{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015654896503739782,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017394329448599757,
      "grad_norm": 938.4461669921875,
      "learning_rate": 2e-05,
      "loss": 92.7669,
      "step": 1
    },
    {
      "epoch": 0.00017394329448599757,
      "eval_loss": 31.392425537109375,
      "eval_runtime": 11.1536,
      "eval_samples_per_second": 217.059,
      "eval_steps_per_second": 108.575,
      "step": 1
    },
    {
      "epoch": 0.00034788658897199514,
      "grad_norm": 957.8446655273438,
      "learning_rate": 4e-05,
      "loss": 101.0292,
      "step": 2
    },
    {
      "epoch": 0.0005218298834579927,
      "grad_norm": 1231.523681640625,
      "learning_rate": 6e-05,
      "loss": 112.8646,
      "step": 3
    },
    {
      "epoch": 0.0005218298834579927,
      "eval_loss": 31.388347625732422,
      "eval_runtime": 10.1308,
      "eval_samples_per_second": 238.974,
      "eval_steps_per_second": 119.537,
      "step": 3
    },
    {
      "epoch": 0.0006957731779439903,
      "grad_norm": 1299.4029541015625,
      "learning_rate": 8e-05,
      "loss": 123.3738,
      "step": 4
    },
    {
      "epoch": 0.0008697164724299878,
      "grad_norm": 2047.63623046875,
      "learning_rate": 0.0001,
      "loss": 178.5324,
      "step": 5
    },
    {
      "epoch": 0.0010436597669159853,
      "grad_norm": 946.2378540039062,
      "learning_rate": 0.00012,
      "loss": 116.1072,
      "step": 6
    },
    {
      "epoch": 0.0010436597669159853,
      "eval_loss": 31.374061584472656,
      "eval_runtime": 10.4286,
      "eval_samples_per_second": 232.151,
      "eval_steps_per_second": 116.123,
      "step": 6
    },
    {
      "epoch": 0.001217603061401983,
      "grad_norm": 1098.9971923828125,
      "learning_rate": 0.00014,
      "loss": 122.798,
      "step": 7
    },
    {
      "epoch": 0.0013915463558879806,
      "grad_norm": 1105.2686767578125,
      "learning_rate": 0.00016,
      "loss": 119.0476,
      "step": 8
    },
    {
      "epoch": 0.0015654896503739782,
      "grad_norm": 1309.9188232421875,
      "learning_rate": 0.00018,
      "loss": 135.7306,
      "step": 9
    },
    {
      "epoch": 0.0015654896503739782,
      "eval_loss": 31.335914611816406,
      "eval_runtime": 10.2088,
      "eval_samples_per_second": 237.148,
      "eval_steps_per_second": 118.623,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9967478243328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}