{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013505392027767086,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7010784055534172e-05,
      "eval_loss": 1.816615343093872,
      "eval_runtime": 2386.5466,
      "eval_samples_per_second": 6.532,
      "eval_steps_per_second": 3.266,
      "step": 1
    },
    {
      "epoch": 0.00013505392027767085,
      "grad_norm": 19.457063674926758,
      "learning_rate": 5e-05,
      "loss": 7.4961,
      "step": 5
    },
    {
      "epoch": 0.0002701078405553417,
      "grad_norm": 13.092379570007324,
      "learning_rate": 0.0001,
      "loss": 7.4463,
      "step": 10
    },
    {
      "epoch": 0.0002701078405553417,
      "eval_loss": 1.6404294967651367,
      "eval_runtime": 2386.2412,
      "eval_samples_per_second": 6.533,
      "eval_steps_per_second": 3.267,
      "step": 10
    },
    {
      "epoch": 0.0004051617608330126,
      "grad_norm": 12.26793098449707,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.4121,
      "step": 15
    },
    {
      "epoch": 0.0005402156811106834,
      "grad_norm": 13.7753324508667,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.8796,
      "step": 20
    },
    {
      "epoch": 0.0005402156811106834,
      "eval_loss": 1.5440306663513184,
      "eval_runtime": 2388.2465,
      "eval_samples_per_second": 6.527,
      "eval_steps_per_second": 3.264,
      "step": 20
    },
    {
      "epoch": 0.0006752696013883543,
      "grad_norm": 11.275755882263184,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.1447,
      "step": 25
    },
    {
      "epoch": 0.0008103235216660252,
      "grad_norm": 13.648428916931152,
      "learning_rate": 5e-05,
      "loss": 6.1032,
      "step": 30
    },
    {
      "epoch": 0.0008103235216660252,
      "eval_loss": 1.5160374641418457,
      "eval_runtime": 2390.8895,
      "eval_samples_per_second": 6.52,
      "eval_steps_per_second": 3.26,
      "step": 30
    },
    {
      "epoch": 0.000945377441943696,
      "grad_norm": 10.981002807617188,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.6308,
      "step": 35
    },
    {
      "epoch": 0.0010804313622213668,
      "grad_norm": 12.902791976928711,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 6.1826,
      "step": 40
    },
    {
      "epoch": 0.0010804313622213668,
      "eval_loss": 1.5041557550430298,
      "eval_runtime": 2389.6876,
      "eval_samples_per_second": 6.523,
      "eval_steps_per_second": 3.262,
      "step": 40
    },
    {
      "epoch": 0.0012154852824990377,
      "grad_norm": 14.114043235778809,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 6.399,
      "step": 45
    },
    {
      "epoch": 0.0013505392027767086,
      "grad_norm": 9.231032371520996,
      "learning_rate": 0.0,
      "loss": 5.4045,
      "step": 50
    },
    {
      "epoch": 0.0013505392027767086,
      "eval_loss": 1.501693844795227,
      "eval_runtime": 2388.0164,
      "eval_samples_per_second": 6.528,
      "eval_steps_per_second": 3.264,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.75266978594816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}