{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8229166666666665,
  "eval_steps": 500,
  "global_step": 1050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034722222222222224,
      "grad_norm": 2.4759202003479004,
      "learning_rate": 1.6379310344827587e-06,
      "loss": 2.5561,
      "step": 20
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 2.5604989528656006,
      "learning_rate": 3.362068965517242e-06,
      "loss": 2.3957,
      "step": 40
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 1.9377268552780151,
      "learning_rate": 5.086206896551724e-06,
      "loss": 2.217,
      "step": 60
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.7941242456436157,
      "learning_rate": 6.810344827586207e-06,
      "loss": 2.0366,
      "step": 80
    },
    {
      "epoch": 0.1736111111111111,
      "grad_norm": 2.2135872840881348,
      "learning_rate": 8.53448275862069e-06,
      "loss": 1.9154,
      "step": 100
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 2.290032148361206,
      "learning_rate": 9.999793100349294e-06,
      "loss": 1.8946,
      "step": 120
    },
    {
      "epoch": 0.24305555555555555,
      "grad_norm": 2.4187541007995605,
      "learning_rate": 9.987843743451796e-06,
      "loss": 1.7858,
      "step": 140
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.115030288696289,
      "learning_rate": 9.957553516178782e-06,
      "loss": 1.7133,
      "step": 160
    },
    {
      "epoch": 0.3125,
      "grad_norm": 2.290724754333496,
      "learning_rate": 9.909033799150947e-06,
      "loss": 1.7567,
      "step": 180
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 2.318016767501831,
      "learning_rate": 9.842463004902127e-06,
      "loss": 1.6653,
      "step": 200
    },
    {
      "epoch": 0.3819444444444444,
      "grad_norm": 2.37850284576416,
      "learning_rate": 9.758085921836076e-06,
      "loss": 1.6518,
      "step": 220
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 2.5013656616210938,
      "learning_rate": 9.656212814111567e-06,
      "loss": 1.669,
      "step": 240
    },
    {
      "epoch": 0.4513888888888889,
      "grad_norm": 3.0407257080078125,
      "learning_rate": 9.53721828076571e-06,
      "loss": 1.6393,
      "step": 260
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 2.709101915359497,
      "learning_rate": 9.401539878270545e-06,
      "loss": 1.6274,
      "step": 280
    },
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 2.9556779861450195,
      "learning_rate": 9.249676511588e-06,
      "loss": 1.6256,
      "step": 300
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.9455294609069824,
      "learning_rate": 9.082186599639429e-06,
      "loss": 1.61,
      "step": 320
    },
    {
      "epoch": 0.5902777777777778,
      "grad_norm": 2.631028413772583,
      "learning_rate": 8.899686021935554e-06,
      "loss": 1.5928,
      "step": 340
    },
    {
      "epoch": 0.625,
      "grad_norm": 2.5670149326324463,
      "learning_rate": 8.702845853917242e-06,
      "loss": 1.5608,
      "step": 360
    },
    {
      "epoch": 0.6597222222222222,
      "grad_norm": 2.519019365310669,
      "learning_rate": 8.492389899334572e-06,
      "loss": 1.5496,
      "step": 380
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 3.059999942779541,
      "learning_rate": 8.269092028737885e-06,
      "loss": 1.5339,
      "step": 400
    },
    {
      "epoch": 0.7291666666666666,
      "grad_norm": 2.882279872894287,
      "learning_rate": 8.033773333867498e-06,
      "loss": 1.5109,
      "step": 420
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 2.6647043228149414,
      "learning_rate": 7.78729910840572e-06,
      "loss": 1.5076,
      "step": 440
    },
    {
      "epoch": 0.7986111111111112,
      "grad_norm": 3.2523193359375,
      "learning_rate": 7.530575666193283e-06,
      "loss": 1.5043,
      "step": 460
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 3.349648952484131,
      "learning_rate": 7.26454700860997e-06,
      "loss": 1.4809,
      "step": 480
    },
    {
      "epoch": 0.8680555555555556,
      "grad_norm": 3.5382089614868164,
      "learning_rate": 6.990191353373876e-06,
      "loss": 1.4808,
      "step": 500
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 3.7552590370178223,
      "learning_rate": 6.708517537523264e-06,
      "loss": 1.4482,
      "step": 520
    },
    {
      "epoch": 0.9375,
      "grad_norm": 3.215052366256714,
