{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007416334476684898,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007416334476684898,
      "grad_norm": 11.880997657775879,
      "learning_rate": 2e-05,
      "loss": 18.8184,
      "step": 1
    },
    {
      "epoch": 0.0007416334476684898,
      "eval_loss": 2.656465768814087,
      "eval_runtime": 71.0471,
      "eval_samples_per_second": 7.995,
      "eval_steps_per_second": 7.995,
      "step": 1
    },
    {
      "epoch": 0.0014832668953369797,
      "grad_norm": 14.265693664550781,
      "learning_rate": 4e-05,
      "loss": 24.6349,
      "step": 2
    },
    {
      "epoch": 0.0014832668953369797,
      "eval_loss": 2.6549131870269775,
      "eval_runtime": 71.0998,
      "eval_samples_per_second": 7.989,
      "eval_steps_per_second": 7.989,
      "step": 2
    },
    {
      "epoch": 0.0022249003430054697,
      "grad_norm": 11.243473052978516,
      "learning_rate": 6e-05,
      "loss": 19.4332,
      "step": 3
    },
    {
      "epoch": 0.0022249003430054697,
      "eval_loss": 2.6460721492767334,
      "eval_runtime": 76.4226,
      "eval_samples_per_second": 7.432,
      "eval_steps_per_second": 7.432,
      "step": 3
    },
    {
      "epoch": 0.0029665337906739594,
      "grad_norm": 11.755112648010254,
      "learning_rate": 8e-05,
      "loss": 19.745,
      "step": 4
    },
    {
      "epoch": 0.0029665337906739594,
      "eval_loss": 2.624095916748047,
      "eval_runtime": 76.492,
      "eval_samples_per_second": 7.426,
      "eval_steps_per_second": 7.426,
      "step": 4
    },
    {
      "epoch": 0.003708167238342449,
      "grad_norm": 18.189170837402344,
      "learning_rate": 0.0001,
      "loss": 20.1983,
      "step": 5
    },
    {
      "epoch": 0.003708167238342449,
      "eval_loss": 2.578369140625,
      "eval_runtime": 76.4624,
      "eval_samples_per_second": 7.428,
      "eval_steps_per_second": 7.428,
      "step": 5
    },
    {
      "epoch": 0.004449800686010939,
      "grad_norm": 18.193552017211914,
      "learning_rate": 0.00012,
      "loss": 19.7283,
      "step": 6
    },
    {
      "epoch": 0.004449800686010939,
      "eval_loss": 2.484401226043701,
      "eval_runtime": 68.8084,
      "eval_samples_per_second": 8.255,
      "eval_steps_per_second": 8.255,
      "step": 6
    },
    {
      "epoch": 0.005191434133679429,
      "grad_norm": 25.999523162841797,
      "learning_rate": 0.00014,
      "loss": 16.9993,
      "step": 7
    },
    {
      "epoch": 0.005191434133679429,
      "eval_loss": 2.3075497150421143,
      "eval_runtime": 68.7893,
      "eval_samples_per_second": 8.257,
      "eval_steps_per_second": 8.257,
      "step": 7
    },
    {
      "epoch": 0.005933067581347919,
      "grad_norm": 19.375476837158203,
      "learning_rate": 0.00016,
      "loss": 19.1259,
      "step": 8
    },
    {
      "epoch": 0.005933067581347919,
      "eval_loss": 2.035842180252075,
      "eval_runtime": 68.8006,
      "eval_samples_per_second": 8.256,
      "eval_steps_per_second": 8.256,
      "step": 8
    },
    {
      "epoch": 0.006674701029016409,
      "grad_norm": 26.23119354248047,
      "learning_rate": 0.00018,
      "loss": 20.2162,
      "step": 9
    },
    {
      "epoch": 0.006674701029016409,
      "eval_loss": 1.706383466720581,
      "eval_runtime": 68.8062,
      "eval_samples_per_second": 8.255,
      "eval_steps_per_second": 8.255,
      "step": 9
    },
    {
      "epoch": 0.007416334476684898,
      "grad_norm": 27.74460220336914,
      "learning_rate": 0.0002,
      "loss": 11.843,
      "step": 10
    },
    {
      "epoch": 0.007416334476684898,
      "eval_loss": 1.3354620933532715,
      "eval_runtime": 68.7847,
      "eval_samples_per_second": 8.258,
      "eval_steps_per_second": 8.258,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "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": 813146528808960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}