{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 3.5123185372718773,
      "learning_rate": 9.999571637870035e-06,
      "loss": 1.226,
      "step": 10
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 1.5848271556442048,
      "learning_rate": 9.948256934098353e-06,
      "loss": 0.6228,
      "step": 20
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.8361496621119446,
      "learning_rate": 9.812276182268236e-06,
      "loss": 0.5515,
      "step": 30
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 1.5115567203780127,
      "learning_rate": 9.593956050744493e-06,
      "loss": 0.5091,
      "step": 40
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 1.4016142884199931,
      "learning_rate": 9.297032057507264e-06,
      "loss": 0.454,
      "step": 50
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 2.00184917460606,
      "learning_rate": 8.926584654403725e-06,
      "loss": 0.4335,
      "step": 60
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 1.6405133492973567,
      "learning_rate": 8.488952299208402e-06,
      "loss": 0.453,
      "step": 70
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 1.3967472920274553,
      "learning_rate": 7.991623002853296e-06,
      "loss": 0.4142,
      "step": 80
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.4922010271447932,
      "learning_rate": 7.443106207484776e-06,
      "loss": 0.371,
      "step": 90
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 2.32029525552868,
      "learning_rate": 6.852787187549182e-06,
      "loss": 0.377,
      "step": 100
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.7742973388229974,
      "learning_rate": 6.230766465144966e-06,
      "loss": 0.4032,
      "step": 110
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 1.5132263980906087,
      "learning_rate": 5.587686987289189e-06,
      "loss": 0.2625,
      "step": 120
    },
    {
      "epoch": 1.0484848484848486,
      "grad_norm": 1.629344876478396,
      "learning_rate": 4.934552022143279e-06,
      "loss": 0.285,
      "step": 130
    },
    {
      "epoch": 1.1292929292929292,
      "grad_norm": 1.1764269702200636,
      "learning_rate": 4.282536890044105e-06,
      "loss": 0.1877,
      "step": 140
    },
    {
      "epoch": 1.2101010101010101,
      "grad_norm": 1.9284051716703332,
      "learning_rate": 3.6427977506746293e-06,
      "loss": 0.246,
      "step": 150
    },
    {
      "epoch": 1.290909090909091,
      "grad_norm": 1.734368263020826,
      "learning_rate": 3.0262807180786647e-06,
      "loss": 0.2198,
      "step": 160
    },
    {
      "epoch": 1.3717171717171717,
      "grad_norm": 1.6192276172886721,
      "learning_rate": 2.4435345696147404e-06,
      "loss": 0.1822,
      "step": 170
    },
    {
      "epoch": 1.4525252525252526,
      "grad_norm": 1.1662832730055461,
      "learning_rate": 1.9045302534508298e-06,
      "loss": 0.2371,
      "step": 180
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 1.7059185552933656,
      "learning_rate": 1.4184902828767288e-06,
      "loss": 0.1919,
      "step": 190
    },
    {
      "epoch": 1.614141414141414,
      "grad_norm": 1.3135725527345246,
      "learning_rate": 9.937309365446973e-07,
      "loss": 0.2161,
      "step": 200
    },
    {
      "epoch": 1.694949494949495,
      "grad_norm": 1.5960042220219293,
      "learning_rate": 6.375199646360142e-07,
      "loss": 0.1842,
      "step": 210
    },
    {
      "epoch": 1.7757575757575759,
      "grad_norm": 1.2292299231323565,
      "learning_rate": 3.5595223564037884e-07,
      "loss": 0.2174,
      "step": 220
    },
    {
      "epoch": 1.8565656565656565,
      "grad_norm": 1.5646423316785911,
      "learning_rate": 1.5384545146622854e-07,
      "loss": 0.1614,
      "step": 230
    },
    {
      "epoch": 1.9373737373737374,
      "grad_norm": 1.197417691855741,
      "learning_rate": 3.465771522536854e-08,
      "loss": 0.1849,
      "step": 240
    },
    {
      "epoch": 2.0,
      "step": 248,
      "total_flos": 7.861584991669453e+16,
      "train_loss": 0.35330821525666023,
      "train_runtime": 1983.9701,
      "train_samples_per_second": 1.994,
      "train_steps_per_second": 0.125
    }
  ],
  "logging_steps": 10,
  "max_steps": 248,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.861584991669453e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}