{
  "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": 2.2747802734375,
      "learning_rate": 5.000000000000001e-07,
      "loss": 1.2932,
      "step": 1
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 2.124077796936035,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.2642,
      "step": 2
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 2.1374475955963135,
      "learning_rate": 1.5e-06,
      "loss": 1.2401,
      "step": 3
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 2.113400459289551,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.2434,
      "step": 4
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 2.054466962814331,
      "learning_rate": 2.5e-06,
      "loss": 1.175,
      "step": 5
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 2.11995267868042,
      "learning_rate": 3e-06,
      "loss": 1.2371,
      "step": 6
    },
    {
      "epoch": 0.3848797250859107,
      "grad_norm": 2.1266541481018066,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 1.2172,
      "step": 7
    },
    {
      "epoch": 0.43986254295532645,
      "grad_norm": 2.604534149169922,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3291,
      "step": 8
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 1.9917025566101074,
      "learning_rate": 4.5e-06,
      "loss": 1.2904,
      "step": 9
    },
    {
      "epoch": 0.5498281786941581,
      "grad_norm": 2.2239606380462646,
      "learning_rate": 5e-06,
      "loss": 1.265,
      "step": 10
    },
    {
      "epoch": 0.6048109965635738,
      "grad_norm": 2.1611850261688232,
      "learning_rate": 5.500000000000001e-06,
      "loss": 1.2288,
      "step": 11
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 2.019578218460083,
      "learning_rate": 6e-06,
      "loss": 1.2479,
      "step": 12
    },
    {
      "epoch": 0.7147766323024055,
      "grad_norm": 2.0458662509918213,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 1.1926,
      "step": 13
    },
    {
      "epoch": 0.7697594501718213,
      "grad_norm": 2.325169563293457,
      "learning_rate": 7.000000000000001e-06,
      "loss": 1.3024,
      "step": 14
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 1.9853283166885376,
      "learning_rate": 7.5e-06,
      "loss": 1.2042,
      "step": 15
    },
    {
      "epoch": 0.8797250859106529,
      "grad_norm": 1.977973461151123,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2033,
      "step": 16
    },
    {
      "epoch": 0.9347079037800687,
      "grad_norm": 1.934755802154541,
      "learning_rate": 8.500000000000002e-06,
      "loss": 1.1652,
      "step": 17
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 1.8828901052474976,
      "learning_rate": 9e-06,
      "loss": 1.1532,
      "step": 18
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.7150800228118896,
      "learning_rate": 9.5e-06,
      "loss": 1.2575,
      "step": 19
    },
    {
      "epoch": 1.0549828178694158,
      "grad_norm": 1.868530035018921,
      "learning_rate": 1e-05,
      "loss": 1.1978,
      "step": 20
    },
    {
      "epoch": 1.1099656357388317,
      "grad_norm": 1.8736613988876343,
      "learning_rate": 1.05e-05,
      "loss": 1.1551,
      "step": 21
    },
    {
      "epoch": 1.1649484536082475,
      "grad_norm": 1.703709363937378,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.0762,
      "step": 22
    },
    {
      "epoch": 1.2199312714776633,
      "grad_norm": 1.3763967752456665,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 1.0799,
      "step": 23
    },
    {
      "epoch": 1.274914089347079,
      "grad_norm": 1.4954501390457153,
      "learning_rate": 1.2e-05,
      "loss": 1.0878,
      "step": 24
    },
    {
      "epoch": 1.3298969072164948,
      "grad_norm": 1.3895385265350342,
      "learning_rate": 1.25e-05,
      "loss": 1.0389,
      "step": 25
    },
    {
      "epoch": 1.3848797250859106,
      "grad_norm": 1.2851823568344116,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.111,
      "step": 26
    },
    {
      "epoch": 1.4398625429553265,
      "grad_norm": 1.243282675743103,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 1.0603,
      "step": 27
    },
    {
      "epoch": 1.4948453608247423,
      "grad_norm": 1.201363205909729,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.1227,
      "step": 28
    },
    {
      "epoch": 1.5498281786941581,
      "grad_norm": 0.9723503589630127,
      "learning_rate": 1.45e-05,
      "loss": 1.0546,
      "step": 29
    },
    {
      "epoch": 1.604810996563574,
      "grad_norm": 1.017640233039856,
      "learning_rate": 1.5e-05,
