{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 57,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 2.3391265869140625,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.2932,
      "step": 1
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 2.1669816970825195,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.2642,
      "step": 2
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 2.2039060592651367,
      "learning_rate": 1.5e-06,
      "loss": 1.2409,
      "step": 3
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 2.185878038406372,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.244,
      "step": 4
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 2.1814076900482178,
      "learning_rate": 2.5e-06,
      "loss": 1.1757,
      "step": 5
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 2.100562334060669,
      "learning_rate": 3e-06,
      "loss": 1.2375,
      "step": 6
    },
    {
      "epoch": 0.3848797250859107,
      "grad_norm": 2.1685991287231445,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 1.218,
      "step": 7
    },
    {
      "epoch": 0.43986254295532645,
      "grad_norm": 2.6219348907470703,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3291,
      "step": 8
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 2.053830862045288,
      "learning_rate": 4.5e-06,
      "loss": 1.2892,
      "step": 9
    },
    {
      "epoch": 0.5498281786941581,
      "grad_norm": 2.335982084274292,
      "learning_rate": 5e-06,
      "loss": 1.2636,
      "step": 10
    },
    {
      "epoch": 0.6048109965635738,
      "grad_norm": 2.1228444576263428,
      "learning_rate": 5.500000000000001e-06,
      "loss": 1.2267,
      "step": 11
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 2.169857978820801,
      "learning_rate": 6e-06,
      "loss": 1.2454,
      "step": 12
    },
    {
      "epoch": 0.7147766323024055,
      "grad_norm": 2.084686279296875,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 1.1907,
      "step": 13
    },
    {
      "epoch": 0.7697594501718213,
      "grad_norm": 2.284982442855835,
      "learning_rate": 7.000000000000001e-06,
      "loss": 1.2998,
      "step": 14
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 1.9793288707733154,
      "learning_rate": 7.5e-06,
      "loss": 1.2019,
      "step": 15
    },
    {
      "epoch": 0.8797250859106529,
      "grad_norm": 1.9528135061264038,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2003,
      "step": 16
    },
    {
      "epoch": 0.9347079037800687,
      "grad_norm": 1.9243836402893066,
      "learning_rate": 8.500000000000002e-06,
      "loss": 1.1621,
      "step": 17
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 1.9052047729492188,
      "learning_rate": 9e-06,
      "loss": 1.1504,
      "step": 18
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.759420394897461,
      "learning_rate": 9.5e-06,
      "loss": 1.2492,
      "step": 19
    },
    {
      "epoch": 1.0549828178694158,
      "grad_norm": 1.8658391237258911,
      "learning_rate": 1e-05,
      "loss": 1.1941,
      "step": 20
    },
    {
      "epoch": 1.1099656357388317,
      "grad_norm": 1.8759143352508545,
      "learning_rate": 1.05e-05,
      "loss": 1.1509,
      "step": 21
    },
    {
      "epoch": 1.1649484536082475,
      "grad_norm": 1.7013018131256104,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.0713,
      "step": 22
    },
    {
      "epoch": 1.2199312714776633,
      "grad_norm": 1.4075945615768433,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 1.0761,
      "step": 23
    },
    {
      "epoch": 1.274914089347079,
      "grad_norm": 1.4849729537963867,
      "learning_rate": 1.2e-05,
      "loss": 1.0839,
      "step": 24
    },
    {
      "epoch": 1.3298969072164948,
      "grad_norm": 1.3940335512161255,
      "learning_rate": 1.25e-05,
      "loss": 1.0349,
      "step": 25
    },
    {
      "epoch": 1.3848797250859106,
      "grad_norm": 1.248413324356079,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.1078,
      "step": 26
    },
    {
      "epoch": 1.4398625429553265,
      "grad_norm": 1.2348881959915161,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 1.0563,
      "step": 27
    },
    {
      "epoch": 1.4948453608247423,
      "grad_norm": 1.1840934753417969,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.117,
      "step": 28
    },
    {
      "epoch": 1.5498281786941581,
      "grad_norm": 0.9969284534454346,
      "learning_rate": 1.45e-05,
      "loss": 1.0499,
      "step": 29
    },
    {
      "epoch": 1.604810996563574,
      "grad_norm": 1.0228712558746338,
      "learning_rate": 1.5e-05,
      "loss": 0.9143,
