{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9852941176470589,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 7.663624286651611,
      "learning_rate": 0.00019338235294117647,
      "loss": 4.9727,
      "step": 10
    },
    {
      "epoch": 0.14705882352941177,
      "grad_norm": 1.8574577569961548,
      "learning_rate": 0.0001860294117647059,
      "loss": 1.6817,
      "step": 20
    },
    {
      "epoch": 0.22058823529411764,
      "grad_norm": 0.788298487663269,
      "learning_rate": 0.0001786764705882353,
      "loss": 1.4084,
      "step": 30
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 0.6028629541397095,
      "learning_rate": 0.0001713235294117647,
      "loss": 1.291,
      "step": 40
    },
    {
      "epoch": 0.36764705882352944,
      "grad_norm": 0.6917942762374878,
      "learning_rate": 0.00016397058823529412,
      "loss": 1.116,
      "step": 50
    },
    {
      "epoch": 0.4411764705882353,
      "grad_norm": 0.5741753578186035,
      "learning_rate": 0.00015661764705882352,
      "loss": 1.1259,
      "step": 60
    },
    {
      "epoch": 0.5147058823529411,
      "grad_norm": 0.6356399655342102,
      "learning_rate": 0.00014926470588235295,
      "loss": 1.0164,
      "step": 70
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.7084798812866211,
      "learning_rate": 0.00014191176470588237,
      "loss": 1.0547,
      "step": 80
    },
    {
      "epoch": 0.6617647058823529,
      "grad_norm": 0.7180666923522949,
      "learning_rate": 0.00013455882352941177,
      "loss": 1.006,
      "step": 90
    },
    {
      "epoch": 0.7352941176470589,
      "grad_norm": 0.672892689704895,
      "learning_rate": 0.00012720588235294117,
      "loss": 1.0526,
      "step": 100
    },
    {
      "epoch": 0.8088235294117647,
      "grad_norm": 0.8210435509681702,
      "learning_rate": 0.00011985294117647058,
      "loss": 1.04,
      "step": 110
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 0.5405668616294861,
      "learning_rate": 0.00011250000000000001,
      "loss": 0.9536,
      "step": 120
    },
    {
      "epoch": 0.9558823529411765,
      "grad_norm": 0.6286842823028564,
      "learning_rate": 0.00010514705882352942,
      "loss": 0.9436,
      "step": 130
    },
    {
      "epoch": 1.0294117647058822,
      "grad_norm": 0.7652072310447693,
      "learning_rate": 9.779411764705882e-05,
      "loss": 0.9743,
      "step": 140
    },
    {
      "epoch": 1.1029411764705883,
      "grad_norm": 0.6663604974746704,
      "learning_rate": 9.044117647058823e-05,
      "loss": 0.9276,
      "step": 150
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.8647569417953491,
      "learning_rate": 8.308823529411766e-05,
      "loss": 0.9063,
      "step": 160
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.6697940826416016,
      "learning_rate": 7.573529411764706e-05,
      "loss": 0.965,
      "step": 170
    },
    {
      "epoch": 1.3235294117647058,
      "grad_norm": 0.5793155431747437,
      "learning_rate": 6.838235294117647e-05,
      "loss": 0.9658,
      "step": 180
    },
    {
      "epoch": 1.3970588235294117,
      "grad_norm": 0.6902905106544495,
      "learning_rate": 6.102941176470589e-05,
      "loss": 0.9561,
      "step": 190
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.943708598613739,
      "learning_rate": 5.3676470588235296e-05,
      "loss": 0.9296,
      "step": 200
    },
    {
      "epoch": 1.5441176470588234,
      "grad_norm": 0.7292776703834534,
      "learning_rate": 4.632352941176471e-05,
      "loss": 0.9141,
      "step": 210
    },
    {
      "epoch": 1.6176470588235294,
      "grad_norm": 0.6016244888305664,
      "learning_rate": 3.897058823529412e-05,
      "loss": 0.918,
      "step": 220
    },
    {
      "epoch": 1.6911764705882353,
      "grad_norm": 0.5953148007392883,
      "learning_rate": 3.161764705882353e-05,
      "loss": 0.9498,
      "step": 230
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.7737902402877808,
      "learning_rate": 2.4264705882352942e-05,
      "loss": 0.9662,
      "step": 240
    },
    {
      "epoch": 1.8382352941176472,
      "grad_norm": 0.6206201910972595,
      "learning_rate": 1.6911764705882355e-05,
      "loss": 0.9088,
      "step": 250
    },
    {
      "epoch": 1.9117647058823528,
      "grad_norm": 0.6300740242004395,
      "learning_rate": 9.558823529411764e-06,
      "loss": 0.9853,
      "step": 260
    },
    {
      "epoch": 1.9852941176470589,
      "grad_norm": 0.8376365303993225,
      "learning_rate": 2.2058823529411767e-06,
      "loss": 1.0004,
      "step": 270
    }
  ],
  "logging_steps": 10,
  "max_steps": 272,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 71221531115520.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}