      "loss": 0.9198,
      "step": 30
    },
    {
      "epoch": 1.6597938144329896,
      "grad_norm": 0.850871205329895,
      "learning_rate": 1.55e-05,
      "loss": 1.0753,
      "step": 31
    },
    {
      "epoch": 1.7147766323024056,
      "grad_norm": 0.6708624958992004,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.9494,
      "step": 32
    },
    {
      "epoch": 1.7697594501718212,
      "grad_norm": 0.7221150994300842,
      "learning_rate": 1.65e-05,
      "loss": 0.9031,
      "step": 33
    },
    {
      "epoch": 1.824742268041237,
      "grad_norm": 0.5405407547950745,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.8795,
      "step": 34
    },
    {
      "epoch": 1.879725085910653,
      "grad_norm": 0.46711477637290955,
      "learning_rate": 1.75e-05,
      "loss": 0.8542,
      "step": 35
    },
    {
      "epoch": 1.9347079037800687,
      "grad_norm": 0.49648287892341614,
      "learning_rate": 1.8e-05,
      "loss": 0.9417,
      "step": 36
    },
    {
      "epoch": 1.9896907216494846,
      "grad_norm": 0.3698864281177521,
      "learning_rate": 1.85e-05,
      "loss": 0.884,
      "step": 37
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.48004987835884094,
      "learning_rate": 1.9e-05,
      "loss": 0.9747,
      "step": 38
    },
    {
      "epoch": 2.0549828178694156,
      "grad_norm": 0.31297996640205383,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.8711,
      "step": 39
    },
    {
      "epoch": 2.1099656357388317,
      "grad_norm": 0.3257434666156769,
      "learning_rate": 2e-05,
      "loss": 0.9167,
      "step": 40
    },
    {
      "epoch": 2.1649484536082473,
      "grad_norm": 0.3740560710430145,
      "learning_rate": 2.05e-05,
      "loss": 0.7789,
      "step": 41
    },
    {
      "epoch": 2.2199312714776633,
      "grad_norm": 0.26695382595062256,
      "learning_rate": 2.1e-05,
      "loss": 0.854,
      "step": 42
    },
    {
      "epoch": 2.274914089347079,
      "grad_norm": 0.2634020447731018,
      "learning_rate": 2.15e-05,
      "loss": 0.8023,
      "step": 43
    },
    {
      "epoch": 2.329896907216495,
      "grad_norm": 0.23030242323875427,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.8841,
      "step": 44
    },
    {
      "epoch": 2.3848797250859106,
      "grad_norm": 0.2185160219669342,
      "learning_rate": 2.25e-05,
      "loss": 0.7976,
      "step": 45
    },
    {
      "epoch": 2.4398625429553267,
      "grad_norm": 0.18541128933429718,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.8459,
      "step": 46
    },
    {
      "epoch": 2.4948453608247423,
      "grad_norm": 0.21860601007938385,
      "learning_rate": 2.35e-05,
      "loss": 0.8594,
      "step": 47
    },
    {
      "epoch": 2.549828178694158,
      "grad_norm": 0.16850370168685913,
      "learning_rate": 2.4e-05,
      "loss": 0.7763,
      "step": 48
    },
    {
      "epoch": 2.604810996563574,
      "grad_norm": 0.18208689987659454,
      "learning_rate": 2.45e-05,
      "loss": 0.8106,
      "step": 49
    },
    {
      "epoch": 2.6597938144329896,
      "grad_norm": 0.1723138839006424,
      "learning_rate": 2.5e-05,
      "loss": 0.8945,
      "step": 50
    },
    {
      "epoch": 2.7147766323024056,
      "grad_norm": 0.16593343019485474,
      "learning_rate": 2.5500000000000003e-05,
      "loss": 0.7774,
      "step": 51
    },
    {
      "epoch": 2.7697594501718212,
      "grad_norm": 0.19333742558956146,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.764,
      "step": 52
    },
    {
      "epoch": 2.824742268041237,
      "grad_norm": 0.1437019407749176,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 0.7429,
      "step": 53
    },
    {
      "epoch": 2.879725085910653,
      "grad_norm": 0.15184654295444489,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.7774,
      "step": 54
    },
    {
      "epoch": 2.934707903780069,
      "grad_norm": 0.1588866114616394,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.837,
      "step": 55
    },
    {
      "epoch": 2.9896907216494846,
      "grad_norm": 0.1829744577407837,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.8212,
      "step": 56
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.22577908635139465,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 0.7369,
      "step": 57
    },
    {
      "epoch": 3.0,
      "step": 57,
      "total_flos": 2.0642424594366464e+16,
      "train_loss": 1.0249844183001602,
      "train_runtime": 35555.0368,
      "train_samples_per_second": 0.098,
      "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
}