,
      "train_runtime": 309.7037,
      "train_samples_per_second": 1.614,
      "train_steps_per_second": 0.032
    }
  ],
  "logging_steps": 5,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8375186227200.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}