{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 17.142857142857142,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 4.297126293182373,
      "learning_rate": 5e-06,
      "loss": 2.0584,
      "step": 1
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 5.442339897155762,
      "learning_rate": 1e-05,
      "loss": 2.1704,
      "step": 2
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 3.8550186157226562,
      "learning_rate": 1.5e-05,
      "loss": 1.9811,
      "step": 3
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 4.534988880157471,
      "learning_rate": 2e-05,
      "loss": 1.9627,
      "step": 4
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 4.389001846313477,
      "learning_rate": 2.5e-05,
      "loss": 1.8195,
      "step": 5
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 2.9333465099334717,
      "learning_rate": 3e-05,
      "loss": 1.7995,
      "step": 6
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.8814234733581543,
      "learning_rate": 3.5e-05,
      "loss": 1.6025,
      "step": 7
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 3.1065313816070557,
      "learning_rate": 4e-05,
      "loss": 1.4849,
      "step": 8
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 3.8952481746673584,
      "learning_rate": 4.5e-05,
      "loss": 1.4171,
      "step": 9
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 2.2721009254455566,
      "learning_rate": 5e-05,
      "loss": 1.3011,
      "step": 10
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 1.9634448289871216,
      "learning_rate": 4.9e-05,
      "loss": 1.2701,
      "step": 11
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 1.7538613080978394,
      "learning_rate": 4.8e-05,
      "loss": 1.1454,
      "step": 12
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 1.5953209400177002,
      "learning_rate": 4.7e-05,
      "loss": 1.1024,
      "step": 13
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.5740618705749512,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.995,
      "step": 14
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 1.4993911981582642,
      "learning_rate": 4.5e-05,
      "loss": 1.042,
      "step": 15
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 2.0913941860198975,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.8267,
      "step": 16
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 1.1753151416778564,
      "learning_rate": 4.3e-05,
      "loss": 0.7648,
      "step": 17
    },
    {
      "epoch": 5.142857142857143,
      "grad_norm": 1.2862088680267334,
      "learning_rate": 4.2e-05,
      "loss": 0.866,
      "step": 18
    },
    {
      "epoch": 5.428571428571429,
      "grad_norm": 0.9621393084526062,
      "learning_rate": 4.1e-05,
      "loss": 0.7878,
      "step": 19
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 1.2728854417800903,
      "learning_rate": 4e-05,
      "loss": 0.6709,
      "step": 20
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9635931253433228,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.7501,
      "step": 21
    },
    {
      "epoch": 6.285714285714286,
      "grad_norm": 0.8941543698310852,
      "learning_rate": 3.8e-05,
      "loss": 0.7428,
      "step": 22
    },
    {
      "epoch": 6.571428571428571,
      "grad_norm": 1.032415747642517,
      "learning_rate": 3.7e-05,
      "loss": 0.5109,
      "step": 23
    },
    {
      "epoch": 6.857142857142857,
      "grad_norm": 1.1366804838180542,
      "learning_rate": 3.6e-05,
      "loss": 0.6937,
      "step": 24
    },
    {
      "epoch": 7.142857142857143,
      "grad_norm": 1.0126097202301025,
      "learning_rate": 3.5e-05,
      "loss": 0.6131,
      "step": 25
    },
    {
      "epoch": 7.428571428571429,
      "grad_norm": 1.0203325748443604,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.6236,
      "step": 26
    },
    {
      "epoch": 7.714285714285714,
      "grad_norm": 1.1223379373550415,
      "learning_rate": 3.3e-05,
      "loss": 0.4396,
      "step": 27
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.156301498413086,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.6135,
      "step": 28
    },
    {
      "epoch": 8.285714285714286,
      "grad_norm": 1.3308717012405396,
      "learning_rate": 3.1e-05,
      "loss": 0.4818,
      "step": 29
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 1.0889034271240234,
      "learning_rate": 3e-05,
      "loss": 0.5571,
      "step": 30
    },
    {
      "epoch": 8.857142857142858,
      "grad_norm": 1.2153044939041138,
      "learning_rate": 2.9e-05,
      "loss": 0.4891,
      "step": 31
