{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9980713596914175,
  "eval_steps": 50,
  "global_step": 518,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 1.5247,
      "step": 10
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 1.4114,
      "step": 20
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 1.3203,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 1.3566,
      "step": 40
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 1.309,
      "step": 50
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.3630590438842773,
      "eval_runtime": 26.2031,
      "eval_samples_per_second": 33.355,
      "eval_steps_per_second": 2.099,
      "step": 50
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 1.2856,
      "step": 60
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 1.3524,
      "step": 70
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 1.317,
      "step": 80
    },
    {
      "epoch": 0.35,
      "learning_rate": 5e-05,
      "loss": 1.324,
      "step": 90
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 1.2966,
      "step": 100
    },
    {
      "epoch": 0.39,
      "eval_loss": 1.3339532613754272,
      "eval_runtime": 25.949,
      "eval_samples_per_second": 33.681,
      "eval_steps_per_second": 2.12,
      "step": 100
    },
    {
      "epoch": 0.42,
      "learning_rate": 5e-05,
      "loss": 1.3073,
      "step": 110
    },
    {
      "epoch": 0.46,
      "learning_rate": 5e-05,
      "loss": 1.3162,
      "step": 120
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 1.3299,
      "step": 130
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 1.3271,
      "step": 140
    },
    {
      "epoch": 0.58,
      "learning_rate": 5e-05,
      "loss": 1.2914,
      "step": 150
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.3168174028396606,
      "eval_runtime": 26.0065,
      "eval_samples_per_second": 33.607,
      "eval_steps_per_second": 2.115,
      "step": 150
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 1.2526,
      "step": 160
    },
    {
      "epoch": 0.66,
      "learning_rate": 5e-05,
      "loss": 1.2924,
      "step": 170
    },
    {
      "epoch": 0.69,
      "learning_rate": 5e-05,
      "loss": 1.3303,
      "step": 180
    },
    {
      "epoch": 0.73,
      "learning_rate": 5e-05,
      "loss": 1.3173,
      "step": 190
    },
    {
      "epoch": 0.77,
      "learning_rate": 5e-05,
      "loss": 1.298,
      "step": 200
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.303916096687317,
      "eval_runtime": 26.2236,
      "eval_samples_per_second": 33.329,
      "eval_steps_per_second": 2.097,
      "step": 200
    },
    {
      "epoch": 0.81,
      "learning_rate": 5e-05,
      "loss": 1.2402,
      "step": 210
    },
    {
      "epoch": 0.85,
      "learning_rate": 5e-05,
      "loss": 1.2768,
      "step": 220
    },
    {
      "epoch": 0.89,
      "learning_rate": 5e-05,
      "loss": 1.2929,
      "step": 230
    },
    {
      "epoch": 0.93,
      "learning_rate": 5e-05,
      "loss": 1.2744,
      "step": 240
    },
    {
      "epoch": 0.96,
      "learning_rate": 5e-05,
      "loss": 1.2678,
      "step": 250
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.2991052865982056,
      "eval_runtime": 26.0876,
      "eval_samples_per_second": 33.502,
      "eval_steps_per_second": 2.108,
      "step": 250
    },
    {
      "epoch": 1.0,
      "learning_rate": 5e-05,
      "loss": 1.2506,
      "step": 260
    },
    {
      "epoch": 1.04,
      "learning_rate": 5e-05,
      "loss": 1.1717,
      "step": 270
    },
    {
      "epoch": 1.08,
      "learning_rate": 5e-05,
      "loss": 1.2022,
      "step": 280
    },
    {
      "epoch": 1.12,
      "learning_rate": 5e-05,
