{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 1.993065357208252,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 2.6875,
      "step": 20
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 1.730460524559021,
      "learning_rate": 2.857142857142857e-05,
      "loss": 2.2829,
      "step": 40
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 1.8479743003845215,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.7818,
      "step": 60
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.4088687896728516,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.2963,
      "step": 80
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.4508253335952759,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.0661,
      "step": 100
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.4717705249786377,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.9221,
      "step": 120
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.364703893661499,
      "learning_rate": 0.0001,
      "loss": 0.8801,
      "step": 140
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 1.5449830293655396,
      "learning_rate": 9.841269841269841e-05,
      "loss": 0.8574,
      "step": 160
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 1.3663296699523926,
      "learning_rate": 9.682539682539682e-05,
      "loss": 0.77,
      "step": 180
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.585909128189087,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.7391,
      "step": 200
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 1.2754377126693726,
      "learning_rate": 9.365079365079366e-05,
      "loss": 0.6384,
      "step": 220
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 1.4652817249298096,
      "learning_rate": 9.206349206349206e-05,
      "loss": 0.6413,
      "step": 240
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 1.5677884817123413,
      "learning_rate": 9.047619047619048e-05,
      "loss": 0.6228,
      "step": 260
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.7060600519180298,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.6543,
      "step": 280
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 1.4226174354553223,
      "learning_rate": 8.730158730158731e-05,
      "loss": 0.6236,
      "step": 300
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.5981993675231934,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.6275,
      "step": 320
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 1.336606502532959,
      "learning_rate": 8.412698412698413e-05,
      "loss": 0.592,
      "step": 340
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 1.4357742071151733,
      "learning_rate": 8.253968253968255e-05,
      "loss": 0.5973,
      "step": 360
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 1.2808163166046143,
      "learning_rate": 8.095238095238096e-05,
      "loss": 0.6327,
      "step": 380
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.493129849433899,
      "learning_rate": 7.936507936507937e-05,
      "loss": 0.6172,
      "step": 400
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.570550560951233,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.6201,
      "step": 420
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 1.8142577409744263,
      "learning_rate": 7.619047619047618e-05,
      "loss": 0.6119,
      "step": 440
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 1.5308444499969482,
      "learning_rate": 7.460317460317461e-05,
      "loss": 0.5743,
      "step": 460
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 1.669749140739441,
      "learning_rate": 7.301587301587302e-05,
      "loss": 0.5811,
      "step": 480
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 1.7088674306869507,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.5639,
      "step": 500
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 1.4929900169372559,
      "learning_rate": 6.984126984126984e-05,
      "loss": 0.5602,
      "step": 520
    },
    {
      "epoch": 0.38571428571428573,
      "grad_norm": 1.5759623050689697,
      "learning_rate": 6.825396825396825e-05,
      "loss": 0.5375,
      "step": 540
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1905630826950073,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.528,
      "step": 560
    },
    {
      "epoch": 0.4142857142857143,
      "grad_norm": 1.3444722890853882,
      "learning_rate": 6.507936507936509e-05,
      "loss": 0.5504,
      "step": 580
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.388431429862976,
      "learning_rate": 6.349206349206349e-05,
      "loss": 0.5425,
      "step": 600
    },
    {
      "epoch": 0.44285714285714284,
      "grad_norm": 1.4573171138763428,
      "learning_rate": 6.19047619047619e-05,
      "loss": 0.5461,
      "step": 620
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.4060829877853394,
      "learning_rate": 6.0317460317460316e-05,
      "loss": 0.5259,
      "step": 640
    },
    {
      "epoch": 0.4714285714285714,
      "grad_norm": 1.3451800346374512,
      "learning_rate": 5.873015873015873e-05,
      "loss": 0.5244,
      "step": 660
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 1.5249203443527222,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.5214,
      "step": 680
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.387425422668457,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.5014,
      "step": 700
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 1.4318238496780396,
      "learning_rate": 5.396825396825397e-05,
      "loss": 0.553,
