{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 747,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.997789428625975e-05,
      "loss": 1.6077,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.99116162380454e-05,
      "loss": 0.9415,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.980128306524183e-05,
      "loss": 0.6271,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.964708988733178e-05,
      "loss": 0.5335,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.944930938833535e-05,
      "loss": 0.3693,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9208291334580104e-05,
      "loss": 0.47,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.892446195615423e-05,
      "loss": 0.4268,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.859832319313697e-05,
      "loss": 0.3653,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8230451807939135e-05,
      "loss": 0.3466,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.782149836532345e-05,
      "loss": 0.3241,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.737218608190878e-05,
      "loss": 0.3763,
      "step": 110
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.6883309547192476e-05,
      "loss": 0.3333,
      "step": 120
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.635573331835302e-05,
      "loss": 0.3106,
      "step": 130
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5790390391317675e-05,
      "loss": 0.3241,
      "step": 140
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.518828055079925e-05,
      "loss": 0.2781,
      "step": 150
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.4550468602219716e-05,
      "loss": 0.3,
      "step": 160
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.387808248864751e-05,
      "loss": 0.3229,
      "step": 170
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.3172311296078595e-05,
      "loss": 0.3347,
      "step": 180
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.2434403150588895e-05,
      "loss": 0.2897,
      "step": 190
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.166566301107687e-05,
      "loss": 0.2951,
      "step": 200
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.08674503614997e-05,
      "loss": 0.3081,
      "step": 210
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.004117680668422e-05,
      "loss": 0.2889,
      "step": 220
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.918830357596434e-05,
      "loss": 0.3207,
      "step": 230
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.8310338939059644e-05,
      "loss": 0.3238,
      "step": 240
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.740883553876515e-05,
      "loss": 0.3146,
      "step": 250
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.6485387645169064e-05,
      "loss": 0.2973,
      "step": 260
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.55416283362546e-05,
      "loss": 0.2631,
      "step": 270
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.457922660987155e-05,
      "loss": 0.3323,
      "step": 280
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.3599884432185225e-05,
      "loss": 0.2631,
      "step": 290
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.260533372782234e-05,
      "loss": 0.3066,
      "step": 300
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.1597333317036545e-05,
      "loss": 0.3131,
      "step": 310
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.057766580531031e-05,
      "loss": 0.3101,
      "step": 320
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.9548134430893604e-05,
      "loss": 0.3022,
      "step": 330
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.8510559875854377e-05,
      "loss": 0.2496,
      "step": 340
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.7466777046280457e-05,
      "loss": 0.3218,
      "step": 350
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6418631827326857e-05,
      "loss": 0.3064,
      "step": 360
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.5367977818847034e-05,
      "loss": 0.2937,
      "step": 370
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.431667305738112e-05,
      "loss": 0.2708,
      "step": 380
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.3266576730297956e-05,
      "loss": 0.2838,
      "step": 390
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.221954588790206e-05,
      "loss": 0.2987,
      "step": 400
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.1177432159319754e-05,
      "loss": 0.3069,
      "step": 410
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.014207847797256e-05,
      "loss": 0.2709,
      "step": 420
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.9115315822428437e-05,
      "loss": 0.3159,
      "step": 430
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.809895997839482e-05,
      "loss": 0.2997,
      "step": 440
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.70948083275794e-05,
      "loss": 0.2347,
      "step": 450
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.6104636669097776e-05,
      "loss": 0.2634,
      "step": 460
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.513019607904882e-05,
      "loss": 0.2438,
      "step": 470
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.4173209813811788e-05,
      "loss": 0.2289,
      "step": 480
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3235370262541272e-05,
      "loss": 0.2609,
      "step": 490
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.2318335954249669e-05,
      "loss": 0.2724,
      "step": 500
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.1423728624769695e-05,
      "loss": 0.272,
      "step": 510
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.0553130348784182e-05,
      "loss": 0.303,
      "step": 520
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.708080741994868e-06,
      "loss": 0.2766,
      "step": 530
    },
    {
      "epoch": 0.72,
      "learning_rate": 8.890074238378074e-06,
      "loss": 0.2333,
      "step": 540
    },
    {
      "epoch": 0.74,
      "learning_rate": 8.100557447342327e-06,
      "loss": 0.2326,
      "step": 550
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.340926595461687e-06,
      "loss": 0.2274,
      "step": 560
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.612525057308949e-06,
      "loss": 0.3255,
      "step": 570
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.9166409797553415e-06,
      "loss": 0.2631,
      "step": 580
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.254505003938043e-06,
      "loss": 0.2938,
      "step": 590
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.627288088924156e-06,
      "loss": 0.2807,
      "step": 600
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.036099440919763e-06,
      "loss": 0.2909,
      "step": 610
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.481984551686429e-06,
      "loss": 0.2997,
      "step": 620
    },
    {
      "epoch": 0.84,
      "learning_rate": 2.9659233496337786e-06,
      "loss": 0.2424,
      "step": 630
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.4888284668582285e-06,
      "loss": 0.2862,
      "step": 640
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.051543625192226e-06,
      "loss": 0.3124,
      "step": 650
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.6548421441183875e-06,
      "loss": 0.2644,
      "step": 660
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.2994255731871963e-06,
      "loss": 0.2622,
      "step": 670
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.85922451356694e-07,
      "loss": 0.2234,
      "step": 680
    },
    {
      "epoch": 0.92,
      "learning_rate": 7.148871954483105e-07,
      "loss": 0.334,
      "step": 690
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.867991196844918e-07,
      "loss": 0.2915,
      "step": 700
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.020615880420713e-07,
      "loss": 0.2802,
      "step": 710
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.6100130092037703e-07,
      "loss": 0.2975,
      "step": 720
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.386771738558506e-08,
      "loss": 0.2531,
      "step": 730
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0832614013073228e-08,
      "loss": 0.2696,
      "step": 740
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.27866294980049133,
      "eval_runtime": 101.2195,
      "eval_samples_per_second": 6.56,
      "eval_steps_per_second": 3.28,
      "step": 747
    },
    {
      "epoch": 1.0,
      "step": 747,
      "total_flos": 1.7883373351469056e+17,
      "train_loss": 0.3299662241814446,
      "train_runtime": 2859.8545,
      "train_samples_per_second": 2.089,
      "train_steps_per_second": 0.261
    }
  ],
  "logging_steps": 10,
  "max_steps": 747,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 1.7883373351469056e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}