{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014832668953369797,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007416334476684898,
      "grad_norm": 11.244009017944336,
      "learning_rate": 2e-05,
      "loss": 18.8184,
      "step": 1
    },
    {
      "epoch": 0.0007416334476684898,
      "eval_loss": 2.656465768814087,
      "eval_runtime": 71.0748,
      "eval_samples_per_second": 7.992,
      "eval_steps_per_second": 7.992,
      "step": 1
    },
    {
      "epoch": 0.0014832668953369797,
      "grad_norm": 13.321176528930664,
      "learning_rate": 4e-05,
      "loss": 24.6349,
      "step": 2
    },
    {
      "epoch": 0.0022249003430054697,
      "grad_norm": 10.89687728881836,
      "learning_rate": 6e-05,
      "loss": 19.4295,
      "step": 3
    },
    {
      "epoch": 0.0029665337906739594,
      "grad_norm": 11.234940528869629,
      "learning_rate": 8e-05,
      "loss": 19.7558,
      "step": 4
    },
    {
      "epoch": 0.003708167238342449,
      "grad_norm": 15.064847946166992,
      "learning_rate": 0.0001,
      "loss": 20.2215,
      "step": 5
    },
    {
      "epoch": 0.003708167238342449,
      "eval_loss": 2.5815353393554688,
      "eval_runtime": 71.1425,
      "eval_samples_per_second": 7.984,
      "eval_steps_per_second": 7.984,
      "step": 5
    },
    {
      "epoch": 0.004449800686010939,
      "grad_norm": 15.631669998168945,
      "learning_rate": 0.00012,
      "loss": 19.749,
      "step": 6
    },
    {
      "epoch": 0.005191434133679429,
      "grad_norm": 22.724105834960938,
      "learning_rate": 0.00014,
      "loss": 17.047,
      "step": 7
    },
    {
      "epoch": 0.005933067581347919,
      "grad_norm": 18.232868194580078,
      "learning_rate": 0.00016,
      "loss": 19.128,
      "step": 8
    },
    {
      "epoch": 0.006674701029016409,
      "grad_norm": 26.458662033081055,
      "learning_rate": 0.00018,
      "loss": 20.2605,
      "step": 9
    },
    {
      "epoch": 0.007416334476684898,
      "grad_norm": 28.14463996887207,
      "learning_rate": 0.0002,
      "loss": 11.6753,
      "step": 10
    },
    {
      "epoch": 0.007416334476684898,
      "eval_loss": 1.3254823684692383,
      "eval_runtime": 71.3979,
      "eval_samples_per_second": 7.955,
      "eval_steps_per_second": 7.955,
      "step": 10
    },
    {
      "epoch": 0.008157967924353388,
      "grad_norm": 24.458194732666016,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.4457,
      "step": 11
    },
    {
      "epoch": 0.008899601372021879,
      "grad_norm": 21.18819236755371,
      "learning_rate": 0.00018090169943749476,
      "loss": 6.5617,
      "step": 12
    },
    {
      "epoch": 0.009641234819690368,
      "grad_norm": 20.3893985748291,
      "learning_rate": 0.00015877852522924732,
      "loss": 3.4987,
      "step": 13
    },
    {
      "epoch": 0.010382868267358857,
      "grad_norm": 14.517038345336914,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.4438,
      "step": 14
    },
    {
      "epoch": 0.011124501715027348,
      "grad_norm": 12.411314964294434,
      "learning_rate": 0.0001,
      "loss": 2.0407,
      "step": 15
    },
    {
      "epoch": 0.011124501715027348,
      "eval_loss": 0.4047902226448059,
      "eval_runtime": 71.2049,
      "eval_samples_per_second": 7.977,
      "eval_steps_per_second": 7.977,
      "step": 15
    },
    {
      "epoch": 0.011866135162695838,
      "grad_norm": 12.487533569335938,
      "learning_rate": 6.909830056250527e-05,
      "loss": 3.643,
      "step": 16
    },
    {
      "epoch": 0.012607768610364327,
      "grad_norm": 16.057682037353516,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.3111,
      "step": 17
    },
    {
      "epoch": 0.013349402058032818,
      "grad_norm": 15.11005687713623,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.0926,
      "step": 18
    },
    {
      "epoch": 0.014091035505701307,
      "grad_norm": 14.691518783569336,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.8223,
      "step": 19
    },
    {
      "epoch": 0.014832668953369797,
      "grad_norm": 28.493478775024414,
      "learning_rate": 0.0,
      "loss": 3.0463,
      "step": 20
    },
    {
      "epoch": 0.014832668953369797,
      "eval_loss": 0.34163063764572144,
      "eval_runtime": 71.2174,
      "eval_samples_per_second": 7.976,
      "eval_steps_per_second": 7.976,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1626293057617920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}