{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8198801550934087,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.0908,
      "step": 20
    },
    {
      "epoch": 0.11,
      "eval_loss": 0.8531244397163391,
      "eval_runtime": 113.8743,
      "eval_samples_per_second": 17.563,
      "eval_steps_per_second": 0.281,
      "step": 20
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 0.9266,
      "step": 40
    },
    {
      "epoch": 0.23,
      "eval_loss": 0.8096991777420044,
      "eval_runtime": 113.8834,
      "eval_samples_per_second": 17.562,
      "eval_steps_per_second": 0.281,
      "step": 40
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 0.8862,
      "step": 60
    },
    {
      "epoch": 0.34,
      "eval_loss": 0.7927151322364807,
      "eval_runtime": 113.7971,
      "eval_samples_per_second": 17.575,
      "eval_steps_per_second": 0.281,
      "step": 60
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 0.8688,
      "step": 80
    },
    {
      "epoch": 0.45,
      "eval_loss": 0.7790905237197876,
      "eval_runtime": 113.7549,
      "eval_samples_per_second": 17.582,
      "eval_steps_per_second": 0.281,
      "step": 80
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.861,
      "step": 100
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.776690661907196,
      "eval_runtime": 113.8772,
      "eval_samples_per_second": 17.563,
      "eval_steps_per_second": 0.281,
      "step": 100
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.8509,
      "step": 120
    },
    {
      "epoch": 0.68,
      "eval_loss": 0.7719365358352661,
      "eval_runtime": 113.7172,
      "eval_samples_per_second": 17.587,
      "eval_steps_per_second": 0.281,
      "step": 120
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.8301,
      "step": 140
    },
    {
      "epoch": 0.79,
      "eval_loss": 0.760235607624054,
      "eval_runtime": 113.7009,
      "eval_samples_per_second": 17.59,
      "eval_steps_per_second": 0.281,
      "step": 140
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 0.8126,
      "step": 160
    },
    {
      "epoch": 0.9,
      "eval_loss": 0.7536348104476929,
      "eval_runtime": 113.7032,
      "eval_samples_per_second": 17.59,
      "eval_steps_per_second": 0.281,
      "step": 160
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002,
      "loss": 0.7979,
      "step": 180
    },
    {
      "epoch": 1.02,
      "eval_loss": 0.7558956742286682,
      "eval_runtime": 113.7654,
      "eval_samples_per_second": 17.58,
      "eval_steps_per_second": 0.281,
      "step": 180
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 0.4881,
      "step": 200
    },
    {
      "epoch": 1.13,
      "eval_loss": 0.7853934168815613,
      "eval_runtime": 113.7426,
      "eval_samples_per_second": 17.584,
      "eval_steps_per_second": 0.281,
      "step": 200
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0002,
      "loss": 0.491,
      "step": 220
    },
    {
      "epoch": 1.24,
      "eval_loss": 0.7784026861190796,
      "eval_runtime": 113.7986,
      "eval_samples_per_second": 17.575,
      "eval_steps_per_second": 0.281,
      "step": 220
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 0.489,
      "step": 240
    },
    {
      "epoch": 1.35,
      "eval_loss": 0.7843385338783264,
      "eval_runtime": 113.8087,
      "eval_samples_per_second": 17.573,
      "eval_steps_per_second": 0.281,
      "step": 240
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 0.4947,
      "step": 260
    },
    {
      "epoch": 1.47,
      "eval_loss": 0.790459156036377,
      "eval_runtime": 113.8164,
      "eval_samples_per_second": 17.572,
      "eval_steps_per_second": 0.281,
      "step": 260
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002,
      "loss": 0.4937,
      "step": 280
    },
    {
      "epoch": 1.58,
      "eval_loss": 0.7871547937393188,
      "eval_runtime": 113.8459,
      "eval_samples_per_second": 17.568,
      "eval_steps_per_second": 0.281,
      "step": 280
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 0.5175,
      "step": 300
    },
    {
      "epoch": 1.69,
      "eval_loss": 0.7906413674354553,
      "eval_runtime": 113.7575,
      "eval_samples_per_second": 17.581,
      "eval_steps_per_second": 0.281,
      "step": 300
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0002,
      "loss": 0.5008,
      "step": 320
    },
    {
      "epoch": 1.8,
      "eval_loss": 0.7836869955062866,
      "eval_runtime": 113.7644,
      "eval_samples_per_second": 17.58,
      "eval_steps_per_second": 0.281,
      "step": 320
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0002,
      "loss": 0.4998,
      "step": 340
    },
    {
      "epoch": 1.92,
      "eval_loss": 0.7940365672111511,
      "eval_runtime": 113.7944,
      "eval_samples_per_second": 17.576,
      "eval_steps_per_second": 0.281,
      "step": 340
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0002,
      "loss": 0.4598,
      "step": 360
    },
    {
      "epoch": 2.03,
      "eval_loss": 0.8568623065948486,
      "eval_runtime": 113.8293,
      "eval_samples_per_second": 17.57,
      "eval_steps_per_second": 0.281,
      "step": 360
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002,
      "loss": 0.2924,
      "step": 380
    },
    {
      "epoch": 2.14,
      "eval_loss": 0.8405641913414001,
      "eval_runtime": 113.7058,
      "eval_samples_per_second": 17.589,
      "eval_steps_per_second": 0.281,
      "step": 380
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0002,
      "loss": 0.3068,
      "step": 400
    },
    {
      "epoch": 2.26,
      "eval_loss": 0.8450121879577637,
      "eval_runtime": 113.8088,
      "eval_samples_per_second": 17.573,
      "eval_steps_per_second": 0.281,
      "step": 400
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0002,
      "loss": 0.2982,
      "step": 420
    },
    {
      "epoch": 2.37,
      "eval_loss": 0.8488427400588989,
      "eval_runtime": 113.7591,
      "eval_samples_per_second": 17.581,
      "eval_steps_per_second": 0.281,
      "step": 420
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0002,
      "loss": 0.3092,
      "step": 440
    },
    {
      "epoch": 2.48,
      "eval_loss": 0.8430971503257751,
      "eval_runtime": 113.7315,
      "eval_samples_per_second": 17.585,
      "eval_steps_per_second": 0.281,
      "step": 440
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 0.3053,
      "step": 460
    },
    {
      "epoch": 2.59,
      "eval_loss": 0.8562591075897217,
      "eval_runtime": 113.7597,
      "eval_samples_per_second": 17.581,
      "eval_steps_per_second": 0.281,
      "step": 460
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0002,
      "loss": 0.3029,
      "step": 480
    },
    {
      "epoch": 2.71,
      "eval_loss": 0.8492431044578552,
      "eval_runtime": 113.744,
      "eval_samples_per_second": 17.583,
      "eval_steps_per_second": 0.281,
      "step": 480
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0002,
      "loss": 0.3233,
      "step": 500
    },
    {
      "epoch": 2.82,
      "eval_loss": 0.8486313223838806,
      "eval_runtime": 113.729,
      "eval_samples_per_second": 17.586,
      "eval_steps_per_second": 0.281,
      "step": 500
    }
  ],
  "max_steps": 750,
  "num_train_epochs": 5,
  "total_flos": 4.995957240616714e+17,
  "trial_name": null,
  "trial_params": null
}