      "learning_rate": 6.420561307807713e-06,
      "loss": 1.4627,
      "step": 540
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 3.1179182529449463,
      "learning_rate": 6.12738151212918e-06,
      "loss": 1.4731,
      "step": 560
    },
    {
      "epoch": 1.0069444444444444,
      "grad_norm": 3.928844451904297,
      "learning_rate": 5.830056206037482e-06,
      "loss": 1.4354,
      "step": 580
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 3.2214365005493164,
      "learning_rate": 5.529678688597081e-06,
      "loss": 1.3671,
      "step": 600
    },
    {
      "epoch": 1.0763888888888888,
      "grad_norm": 3.3545398712158203,
      "learning_rate": 5.2273534822017105e-06,
      "loss": 1.373,
      "step": 620
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 4.0173234939575195,
      "learning_rate": 4.924192271119554e-06,
      "loss": 1.3456,
      "step": 640
    },
    {
      "epoch": 1.1458333333333333,
      "grad_norm": 3.150284767150879,
      "learning_rate": 4.621309813703385e-06,
      "loss": 1.3462,
      "step": 660
    },
    {
      "epoch": 1.1805555555555556,
      "grad_norm": 4.555105209350586,
      "learning_rate": 4.319819843296952e-06,
      "loss": 1.3409,
      "step": 680
    },
    {
      "epoch": 1.2152777777777777,
      "grad_norm": 3.7820332050323486,
      "learning_rate": 4.020830972910433e-06,
      "loss": 1.3522,
      "step": 700
    },
    {
      "epoch": 1.25,
      "grad_norm": 3.446506977081299,
      "learning_rate": 3.7254426187239567e-06,
      "loss": 1.3083,
      "step": 720
    },
    {
      "epoch": 1.2847222222222223,
      "grad_norm": 3.7315480709075928,
      "learning_rate": 3.4347409574088896e-06,
      "loss": 1.3234,
      "step": 740
    },
    {
      "epoch": 1.3194444444444444,
      "grad_norm": 4.601447105407715,
      "learning_rate": 3.149794932132331e-06,
      "loss": 1.3384,
      "step": 760
    },
    {
      "epoch": 1.3541666666666667,
      "grad_norm": 4.626559257507324,
      "learning_rate": 2.871652321931161e-06,
      "loss": 1.3196,
      "step": 780
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 3.092618227005005,
      "learning_rate": 2.601335888909005e-06,
      "loss": 1.3185,
      "step": 800
    },
    {
      "epoch": 1.4236111111111112,
      "grad_norm": 4.193453788757324,
      "learning_rate": 2.339839617423318e-06,
      "loss": 1.2816,
      "step": 820
    },
    {
      "epoch": 1.4583333333333333,
      "grad_norm": 3.9958441257476807,
      "learning_rate": 2.0881250590915316e-06,
      "loss": 1.2989,
      "step": 840
    },
    {
      "epoch": 1.4930555555555556,
      "grad_norm": 4.101428985595703,
      "learning_rate": 1.8471177970560712e-06,
      "loss": 1.3146,
      "step": 860
    },
    {
      "epoch": 1.5277777777777777,
      "grad_norm": 3.387007236480713,
      "learning_rate": 1.6177040425095664e-06,
      "loss": 1.2792,
      "step": 880
    },
    {
      "epoch": 1.5625,
      "grad_norm": 3.733682870864868,
      "learning_rate": 1.40072737599522e-06,
      "loss": 1.3185,
      "step": 900
    },
    {
      "epoch": 1.5972222222222223,
      "grad_norm": 3.3572065830230713,
      "learning_rate": 1.196985645464921e-06,
      "loss": 1.2915,
      "step": 920
    },
    {
      "epoch": 1.6319444444444444,
      "grad_norm": 4.337113380432129,
      "learning_rate": 1.0072280325013185e-06,
      "loss": 1.2886,
      "step": 940
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 4.326784133911133,
      "learning_rate": 8.321522974916968e-07,
      "loss": 1.3046,
      "step": 960
    },
    {
      "epoch": 1.7013888888888888,
      "grad_norm": 4.501497268676758,
      "learning_rate": 6.724022138834341e-07,
      "loss": 1.2783,
      "step": 980
    },
    {
      "epoch": 1.7361111111111112,
      "grad_norm": 3.4914722442626953,
      "learning_rate": 5.285652009556075e-07,
      "loss": 1.2741,
      "step": 1000
    },
    {
      "epoch": 1.7708333333333335,
      "grad_norm": 4.376003742218018,
      "learning_rate": 4.0117016381130636e-07,
      "loss": 1.279,
      "step": 1020
    },
    {
      "epoch": 1.8055555555555556,
      "grad_norm": 4.257233619689941,
      "learning_rate": 2.906855485332305e-07,
      "loss": 1.2538,
      "step": 1040
    }
  ],
  "logging_steps": 20,
  "max_steps": 1152,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.108497820932178e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}