{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 47.0,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.44166135787963867,
      "step": 5
    },
    {
      "epoch": 0.4,
      "grad_norm": 90.0,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.43323187828063964,
      "step": 10
    },
    {
      "epoch": 0.6,
      "grad_norm": 59.25,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 0.5504327774047851,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 53.25,
      "learning_rate": 3.0400000000000004e-05,
      "loss": 0.5285934448242188,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 87.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.8807684898376464,
      "step": 25
    },
    {
      "epoch": 1.2,
      "grad_norm": 130.0,
      "learning_rate": 3.9288888888888894e-05,
      "loss": 0.8127049446105957,
      "step": 30
    },
    {
      "epoch": 1.4,
      "grad_norm": 136.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 1.0883628845214843,
      "step": 35
    },
    {
      "epoch": 1.6,
      "grad_norm": 101.5,
      "learning_rate": 3.7511111111111116e-05,
      "loss": 1.1396523475646974,
      "step": 40
    },
    {
      "epoch": 1.8,
      "grad_norm": 117.0,
      "learning_rate": 3.662222222222223e-05,
      "loss": 1.1286127090454101,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 250.0,
      "learning_rate": 3.573333333333333e-05,
      "loss": -0.20869193077087403,
      "step": 50
    },
    {
      "epoch": 2.2,
      "grad_norm": 696.0,
      "learning_rate": 3.4844444444444444e-05,
      "loss": -6.911644744873047,
      "step": 55
    },
    {
      "epoch": 2.4,
      "grad_norm": 4256.0,
      "learning_rate": 3.395555555555556e-05,
      "loss": -45.076141357421875,
      "step": 60
    },
    {
      "epoch": 2.6,
      "grad_norm": 320.0,
      "learning_rate": 3.3066666666666666e-05,
      "loss": -68.7654541015625,
      "step": 65
    },
    {
      "epoch": 2.8,
      "grad_norm": 157.0,
      "learning_rate": 3.217777777777778e-05,
      "loss": -84.94921264648437,
      "step": 70
    },
    {
      "epoch": 3.0,
      "grad_norm": 193.0,
      "learning_rate": 3.1288888888888896e-05,
      "loss": -93.52960205078125,
      "step": 75
    },
    {
      "epoch": 3.2,
      "grad_norm": 128.0,
      "learning_rate": 3.0400000000000004e-05,
      "loss": -93.83045654296875,
      "step": 80
    },
    {
      "epoch": 3.4,
      "grad_norm": 124.0,
      "learning_rate": 2.951111111111111e-05,
      "loss": -95.073974609375,
      "step": 85
    },
    {
      "epoch": 3.6,
      "grad_norm": 152.0,
      "learning_rate": 2.8622222222222223e-05,
      "loss": -96.28338012695312,
      "step": 90
    },
    {
      "epoch": 3.8,
      "grad_norm": 126.0,
      "learning_rate": 2.7733333333333338e-05,
      "loss": -97.26625366210938,
      "step": 95
    },
    {
      "epoch": 4.0,
      "grad_norm": 132.0,
      "learning_rate": 2.6844444444444446e-05,
      "loss": -95.24658813476563,
      "step": 100
    },
    {
      "epoch": 4.2,
      "grad_norm": 129.0,
      "learning_rate": 2.5955555555555557e-05,
      "loss": -97.90447387695312,
      "step": 105
    },
    {
      "epoch": 4.4,
      "grad_norm": 127.0,
      "learning_rate": 2.5066666666666672e-05,
      "loss": -96.20138549804688,
      "step": 110
    },
    {
      "epoch": 4.6,
      "grad_norm": 308.0,
      "learning_rate": 2.417777777777778e-05,
      "loss": -97.29202880859376,
      "step": 115
    },
    {
      "epoch": 4.8,
      "grad_norm": 125.0,
      "learning_rate": 2.328888888888889e-05,
      "loss": -98.5575439453125,
      "step": 120
    },
    {
      "epoch": 5.0,
      "grad_norm": 124.0,
      "learning_rate": 2.2400000000000002e-05,
      "loss": -100.56572875976562,
      "step": 125
    },
    {
      "epoch": 5.2,
      "grad_norm": 122.0,
      "learning_rate": 2.1511111111111114e-05,
      "loss": -100.512109375,
      "step": 130
    },
    {
      "epoch": 5.4,
      "grad_norm": 129.0,