      "loss": 1.2237,
      "step": 290
    },
    {
      "epoch": 1.16,
      "learning_rate": 5e-05,
      "loss": 1.216,
      "step": 300
    },
    {
      "epoch": 1.16,
      "eval_loss": 1.3007503747940063,
      "eval_runtime": 28.1383,
      "eval_samples_per_second": 31.061,
      "eval_steps_per_second": 1.955,
      "step": 300
    },
    {
      "epoch": 1.2,
      "learning_rate": 5e-05,
      "loss": 1.2264,
      "step": 310
    },
    {
      "epoch": 1.23,
      "learning_rate": 5e-05,
      "loss": 1.1461,
      "step": 320
    },
    {
      "epoch": 1.27,
      "learning_rate": 5e-05,
      "loss": 1.1855,
      "step": 330
    },
    {
      "epoch": 1.31,
      "learning_rate": 5e-05,
      "loss": 1.2014,
      "step": 340
    },
    {
      "epoch": 1.35,
      "learning_rate": 5e-05,
      "loss": 1.2467,
      "step": 350
    },
    {
      "epoch": 1.35,
      "eval_loss": 1.2945101261138916,
      "eval_runtime": 25.9821,
      "eval_samples_per_second": 33.639,
      "eval_steps_per_second": 2.117,
      "step": 350
    },
    {
      "epoch": 1.39,
      "learning_rate": 5e-05,
      "loss": 1.2136,
      "step": 360
    },
    {
      "epoch": 1.43,
      "learning_rate": 5e-05,
      "loss": 1.1727,
      "step": 370
    },
    {
      "epoch": 1.47,
      "learning_rate": 5e-05,
      "loss": 1.192,
      "step": 380
    },
    {
      "epoch": 1.5,
      "learning_rate": 5e-05,
      "loss": 1.1963,
      "step": 390
    },
    {
      "epoch": 1.54,
      "learning_rate": 5e-05,
      "loss": 1.223,
      "step": 400
    },
    {
      "epoch": 1.54,
      "eval_loss": 1.293986201286316,
      "eval_runtime": 26.8556,
      "eval_samples_per_second": 32.544,
      "eval_steps_per_second": 2.048,
      "step": 400
    },
    {
      "epoch": 1.58,
      "learning_rate": 5e-05,
      "loss": 1.2076,
      "step": 410
    },
    {
      "epoch": 1.62,
      "learning_rate": 5e-05,
      "loss": 1.1373,
      "step": 420
    },
    {
      "epoch": 1.66,
      "learning_rate": 5e-05,
      "loss": 1.224,
      "step": 430
    },
    {
      "epoch": 1.7,
      "learning_rate": 5e-05,
      "loss": 1.1841,
      "step": 440
    },
    {
      "epoch": 1.74,
      "learning_rate": 5e-05,
      "loss": 1.2,
      "step": 450
    },
    {
      "epoch": 1.74,
      "eval_loss": 1.2924402952194214,
      "eval_runtime": 29.7855,
      "eval_samples_per_second": 29.343,
      "eval_steps_per_second": 1.847,
      "step": 450
    },
    {
      "epoch": 1.77,
      "learning_rate": 5e-05,
      "loss": 1.1896,
      "step": 460
    },
    {
      "epoch": 1.81,
      "learning_rate": 5e-05,
      "loss": 1.1476,
      "step": 470
    },
    {
      "epoch": 1.85,
      "learning_rate": 5e-05,
      "loss": 1.1986,
      "step": 480
    },
    {
      "epoch": 1.89,
      "learning_rate": 5e-05,
      "loss": 1.2185,
      "step": 490
    },
    {
      "epoch": 1.93,
      "learning_rate": 5e-05,
      "loss": 1.2406,
      "step": 500
    },
    {
      "epoch": 1.93,
      "eval_loss": 1.2884066104888916,
      "eval_runtime": 26.2052,
      "eval_samples_per_second": 33.352,
      "eval_steps_per_second": 2.099,
      "step": 500
    },
    {
      "epoch": 1.97,
      "learning_rate": 5e-05,
      "loss": 1.1962,
      "step": 510
    },
    {
      "epoch": 2.0,
      "step": 518,
      "total_flos": 5.99394721244119e+17,
      "train_loss": 1.2557248572124937,
      "train_runtime": 2763.6306,
      "train_samples_per_second": 12.007,
      "train_steps_per_second": 0.187
    }
  ],
  "logging_steps": 10,
  "max_steps": 518,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 5.99394721244119e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}