{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013157894736842105,
      "grad_norm": 30.562854766845703,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.2022,
      "step": 1
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 31.231891632080078,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.2332,
      "step": 2
    },
    {
      "epoch": 0.039473684210526314,
      "grad_norm": 30.672441482543945,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.1838,
      "step": 3
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 30.322587966918945,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.1722,
      "step": 4
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 30.77847671508789,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.1905,
      "step": 5
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 30.271461486816406,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.152,
      "step": 6
    },
    {
      "epoch": 0.09210526315789473,
      "grad_norm": 30.211917877197266,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.1535,
      "step": 7
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 30.876808166503906,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.1821,
      "step": 8
    },
    {
      "epoch": 0.11842105263157894,
      "grad_norm": 30.311782836914062,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.1493,
      "step": 9
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 29.994876861572266,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.1006,
      "step": 10
    },
    {
      "epoch": 0.14473684210526316,
      "grad_norm": 30.387903213500977,
      "learning_rate": 5.5e-07,
      "loss": 2.1116,
      "step": 11
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 29.694482803344727,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.0657,
      "step": 12
    },
    {
      "epoch": 0.17105263157894737,
      "grad_norm": 29.319564819335938,
      "learning_rate": 6.5e-07,
      "loss": 2.0295,
      "step": 13
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 29.47940444946289,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.0205,
      "step": 14
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 28.094648361206055,
      "learning_rate": 7.5e-07,
      "loss": 1.9182,
      "step": 15
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 27.290010452270508,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.8242,
      "step": 16
    },
    {
      "epoch": 0.2236842105263158,
      "grad_norm": 27.355669021606445,
      "learning_rate": 8.500000000000001e-07,
      "loss": 1.8095,
      "step": 17
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 26.473133087158203,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.7021,
      "step": 18
    },
    {
      "epoch": 0.25,
      "grad_norm": 25.996793746948242,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.6026,
      "step": 19
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 25.409788131713867,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.4958,
      "step": 20
    },
    {
      "epoch": 0.27631578947368424,
      "grad_norm": 25.045166015625,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.3705,
      "step": 21
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 24.878185272216797,
      "learning_rate": 1.1e-06,
      "loss": 1.2165,
      "step": 22
    },
    {
      "epoch": 0.3026315789473684,
      "grad_norm": 24.428897857666016,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.0541,
      "step": 23
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 23.59629249572754,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.8731,
      "step": 24
    },
    {
      "epoch": 0.32894736842105265,
      "grad_norm": 22.640525817871094,
      "learning_rate": 1.25e-06,
      "loss": 0.6974,
      "step": 25
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 20.182687759399414,
      "learning_rate": 1.3e-06,
      "loss": 0.5304,
      "step": 26
    },
    {
      "epoch": 0.35526315789473684,
      "grad_norm": 16.674095153808594,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.3994,
      "step": 27
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 11.497395515441895,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.2574,
      "step": 28
    },
    {
      "epoch": 0.3815789473684211,
      "grad_norm": 7.353602886199951,
      "learning_rate": 1.45e-06,
      "loss": 0.192,
      "step": 29
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 5.207138538360596,
      "learning_rate": 1.5e-06,
      "loss": 0.1373,
      "step": 30
    },
    {
      "epoch": 0.40789473684210525,
      "grad_norm": 3.827702522277832,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1182,
      "step": 31
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 2.3438303470611572,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.0889,
      "step": 32
    },
    {
      "epoch": 0.4342105263157895,
      "grad_norm": 1.3860067129135132,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.079,
      "step": 33
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 1.272938847541809,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0716,
      "step": 34
    },
    {
      "epoch": 0.4605263157894737,
      "grad_norm": 1.0202291011810303,
      "learning_rate": 1.75e-06,
      "loss": 0.0669,
      "step": 35
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.7427852153778076,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0553,
      "step": 36
    },
    {
      "epoch": 0.4868421052631579,
      "grad_norm": 0.633512020111084,
      "learning_rate": 1.85e-06,
      "loss": 0.059,
      "step": 37
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.4689115285873413,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0513,
      "step": 38
    },
    {
      "epoch": 0.5131578947368421,