      "learning_rate": 2.0622222222222225e-05,
      "loss": -101.71362915039063,
      "step": 135
    },
    {
      "epoch": 5.6,
      "grad_norm": 122.0,
      "learning_rate": 1.9733333333333336e-05,
      "loss": -99.4461669921875,
      "step": 140
    },
    {
      "epoch": 5.8,
      "grad_norm": 125.0,
      "learning_rate": 1.8844444444444444e-05,
      "loss": -101.84241333007813,
      "step": 145
    },
    {
      "epoch": 6.0,
      "grad_norm": 156.0,
      "learning_rate": 1.7955555555555556e-05,
      "loss": -104.2747314453125,
      "step": 150
    },
    {
      "epoch": 6.2,
      "grad_norm": 176.0,
      "learning_rate": 1.706666666666667e-05,
      "loss": -104.3238037109375,
      "step": 155
    },
    {
      "epoch": 6.4,
      "grad_norm": 132.0,
      "learning_rate": 1.617777777777778e-05,
      "loss": -104.5203125,
      "step": 160
    },
    {
      "epoch": 6.6,
      "grad_norm": 125.5,
      "learning_rate": 1.528888888888889e-05,
      "loss": -100.71946411132812,
      "step": 165
    },
    {
      "epoch": 6.8,
      "grad_norm": 139.0,
      "learning_rate": 1.4400000000000001e-05,
      "loss": -104.731396484375,
      "step": 170
    },
    {
      "epoch": 7.0,
      "grad_norm": 157.0,
      "learning_rate": 1.3511111111111112e-05,
      "loss": -102.12015380859376,
      "step": 175
    },
    {
      "epoch": 7.2,
      "grad_norm": 123.5,
      "learning_rate": 1.2622222222222222e-05,
      "loss": -104.81466064453124,
      "step": 180
    },
    {
      "epoch": 7.4,
      "grad_norm": 128.0,
      "learning_rate": 1.1733333333333335e-05,
      "loss": -103.458349609375,
      "step": 185
    },
    {
      "epoch": 7.6,
      "grad_norm": 127.5,
      "learning_rate": 1.0844444444444446e-05,
      "loss": -103.835107421875,
      "step": 190
    },
    {
      "epoch": 7.8,
      "grad_norm": 143.0,
      "learning_rate": 9.955555555555556e-06,
      "loss": -104.95999755859376,
      "step": 195
    },
    {
      "epoch": 8.0,
      "grad_norm": 134.0,
      "learning_rate": 9.066666666666667e-06,
      "loss": -104.40067138671876,
      "step": 200
    },
    {
      "epoch": 8.2,
      "grad_norm": 6560.0,
      "learning_rate": 8.177777777777779e-06,
      "loss": -103.65928955078125,
      "step": 205
    },
    {
      "epoch": 8.4,
      "grad_norm": 122.0,
      "learning_rate": 7.28888888888889e-06,
      "loss": -102.37640991210938,
      "step": 210
    },
    {
      "epoch": 8.6,
      "grad_norm": 122.0,
      "learning_rate": 6.4000000000000006e-06,
      "loss": -102.38164672851562,
      "step": 215
    },
    {
      "epoch": 8.8,
      "grad_norm": 140.0,
      "learning_rate": 5.511111111111112e-06,
      "loss": -105.20797119140624,
      "step": 220
    },
    {
      "epoch": 9.0,
      "grad_norm": 123.5,
      "learning_rate": 4.622222222222222e-06,
      "loss": -102.82015380859374,
      "step": 225
    },
    {
      "epoch": 9.2,
      "grad_norm": 119.5,
      "learning_rate": 3.7333333333333337e-06,
      "loss": -102.04013061523438,
      "step": 230
    },
    {
      "epoch": 9.4,
      "grad_norm": 124.0,
      "learning_rate": 2.8444444444444446e-06,
      "loss": -104.92872314453125,
      "step": 235
    },
    {
      "epoch": 9.6,
      "grad_norm": 125.0,
      "learning_rate": 1.955555555555556e-06,
      "loss": -105.53155517578125,
      "step": 240
    },
    {
      "epoch": 9.8,
      "grad_norm": 186.0,
      "learning_rate": 1.066666666666667e-06,
      "loss": -103.87576904296876,
      "step": 245
    },
    {
      "epoch": 10.0,
      "grad_norm": 123.5,
      "learning_rate": 1.777777777777778e-07,
      "loss": -105.57698974609374,
      "step": 250
    },
    {
      "epoch": 10.0,
      "step": 250,
      "total_flos": 0.0,
      "train_loss": -76.89460292816162,
      "train_runtime": 380.0623,
      "train_samples_per_second": 10.525,
      "train_steps_per_second": 0.658
    }
  ],
  "logging_steps": 5,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}