{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004465780953444233,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004465780953444234,
      "grad_norm": 3.0460236072540283,
      "learning_rate": 2e-05,
      "loss": 10.0642,
      "step": 1
    },
    {
      "epoch": 0.0004465780953444234,
      "eval_loss": 2.1306488513946533,
      "eval_runtime": 41.9331,
      "eval_samples_per_second": 22.488,
      "eval_steps_per_second": 11.256,
      "step": 1
    },
    {
      "epoch": 0.0008931561906888468,
      "grad_norm": 0.9173904061317444,
      "learning_rate": 4e-05,
      "loss": 9.0667,
      "step": 2
    },
    {
      "epoch": 0.00133973428603327,
      "grad_norm": 1.6254750490188599,
      "learning_rate": 6e-05,
      "loss": 8.6243,
      "step": 3
    },
    {
      "epoch": 0.00133973428603327,
      "eval_loss": 2.1302742958068848,
      "eval_runtime": 41.9556,
      "eval_samples_per_second": 22.476,
      "eval_steps_per_second": 11.25,
      "step": 3
    },
    {
      "epoch": 0.0017863123813776935,
      "grad_norm": 1.7511132955551147,
      "learning_rate": 8e-05,
      "loss": 7.9792,
      "step": 4
    },
    {
      "epoch": 0.0022328904767221166,
      "grad_norm": 0.9177462458610535,
      "learning_rate": 0.0001,
      "loss": 9.5728,
      "step": 5
    },
    {
      "epoch": 0.00267946857206654,
      "grad_norm": 1.455472707748413,
      "learning_rate": 0.00012,
      "loss": 8.7651,
      "step": 6
    },
    {
      "epoch": 0.00267946857206654,
      "eval_loss": 2.127479314804077,
      "eval_runtime": 41.9906,
      "eval_samples_per_second": 22.457,
      "eval_steps_per_second": 11.241,
      "step": 6
    },
    {
      "epoch": 0.0031260466674109637,
      "grad_norm": 1.458383321762085,
      "learning_rate": 0.00014,
      "loss": 9.5776,
      "step": 7
    },
    {
      "epoch": 0.003572624762755387,
      "grad_norm": 1.346551537513733,
      "learning_rate": 0.00016,
      "loss": 9.4983,
      "step": 8
    },
    {
      "epoch": 0.00401920285809981,
      "grad_norm": 1.525188684463501,
      "learning_rate": 0.00018,
      "loss": 8.969,
      "step": 9
    },
    {
      "epoch": 0.00401920285809981,
      "eval_loss": 2.1105306148529053,
      "eval_runtime": 42.0209,
      "eval_samples_per_second": 22.441,
      "eval_steps_per_second": 11.233,
      "step": 9
    },
    {
      "epoch": 0.004465780953444233,
      "grad_norm": 2.7356202602386475,
      "learning_rate": 0.0002,
      "loss": 10.3248,
      "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": 1995217821499392.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}