    },
    {
      "epoch": 9.142857142857142,
      "grad_norm": 1.2152674198150635,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.5333,
      "step": 32
    },
    {
      "epoch": 9.428571428571429,
      "grad_norm": 1.1658018827438354,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.4143,
      "step": 33
    },
    {
      "epoch": 9.714285714285714,
      "grad_norm": 1.2498981952667236,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.3726,
      "step": 34
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.313835620880127,
      "learning_rate": 2.5e-05,
      "loss": 0.3324,
      "step": 35
    },
    {
      "epoch": 10.285714285714286,
      "grad_norm": 1.2041679620742798,
      "learning_rate": 2.4e-05,
      "loss": 0.3397,
      "step": 36
    },
    {
      "epoch": 10.571428571428571,
      "grad_norm": 1.312419056892395,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.4332,
      "step": 37
    },
    {
      "epoch": 10.857142857142858,
      "grad_norm": 1.392309546470642,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.2769,
      "step": 38
    },
    {
      "epoch": 11.142857142857142,
      "grad_norm": 1.255035638809204,
      "learning_rate": 2.1e-05,
      "loss": 0.4282,
      "step": 39
    },
    {
      "epoch": 11.428571428571429,
      "grad_norm": 1.450054407119751,
      "learning_rate": 2e-05,
      "loss": 0.2118,
      "step": 40
    },
    {
      "epoch": 11.714285714285714,
      "grad_norm": 1.3045405149459839,
      "learning_rate": 1.9e-05,
      "loss": 0.2816,
      "step": 41
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.3475886583328247,
      "learning_rate": 1.8e-05,
      "loss": 0.2846,
      "step": 42
    },
    {
      "epoch": 12.285714285714286,
      "grad_norm": 1.299771785736084,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.335,
      "step": 43
    },
    {
      "epoch": 12.571428571428571,
      "grad_norm": 1.272226333618164,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2031,
      "step": 44
    },
    {
      "epoch": 12.857142857142858,
      "grad_norm": 1.7329617738723755,
      "learning_rate": 1.5e-05,
      "loss": 0.2738,
      "step": 45
    },
    {
      "epoch": 13.142857142857142,
      "grad_norm": 1.6047208309173584,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.2792,
      "step": 46
    },
    {
      "epoch": 13.428571428571429,
      "grad_norm": 1.2631847858428955,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.2651,
      "step": 47
    },
    {
      "epoch": 13.714285714285714,
      "grad_norm": 1.3166191577911377,
      "learning_rate": 1.2e-05,
      "loss": 0.1932,
      "step": 48
    },
    {
      "epoch": 14.0,
      "grad_norm": 1.5138972997665405,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.2165,
      "step": 49
    },
    {
      "epoch": 14.285714285714286,
      "grad_norm": 1.1001005172729492,
      "learning_rate": 1e-05,
      "loss": 0.1508,
      "step": 50
    },
    {
      "epoch": 14.571428571428571,
      "grad_norm": 1.3192509412765503,
      "learning_rate": 9e-06,
      "loss": 0.2484,
      "step": 51
    },
    {
      "epoch": 14.857142857142858,
      "grad_norm": 1.7928791046142578,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1838,
      "step": 52
    },
    {
      "epoch": 15.142857142857142,
      "grad_norm": 1.579509973526001,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.2775,
      "step": 53
    },
    {
      "epoch": 15.428571428571429,
      "grad_norm": 1.0521697998046875,
      "learning_rate": 6e-06,
      "loss": 0.147,
      "step": 54
    },
    {
      "epoch": 15.714285714285714,
      "grad_norm": 1.6448253393173218,
      "learning_rate": 5e-06,
      "loss": 0.2041,
      "step": 55
    },
    {
      "epoch": 16.0,
      "grad_norm": 1.2469841241836548,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.1623,
      "step": 56
    },
    {
      "epoch": 16.285714285714285,
      "grad_norm": 1.1743882894515991,
      "learning_rate": 3e-06,
      "loss": 0.1822,
      "step": 57
    },
    {
      "epoch": 16.571428571428573,
      "grad_norm": 1.246579885482788,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.2199,
      "step": 58
    },
    {
      "epoch": 16.857142857142858,
      "grad_norm": 1.1595028638839722,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.1361,
      "step": 59
    },
    {
      "epoch": 17.142857142857142,
      "grad_norm": 1.380496859550476,
      "learning_rate": 0.0,
      "loss": 0.1335,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2902028263292928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}