      "step": 30
    },
    {
      "epoch": 1.6597938144329896,
      "grad_norm": 0.8392165303230286,
      "learning_rate": 1.55e-05,
      "loss": 1.0712,
      "step": 31
    },
    {
      "epoch": 1.7147766323024056,
      "grad_norm": 0.6976754069328308,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.9455,
      "step": 32
    },
    {
      "epoch": 1.7697594501718212,
      "grad_norm": 0.7253638505935669,
      "learning_rate": 1.65e-05,
      "loss": 0.8994,
      "step": 33
    },
    {
      "epoch": 1.824742268041237,
      "grad_norm": 0.5587965846061707,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.8769,
      "step": 34
    },
    {
      "epoch": 1.879725085910653,
      "grad_norm": 0.5404813885688782,
      "learning_rate": 1.75e-05,
      "loss": 0.8509,
      "step": 35
    },
    {
      "epoch": 1.9347079037800687,
      "grad_norm": 0.4780674874782562,
      "learning_rate": 1.8e-05,
      "loss": 0.9384,
      "step": 36
    },
    {
      "epoch": 1.9896907216494846,
      "grad_norm": 0.4203198254108429,
      "learning_rate": 1.85e-05,
      "loss": 0.8815,
      "step": 37
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5001429319381714,
      "learning_rate": 1.9e-05,
      "loss": 0.9702,
      "step": 38
    },
    {
      "epoch": 2.0549828178694156,
      "grad_norm": 0.33664512634277344,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.8686,
      "step": 39
    },
    {
      "epoch": 2.1099656357388317,
      "grad_norm": 0.3299224376678467,
      "learning_rate": 2e-05,
      "loss": 0.9143,
      "step": 40
    },
    {
      "epoch": 2.1649484536082473,
      "grad_norm": 0.3843877911567688,
      "learning_rate": 2.05e-05,
      "loss": 0.7757,
      "step": 41
    },
    {
      "epoch": 2.2199312714776633,
      "grad_norm": 0.2754301428794861,
      "learning_rate": 2.1e-05,
      "loss": 0.8514,
      "step": 42
    },
    {
      "epoch": 2.274914089347079,
      "grad_norm": 0.27374932169914246,
      "learning_rate": 2.15e-05,
      "loss": 0.7997,
      "step": 43
    },
    {
      "epoch": 2.329896907216495,
      "grad_norm": 0.2719466984272003,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.8819,
      "step": 44
    },
    {
      "epoch": 2.3848797250859106,
      "grad_norm": 0.2750904858112335,
      "learning_rate": 2.25e-05,
      "loss": 0.7952,
      "step": 45
    },
    {
      "epoch": 2.4398625429553267,
      "grad_norm": 0.20324264466762543,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.8438,
      "step": 46
    },
    {
      "epoch": 2.4948453608247423,
      "grad_norm": 0.22448420524597168,
      "learning_rate": 2.35e-05,
      "loss": 0.8569,
      "step": 47
    },
    {
      "epoch": 2.549828178694158,
      "grad_norm": 0.3943282961845398,
      "learning_rate": 2.4e-05,
      "loss": 0.7743,
      "step": 48
    },
    {
      "epoch": 2.604810996563574,
      "grad_norm": 0.23266704380512238,
      "learning_rate": 2.45e-05,
      "loss": 0.8089,
      "step": 49
    },
    {
      "epoch": 2.6597938144329896,
      "grad_norm": 0.1900027096271515,
      "learning_rate": 2.5e-05,
      "loss": 0.8926,
      "step": 50
    },
    {
      "epoch": 2.7147766323024056,
      "grad_norm": 0.19019268453121185,
      "learning_rate": 2.5500000000000003e-05,
      "loss": 0.7765,
      "step": 51
    },
    {
      "epoch": 2.7697594501718212,
      "grad_norm": 0.2077689915895462,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.763,
      "step": 52
    },
    {
      "epoch": 2.824742268041237,
      "grad_norm": 0.1671900600194931,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 0.7413,
      "step": 53
    },
    {
      "epoch": 2.879725085910653,
      "grad_norm": 0.2202858328819275,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.7761,
      "step": 54
    },
    {
      "epoch": 2.934707903780069,
      "grad_norm": 0.18933026492595673,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.8357,
      "step": 55
    },
    {
      "epoch": 2.9896907216494846,
      "grad_norm": 0.19358232617378235,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.8198,
      "step": 56
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2464047223329544,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 0.7364,
      "step": 57
    },
    {
      "epoch": 3.0,
      "step": 57,
      "total_flos": 2.0642424594366464e+16,
      "train_loss": 1.0225378860507095,
      "train_runtime": 36983.6897,
      "train_samples_per_second": 0.094,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 57,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.0642424594366464e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}