{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6493055555555556,
  "eval_steps": 500,
  "global_step": 950,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034722222222222224,
      "grad_norm": 3.1068832874298096,
      "learning_rate": 1.6379310344827587e-06,
      "loss": 2.675,
      "step": 20
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 2.46288800239563,
      "learning_rate": 3.362068965517242e-06,
      "loss": 2.4759,
      "step": 40
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 2.1140520572662354,
      "learning_rate": 5.086206896551724e-06,
      "loss": 2.3011,
      "step": 60
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 1.9008077383041382,
      "learning_rate": 6.810344827586207e-06,
      "loss": 2.0724,
      "step": 80
    },
    {
      "epoch": 0.1736111111111111,
      "grad_norm": 2.368029832839966,
      "learning_rate": 8.53448275862069e-06,
      "loss": 1.9312,
      "step": 100
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 2.3201775550842285,
      "learning_rate": 9.999793100349294e-06,
      "loss": 1.8941,
      "step": 120
    },
    {
      "epoch": 0.24305555555555555,
      "grad_norm": 2.499159812927246,
      "learning_rate": 9.987843743451796e-06,
      "loss": 1.7747,
      "step": 140
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.1269280910491943,
      "learning_rate": 9.957553516178782e-06,
      "loss": 1.7052,
      "step": 160
    },
    {
      "epoch": 0.3125,
      "grad_norm": 2.290123224258423,
      "learning_rate": 9.909033799150947e-06,
      "loss": 1.7429,
      "step": 180
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 2.3117945194244385,
      "learning_rate": 9.842463004902127e-06,
      "loss": 1.6598,
      "step": 200
    },
    {
      "epoch": 0.3819444444444444,
      "grad_norm": 2.6141538619995117,
      "learning_rate": 9.758085921836076e-06,
      "loss": 1.6429,
      "step": 220
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 2.4996819496154785,
      "learning_rate": 9.656212814111567e-06,
      "loss": 1.6566,
      "step": 240
    },
    {
      "epoch": 0.4513888888888889,
      "grad_norm": 2.8781185150146484,
      "learning_rate": 9.53721828076571e-06,
      "loss": 1.6255,
      "step": 260
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 2.8994524478912354,
      "learning_rate": 9.401539878270545e-06,
      "loss": 1.6064,
      "step": 280
    },
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 2.9606640338897705,
      "learning_rate": 9.249676511588e-06,
      "loss": 1.6141,
      "step": 300
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.9091055393218994,
      "learning_rate": 9.082186599639429e-06,
      "loss": 1.598,
      "step": 320
    },
    {
      "epoch": 0.5902777777777778,
      "grad_norm": 2.523542642593384,
      "learning_rate": 8.899686021935554e-06,
      "loss": 1.5779,
      "step": 340
    },
    {
      "epoch": 0.625,
      "grad_norm": 2.5727219581604004,
      "learning_rate": 8.702845853917242e-06,
      "loss": 1.5475,
      "step": 360
    },
    {
      "epoch": 0.6597222222222222,
      "grad_norm": 2.4910247325897217,
      "learning_rate": 8.492389899334572e-06,
      "loss": 1.5346,
      "step": 380
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 3.080043077468872,
      "learning_rate": 8.269092028737885e-06,
      "loss": 1.5282,
      "step": 400
    },
    {
      "epoch": 0.7291666666666666,
      "grad_norm": 3.0990397930145264,
      "learning_rate": 8.033773333867498e-06,
      "loss": 1.4993,
      "step": 420
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 2.7828781604766846,
      "learning_rate": 7.78729910840572e-06,
      "loss": 1.4994,
      "step": 440
    },
    {
      "epoch": 0.7986111111111112,
      "grad_norm": 3.1256909370422363,
      "learning_rate": 7.530575666193283e-06,
      "loss": 1.5023,
      "step": 460
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 3.1738061904907227,
      "learning_rate": 7.26454700860997e-06,