      "step": 720
    },
    {
      "epoch": 0.5285714285714286,
      "grad_norm": 1.4433730840682983,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 0.5273,
      "step": 740
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 1.4052830934524536,
      "learning_rate": 5.0793650793650794e-05,
      "loss": 0.5331,
      "step": 760
    },
    {
      "epoch": 0.5571428571428572,
      "grad_norm": 1.4758517742156982,
      "learning_rate": 4.9206349206349204e-05,
      "loss": 0.5138,
      "step": 780
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.4489214420318604,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.5194,
      "step": 800
    },
    {
      "epoch": 0.5857142857142857,
      "grad_norm": 1.4176747798919678,
      "learning_rate": 4.603174603174603e-05,
      "loss": 0.5288,
      "step": 820
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.6866075992584229,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.5479,
      "step": 840
    },
    {
      "epoch": 0.6142857142857143,
      "grad_norm": 1.6059644222259521,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.5363,
      "step": 860
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 1.455381989479065,
      "learning_rate": 4.126984126984127e-05,
      "loss": 0.5019,
      "step": 880
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.6726956367492676,
      "learning_rate": 3.968253968253968e-05,
      "loss": 0.5084,
      "step": 900
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 1.8781988620758057,
      "learning_rate": 3.809523809523809e-05,
      "loss": 0.5251,
      "step": 920
    },
    {
      "epoch": 0.6714285714285714,
      "grad_norm": 1.7066335678100586,
      "learning_rate": 3.650793650793651e-05,
      "loss": 0.4725,
      "step": 940
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.7107722759246826,
      "learning_rate": 3.492063492063492e-05,
      "loss": 0.5251,
      "step": 960
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.4758689403533936,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.531,
      "step": 980
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.3672478199005127,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.5009,
      "step": 1000
    },
    {
      "epoch": 0.7285714285714285,
      "grad_norm": 1.4896430969238281,
      "learning_rate": 3.0158730158730158e-05,
      "loss": 0.5204,
      "step": 1020
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 1.2683701515197754,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.4953,
      "step": 1040
    },
    {
      "epoch": 0.7571428571428571,
      "grad_norm": 1.4984241724014282,
      "learning_rate": 2.6984126984126984e-05,
      "loss": 0.4819,
      "step": 1060
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 1.516722321510315,
      "learning_rate": 2.5396825396825397e-05,
      "loss": 0.4815,
      "step": 1080
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.7547037601470947,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.4803,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.368112564086914,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4984,
      "step": 1120
    },
    {
      "epoch": 0.8142857142857143,
      "grad_norm": 1.5048097372055054,
      "learning_rate": 2.0634920634920636e-05,
      "loss": 0.4843,
      "step": 1140
    },
    {
      "epoch": 0.8285714285714286,
      "grad_norm": 1.5499813556671143,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 0.4645,
      "step": 1160
    },
    {
      "epoch": 0.8428571428571429,
      "grad_norm": 1.5108025074005127,
      "learning_rate": 1.746031746031746e-05,
      "loss": 0.4868,
      "step": 1180
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.5287548303604126,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.4726,
      "step": 1200
    },
    {
      "epoch": 0.8714285714285714,
      "grad_norm": 1.441148042678833,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.4755,
      "step": 1220
    },
    {
      "epoch": 0.8857142857142857,
      "grad_norm": 1.4745419025421143,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 0.4786,
      "step": 1240
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.432034969329834,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.4827,
      "step": 1260
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.4481098651885986,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.4761,
      "step": 1280
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.5955500602722168,
      "learning_rate": 7.936507936507936e-06,
      "loss": 0.4582,
      "step": 1300
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 1.6500182151794434,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.492,
      "step": 1320
    },
    {
      "epoch": 0.9571428571428572,
      "grad_norm": 1.5469691753387451,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 0.4797,
      "step": 1340
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 1.6121824979782104,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 0.4938,
      "step": 1360
    },
    {
      "epoch": 0.9857142857142858,
      "grad_norm": 1.512402892112732,
      "learning_rate": 1.5873015873015873e-06,
      "loss": 0.4829,
      "step": 1380
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7282683849334717,
      "learning_rate": 0.0,
      "loss": 0.4737,
      "step": 1400
    }
  ],
  "logging_steps": 20,
  "max_steps": 1400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8419093040332800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}