      "grad_norm": 0.5156136751174927,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0447,
      "step": 39
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.4687592387199402,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0478,
      "step": 40
    },
    {
      "epoch": 0.5394736842105263,
      "grad_norm": 0.6448376774787903,
      "learning_rate": 2.05e-06,
      "loss": 0.0453,
      "step": 41
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 0.526674211025238,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0479,
      "step": 42
    },
    {
      "epoch": 0.5657894736842105,
      "grad_norm": 0.5008970499038696,
      "learning_rate": 2.15e-06,
      "loss": 0.0413,
      "step": 43
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.47381266951560974,
      "learning_rate": 2.2e-06,
      "loss": 0.0454,
      "step": 44
    },
    {
      "epoch": 0.5921052631578947,
      "grad_norm": 0.5133708715438843,
      "learning_rate": 2.25e-06,
      "loss": 0.0405,
      "step": 45
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 0.3338497579097748,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0399,
      "step": 46
    },
    {
      "epoch": 0.618421052631579,
      "grad_norm": 0.36396729946136475,
      "learning_rate": 2.35e-06,
      "loss": 0.0376,
      "step": 47
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.24808718264102936,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0398,
      "step": 48
    },
    {
      "epoch": 0.6447368421052632,
      "grad_norm": 0.4498325288295746,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0379,
      "step": 49
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.3247833251953125,
      "learning_rate": 2.5e-06,
      "loss": 0.0347,
      "step": 50
    },
    {
      "epoch": 0.6710526315789473,
      "grad_norm": 0.5700550675392151,
      "learning_rate": 2.55e-06,
      "loss": 0.0401,
      "step": 51
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.40577009320259094,
      "learning_rate": 2.6e-06,
      "loss": 0.0445,
      "step": 52
    },
    {
      "epoch": 0.6973684210526315,
      "grad_norm": 0.26929962635040283,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0374,
      "step": 53
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 0.2586027979850769,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0367,
      "step": 54
    },
    {
      "epoch": 0.7236842105263158,
      "grad_norm": 0.37353914976119995,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0374,
      "step": 55
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.24289675056934357,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0367,
      "step": 56
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3887583315372467,
      "learning_rate": 2.85e-06,
      "loss": 0.0341,
      "step": 57
    },
    {
      "epoch": 0.7631578947368421,
      "grad_norm": 0.2641527056694031,
      "learning_rate": 2.9e-06,
      "loss": 0.0396,
      "step": 58
    },
    {
      "epoch": 0.7763157894736842,
      "grad_norm": 0.3535292446613312,
      "learning_rate": 2.95e-06,
      "loss": 0.0353,
      "step": 59
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.28277266025543213,
      "learning_rate": 3e-06,
      "loss": 0.0297,
      "step": 60
    },
    {
      "epoch": 0.8026315789473685,
      "grad_norm": 0.3220183253288269,
      "learning_rate": 3.05e-06,
      "loss": 0.034,
      "step": 61
    },
    {
      "epoch": 0.8157894736842105,
      "grad_norm": 0.35354799032211304,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0334,
      "step": 62
    },
    {
      "epoch": 0.8289473684210527,
      "grad_norm": 0.290508896112442,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0326,
      "step": 63
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.37485048174858093,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0341,
      "step": 64
    },
    {
      "epoch": 0.8552631578947368,
      "grad_norm": 0.30379700660705566,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0312,
      "step": 65
    },
    {
      "epoch": 0.868421052631579,
      "grad_norm": 0.4121778905391693,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0307,
      "step": 66
    },
    {
      "epoch": 0.881578947368421,
      "grad_norm": 0.4124625325202942,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.034,
      "step": 67
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.47734567523002625,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0341,
      "step": 68
    },
    {
      "epoch": 0.9078947368421053,
      "grad_norm": 0.24404998123645782,
      "learning_rate": 3.45e-06,
      "loss": 0.0304,
      "step": 69
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.3431500196456909,
      "learning_rate": 3.5e-06,
      "loss": 0.0334,
      "step": 70
    },
    {
      "epoch": 0.9342105263157895,
      "grad_norm": 0.19714811444282532,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0302,
      "step": 71
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.3125874996185303,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0286,
      "step": 72
    },
    {
      "epoch": 0.9605263157894737,
      "grad_norm": 0.2595495879650116,
      "learning_rate": 3.65e-06,
      "loss": 0.0316,
      "step": 73
    },
    {
      "epoch": 0.9736842105263158,
      "grad_norm": 0.2165302336215973,
      "learning_rate": 3.7e-06,
      "loss": 0.0289,
      "step": 74
    },
    {
      "epoch": 0.9868421052631579,
      "grad_norm": 0.268668532371521,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0279,
      "step": 75
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.32586586475372314,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0304,
      "step": 76
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 76,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.889219280312205e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}