{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012861736334405145,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042872454448017146,
      "eval_loss": 3.3277385234832764,
      "eval_runtime": 193.6833,
      "eval_samples_per_second": 5.075,
      "eval_steps_per_second": 2.54,
      "step": 1
    },
    {
      "epoch": 0.0012861736334405145,
      "grad_norm": 4.956560134887695,
      "learning_rate": 6e-05,
      "loss": 3.3191,
      "step": 3
    },
    {
      "epoch": 0.002572347266881029,
      "grad_norm": 1.7087070941925049,
      "learning_rate": 0.00012,
      "loss": 2.7794,
      "step": 6
    },
    {
      "epoch": 0.0034297963558413717,
      "eval_loss": 2.453972578048706,
      "eval_runtime": 195.598,
      "eval_samples_per_second": 5.026,
      "eval_steps_per_second": 2.515,
      "step": 8
    },
    {
      "epoch": 0.0038585209003215433,
      "grad_norm": 1.5035028457641602,
      "learning_rate": 0.00018,
      "loss": 2.5107,
      "step": 9
    },
    {
      "epoch": 0.005144694533762058,
      "grad_norm": 1.7687604427337646,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.3016,
      "step": 12
    },
    {
      "epoch": 0.006430868167202572,
      "grad_norm": 2.1629226207733154,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.3096,
      "step": 15
    },
    {
      "epoch": 0.006859592711682743,
      "eval_loss": 2.2726452350616455,
      "eval_runtime": 195.844,
      "eval_samples_per_second": 5.019,
      "eval_steps_per_second": 2.512,
      "step": 16
    },
    {
      "epoch": 0.0077170418006430866,
      "grad_norm": 1.5604491233825684,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1609,
      "step": 18
    },
    {
      "epoch": 0.0090032154340836,
      "grad_norm": 1.5848770141601562,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.2663,
      "step": 21
    },
    {
      "epoch": 0.010289389067524116,
      "grad_norm": 1.5910948514938354,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.163,
      "step": 24
    },
    {
      "epoch": 0.010289389067524116,
      "eval_loss": 2.192744016647339,
      "eval_runtime": 195.2457,
      "eval_samples_per_second": 5.035,
      "eval_steps_per_second": 2.52,
      "step": 24
    },
    {
      "epoch": 0.01157556270096463,
      "grad_norm": 1.6390970945358276,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.2368,
      "step": 27
    },
    {
      "epoch": 0.012861736334405145,
      "grad_norm": 1.5747755765914917,
      "learning_rate": 0.0,
      "loss": 2.1479,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.235418813038592e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}