      "loss": 1.4671,
      "step": 480
    },
    {
      "epoch": 0.8680555555555556,
      "grad_norm": 3.4600017070770264,
      "learning_rate": 6.990191353373876e-06,
      "loss": 1.466,
      "step": 500
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 3.556324005126953,
      "learning_rate": 6.708517537523264e-06,
      "loss": 1.4407,
      "step": 520
    },
    {
      "epoch": 0.9375,
      "grad_norm": 3.1536033153533936,
      "learning_rate": 6.420561307807713e-06,
      "loss": 1.4485,
      "step": 540
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 3.01642107963562,
      "learning_rate": 6.12738151212918e-06,
      "loss": 1.4672,
      "step": 560
    },
    {
      "epoch": 1.0069444444444444,
      "grad_norm": 3.864258050918579,
      "learning_rate": 5.830056206037482e-06,
      "loss": 1.4258,
      "step": 580
    },
    {
      "epoch": 1.0416666666666667,
      "grad_norm": 2.967533826828003,
      "learning_rate": 5.529678688597081e-06,
      "loss": 1.3619,
      "step": 600
    },
    {
      "epoch": 1.0763888888888888,
      "grad_norm": 3.2055039405822754,
      "learning_rate": 5.2273534822017105e-06,
      "loss": 1.3592,
      "step": 620
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 3.8909292221069336,
      "learning_rate": 4.924192271119554e-06,
      "loss": 1.3359,
      "step": 640
    },
    {
      "epoch": 1.1458333333333333,
      "grad_norm": 3.0267176628112793,
      "learning_rate": 4.621309813703385e-06,
      "loss": 1.3424,
      "step": 660
    },
    {
      "epoch": 1.1805555555555556,
      "grad_norm": 4.415727138519287,
      "learning_rate": 4.319819843296952e-06,
      "loss": 1.3435,
      "step": 680
    },
    {
      "epoch": 1.2152777777777777,
      "grad_norm": 3.6791961193084717,
      "learning_rate": 4.020830972910433e-06,
      "loss": 1.3391,
      "step": 700
    },
    {
      "epoch": 1.25,
      "grad_norm": 3.3228704929351807,
      "learning_rate": 3.7254426187239567e-06,
      "loss": 1.3054,
      "step": 720
    },
    {
      "epoch": 1.2847222222222223,
      "grad_norm": 3.616981267929077,
      "learning_rate": 3.4347409574088896e-06,
      "loss": 1.312,
      "step": 740
    },
    {
      "epoch": 1.3194444444444444,
      "grad_norm": 4.216521739959717,
      "learning_rate": 3.149794932132331e-06,
      "loss": 1.3334,
      "step": 760
    },
    {
      "epoch": 1.3541666666666667,
      "grad_norm": 4.408073425292969,
      "learning_rate": 2.871652321931161e-06,
      "loss": 1.317,
      "step": 780
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 2.9930851459503174,
      "learning_rate": 2.601335888909005e-06,
      "loss": 1.3089,
      "step": 800
    },
    {
      "epoch": 1.4236111111111112,
      "grad_norm": 4.05021858215332,
      "learning_rate": 2.339839617423318e-06,
      "loss": 1.2859,
      "step": 820
    },
    {
      "epoch": 1.4583333333333333,
      "grad_norm": 4.1063079833984375,
      "learning_rate": 2.0881250590915316e-06,
      "loss": 1.2947,
      "step": 840
    },
    {
      "epoch": 1.4930555555555556,
      "grad_norm": 3.8521957397460938,
      "learning_rate": 1.8471177970560712e-06,
      "loss": 1.3056,
      "step": 860
    },
    {
      "epoch": 1.5277777777777777,
      "grad_norm": 3.304344415664673,
      "learning_rate": 1.6177040425095664e-06,
      "loss": 1.2695,
      "step": 880
    },
    {
      "epoch": 1.5625,
      "grad_norm": 3.73410701751709,
      "learning_rate": 1.40072737599522e-06,
      "loss": 1.3125,
      "step": 900
    },
    {
      "epoch": 1.5972222222222223,
      "grad_norm": 3.594968318939209,
      "learning_rate": 1.196985645464921e-06,
      "loss": 1.2841,
      "step": 920
    },
    {
      "epoch": 1.6319444444444444,
      "grad_norm": 4.417556285858154,
      "learning_rate": 1.0072280325013185e-06,
      "loss": 1.2878,
      "step": 940
    }
  ],
  "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": 1.9311640760991744e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}