{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7976071784646062,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03988035892323031,
      "grad_norm": 16.628543853759766,
      "learning_rate": 0.00012,
      "loss": 2.1274,
      "step": 10
    },
    {
      "epoch": 0.07976071784646062,
      "grad_norm": 12.371907234191895,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.7722,
      "step": 20
    },
    {
      "epoch": 0.11964107676969092,
      "grad_norm": 9.106270790100098,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.4456,
      "step": 30
    },
    {
      "epoch": 0.15952143569292124,
      "grad_norm": 5.712669372558594,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.3662,
      "step": 40
    },
    {
      "epoch": 0.19940179461615154,
      "grad_norm": 2.922630548477173,
      "learning_rate": 0.00018280088311480201,
      "loss": 0.2983,
      "step": 50
    },
    {
      "epoch": 0.23928215353938184,
      "grad_norm": 5.451596260070801,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.3034,
      "step": 60
    },
    {
      "epoch": 0.27916251246261214,
      "grad_norm": 3.604940414428711,
      "learning_rate": 0.00016010811472830252,
      "loss": 0.2754,
      "step": 70
    },
    {
      "epoch": 0.3190428713858425,
      "grad_norm": 2.805121660232544,
      "learning_rate": 0.0001461341162978688,
      "loss": 0.2659,
      "step": 80
    },
    {
      "epoch": 0.3589232303090728,
      "grad_norm": 3.4018733501434326,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.2767,
      "step": 90
    },
    {
      "epoch": 0.3988035892323031,
      "grad_norm": 3.0557034015655518,
      "learning_rate": 0.0001148263647711842,
      "loss": 0.286,
      "step": 100
    },
    {
      "epoch": 0.4386839481555334,
      "grad_norm": 4.8394036293029785,
      "learning_rate": 9.834660552336415e-05,
      "loss": 0.2604,
      "step": 110
    },
    {
      "epoch": 0.4785643070787637,
      "grad_norm": 6.2420759201049805,
      "learning_rate": 8.191194656678904e-05,
      "loss": 0.2447,
      "step": 120
    },
    {
      "epoch": 0.518444666001994,
      "grad_norm": 3.427865505218506,
      "learning_rate": 6.59706825558357e-05,
      "loss": 0.282,
      "step": 130
    },
    {
      "epoch": 0.5583250249252243,
      "grad_norm": 5.478673934936523,
      "learning_rate": 5.095764961694922e-05,
      "loss": 0.2314,
      "step": 140
    },
    {
      "epoch": 0.5982053838484547,
      "grad_norm": 1.9072978496551514,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 0.2284,
      "step": 150
    },
    {
      "epoch": 0.638085742771685,
      "grad_norm": 2.6893632411956787,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 0.2232,
      "step": 160
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 2.540834665298462,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 0.2421,
      "step": 170
    },
    {
      "epoch": 0.7178464606181456,
      "grad_norm": 2.5203776359558105,
      "learning_rate": 7.771024502261526e-06,
      "loss": 0.2265,
      "step": 180
    },
    {
      "epoch": 0.7577268195413759,
      "grad_norm": 2.1481897830963135,
      "learning_rate": 2.667340275199426e-06,
      "loss": 0.2287,
      "step": 190
    },
    {
      "epoch": 0.7976071784646062,
      "grad_norm": 2.8947484493255615,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 0.2406,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2868052066295808.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}