trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08154943934760449,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00815494393476045,
      "eval_loss": 2.0249228477478027,
      "eval_runtime": 6.6144,
      "eval_samples_per_second": 16.63,
      "eval_steps_per_second": 16.63,
      "step": 1
    },
    {
      "epoch": 0.0163098878695209,
      "eval_loss": 2.0154640674591064,
      "eval_runtime": 6.71,
      "eval_samples_per_second": 16.394,
      "eval_steps_per_second": 16.394,
      "step": 2
    },
    {
      "epoch": 0.024464831804281346,
      "eval_loss": 1.9926271438598633,
      "eval_runtime": 6.46,
      "eval_samples_per_second": 17.028,
      "eval_steps_per_second": 17.028,
      "step": 3
    },
    {
      "epoch": 0.0326197757390418,
      "eval_loss": 1.9593819379806519,
      "eval_runtime": 6.741,
      "eval_samples_per_second": 16.318,
      "eval_steps_per_second": 16.318,
      "step": 4
    },
    {
      "epoch": 0.040774719673802244,
      "eval_loss": 1.919368863105774,
      "eval_runtime": 6.6614,
      "eval_samples_per_second": 16.513,
      "eval_steps_per_second": 16.513,
      "step": 5
    },
    {
      "epoch": 0.04892966360856269,
      "eval_loss": 1.8850003480911255,
      "eval_runtime": 6.643,
      "eval_samples_per_second": 16.559,
      "eval_steps_per_second": 16.559,
      "step": 6
    },
    {
      "epoch": 0.05708460754332314,
      "eval_loss": 1.8630123138427734,
      "eval_runtime": 6.5654,
      "eval_samples_per_second": 16.755,
      "eval_steps_per_second": 16.755,
      "step": 7
    },
    {
      "epoch": 0.0652395514780836,
      "eval_loss": 1.849714756011963,
      "eval_runtime": 6.5065,
      "eval_samples_per_second": 16.906,
      "eval_steps_per_second": 16.906,
      "step": 8
    },
    {
      "epoch": 0.07339449541284404,
      "eval_loss": 1.8416643142700195,
      "eval_runtime": 6.5223,
      "eval_samples_per_second": 16.865,
      "eval_steps_per_second": 16.865,
      "step": 9
    },
    {
      "epoch": 0.08154943934760449,
      "grad_norm": 2.23551869392395,
      "learning_rate": 0.0,
      "loss": 1.6809,
      "step": 10
    },
    {
      "epoch": 0.08154943934760449,
      "eval_loss": 1.8423653841018677,
      "eval_runtime": 6.6009,
      "eval_samples_per_second": 16.664,
      "eval_steps_per_second": 16.664,
      "step": 10
    },
    {
      "epoch": 0.08154943934760449,
      "step": 10,
      "total_flos": 124335445598208.0,
      "train_loss": 1.6808662414550781,
      "train_runtime": 116.3838,
      "train_samples_per_second": 0.687,
      "train_steps_per_second": 0.086
    }
  ],
  "logging_steps": 10,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 124335445598208.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}