{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015239256324291375,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015239256324291374,
      "grad_norm": 0.17576512694358826,
      "learning_rate": 2e-05,
      "loss": 1.6018,
      "step": 1
    },
    {
      "epoch": 0.00015239256324291374,
      "eval_loss": 1.921917200088501,
      "eval_runtime": 85.1847,
      "eval_samples_per_second": 32.435,
      "eval_steps_per_second": 16.224,
      "step": 1
    },
    {
      "epoch": 0.00030478512648582747,
      "grad_norm": 0.1938357651233673,
      "learning_rate": 4e-05,
      "loss": 1.6758,
      "step": 2
    },
    {
      "epoch": 0.00045717768972874126,
      "grad_norm": 0.21932876110076904,
      "learning_rate": 6e-05,
      "loss": 1.3734,
      "step": 3
    },
    {
      "epoch": 0.00045717768972874126,
      "eval_loss": 1.9207637310028076,
      "eval_runtime": 83.1671,
      "eval_samples_per_second": 33.222,
      "eval_steps_per_second": 16.617,
      "step": 3
    },
    {
      "epoch": 0.0006095702529716549,
      "grad_norm": 0.2311554253101349,
      "learning_rate": 8e-05,
      "loss": 1.1501,
      "step": 4
    },
    {
      "epoch": 0.0007619628162145687,
      "grad_norm": 0.18470384180545807,
      "learning_rate": 0.0001,
      "loss": 0.8366,
      "step": 5
    },
    {
      "epoch": 0.0009143553794574825,
      "grad_norm": 0.2916955351829529,
      "learning_rate": 0.00012,
      "loss": 0.6837,
      "step": 6
    },
    {
      "epoch": 0.0009143553794574825,
      "eval_loss": 1.8857704401016235,
      "eval_runtime": 83.314,
      "eval_samples_per_second": 33.164,
      "eval_steps_per_second": 16.588,
      "step": 6
    },
    {
      "epoch": 0.0010667479427003963,
      "grad_norm": 0.28477999567985535,
      "learning_rate": 0.00014,
      "loss": 2.2671,
      "step": 7
    },
    {
      "epoch": 0.0012191405059433099,
      "grad_norm": 0.2434885948896408,
      "learning_rate": 0.00016,
      "loss": 1.5582,
      "step": 8
    },
    {
      "epoch": 0.0013715330691862237,
      "grad_norm": 0.534342885017395,
      "learning_rate": 0.00018,
      "loss": 1.6292,
      "step": 9
    },
    {
      "epoch": 0.0013715330691862237,
      "eval_loss": 1.8226882219314575,
      "eval_runtime": 83.277,
      "eval_samples_per_second": 33.178,
      "eval_steps_per_second": 16.595,
      "step": 9
    },
    {
      "epoch": 0.0015239256324291375,
      "grad_norm": 0.47443780303001404,
      "learning_rate": 0.0002,
      "loss": 1.0188,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1916899650699264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}