{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5614035087719298,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.031189083820662766,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.0001,
      "loss": 0.6599,
      "step": 5
    },
    {
      "epoch": 0.06237816764132553,
      "grad_norm": 0.049560546875,
      "learning_rate": 0.0001,
      "loss": 0.4191,
      "step": 10
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 0.046875,
      "learning_rate": 0.0001,
      "loss": 0.3937,
      "step": 15
    },
    {
      "epoch": 0.12475633528265107,
      "grad_norm": 0.056640625,
      "learning_rate": 0.0001,
      "loss": 0.3818,
      "step": 20
    },
    {
      "epoch": 0.15594541910331383,
      "grad_norm": 0.030029296875,
      "learning_rate": 0.0001,
      "loss": 0.3685,
      "step": 25
    },
    {
      "epoch": 0.1871345029239766,
      "grad_norm": 0.031005859375,
      "learning_rate": 0.0001,
      "loss": 0.361,
      "step": 30
    },
    {
      "epoch": 0.21832358674463936,
      "grad_norm": 0.03564453125,
      "learning_rate": 0.0001,
      "loss": 0.3753,
      "step": 35
    },
    {
      "epoch": 0.24951267056530213,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.0001,
      "loss": 0.4059,
      "step": 40
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 0.045166015625,
      "learning_rate": 0.0001,
      "loss": 0.3342,
      "step": 45
    },
    {
      "epoch": 0.31189083820662766,
      "grad_norm": 0.027587890625,
      "learning_rate": 0.0001,
      "loss": 0.3155,
      "step": 50
    },
    {
      "epoch": 0.34307992202729043,
      "grad_norm": 0.0284423828125,
      "learning_rate": 0.0001,
      "loss": 0.3219,
      "step": 55
    },
    {
      "epoch": 0.3742690058479532,
      "grad_norm": 0.0255126953125,
      "learning_rate": 0.0001,
      "loss": 0.3279,
      "step": 60
    },
    {
      "epoch": 0.40545808966861596,
      "grad_norm": 0.0267333984375,
      "learning_rate": 0.0001,
      "loss": 0.3145,
      "step": 65
    },
    {
      "epoch": 0.43664717348927873,
      "grad_norm": 0.027099609375,
      "learning_rate": 0.0001,
      "loss": 0.3277,
      "step": 70
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 0.03173828125,
      "learning_rate": 0.0001,
      "loss": 0.3354,
      "step": 75
    },
    {
      "epoch": 0.49902534113060426,
      "grad_norm": 0.06982421875,
      "learning_rate": 0.0001,
      "loss": 0.3578,
      "step": 80
    },
    {
      "epoch": 0.530214424951267,
      "grad_norm": 0.03759765625,
      "learning_rate": 0.0001,
      "loss": 0.317,
      "step": 85
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.02734375,
      "learning_rate": 0.0001,
      "loss": 0.2833,
      "step": 90
    }
  ],
  "logging_steps": 5,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 90,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.797935130464256e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}