{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 46,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.021739130434782608,
      "grad_norm": 1.1839052438735962,
      "learning_rate": 0.0,
      "loss": 2.5329,
      "step": 1
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 1.286145567893982,
      "learning_rate": 8e-05,
      "loss": 2.4878,
      "step": 2
    },
    {
      "epoch": 0.06521739130434782,
      "grad_norm": 1.2978639602661133,
      "learning_rate": 0.00016,
      "loss": 2.2947,
      "step": 3
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 1.4251940250396729,
      "learning_rate": 0.00024,
      "loss": 1.8883,
      "step": 4
    },
    {
      "epoch": 0.10869565217391304,
      "grad_norm": 1.7767548561096191,
      "learning_rate": 0.00032,
      "loss": 1.4114,
      "step": 5
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 2.304410696029663,
      "learning_rate": 0.0004,
      "loss": 0.9961,
      "step": 6
    },
    {
      "epoch": 0.15217391304347827,
      "grad_norm": 3.0359408855438232,
      "learning_rate": 0.00039941316023674807,
      "loss": 0.826,
      "step": 7
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 1.336562156677246,
      "learning_rate": 0.00039765608475606976,
      "loss": 0.8054,
      "step": 8
    },
    {
      "epoch": 0.1956521739130435,
      "grad_norm": 0.5087499618530273,
      "learning_rate": 0.00039473908477555584,
      "loss": 0.626,
      "step": 9
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.47382721304893494,
      "learning_rate": 0.0003906792784109861,
      "loss": 0.5957,
      "step": 10
    },
    {
      "epoch": 0.2391304347826087,
      "grad_norm": 0.8307927250862122,
      "learning_rate": 0.000385500490220419,
      "loss": 0.6326,
      "step": 11
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.7591253519058228,
      "learning_rate": 0.00037923311139221114,
      "loss": 0.5715,
      "step": 12
    },
    {
      "epoch": 0.2826086956521739,
      "grad_norm": 0.4196276068687439,
      "learning_rate": 0.00037191392139744025,
      "loss": 0.519,
      "step": 13
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.3430580496788025,
      "learning_rate": 0.00036358587215334356,
      "loss": 0.5277,
      "step": 14
    },
    {
      "epoch": 0.32608695652173914,
      "grad_norm": 0.39747822284698486,
      "learning_rate": 0.0003542978359643886,
      "loss": 0.5513,
      "step": 15
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.2966645359992981,
      "learning_rate": 0.0003441043187201574,
      "loss": 0.4966,
      "step": 16
    },
    {
      "epoch": 0.3695652173913043,
      "grad_norm": 0.3044649660587311,
      "learning_rate": 0.00033306514003311305,
      "loss": 0.5843,
      "step": 17
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.29440030455589294,
      "learning_rate": 0.0003212450821933276,
      "loss": 0.5514,
      "step": 18
    },
    {
      "epoch": 0.41304347826086957,
      "grad_norm": 0.25709202885627747,
      "learning_rate": 0.00030871351000024425,
      "loss": 0.5554,
      "step": 19
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.2896120548248291,
      "learning_rate": 0.0002955439637024526,
      "loss": 0.5084,
      "step": 20
    },
    {
      "epoch": 0.45652173913043476,
      "grad_norm": 0.31083154678344727,
      "learning_rate": 0.00028181372743426805,
      "loss": 0.5945,
      "step": 21
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.2456878423690796,
      "learning_rate": 0.00026760337568170053,
      "loss": 0.413,
      "step": 22
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.23984560370445251,
      "learning_rate": 0.0002529963004393324,
      "loss": 0.551,
      "step": 23
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.29197460412979126,
      "learning_rate": 0.0002380782218329337,
      "loss": 0.4758,
      "step": 24
    },
    {
      "epoch": 0.5434782608695652,
      "grad_norm": 0.24348799884319305,
      "learning_rate": 0.00022293668507968013,
      "loss": 0.4229,
      "step": 25
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.259126216173172,
      "learning_rate": 0.0002076605467380071,
      "loss": 0.5218,
      "step": 26
    },
    {
      "epoch": 0.5869565217391305,
      "grad_norm": 0.2982611060142517,
      "learning_rate": 0.00019233945326199294,
      "loss": 0.5754,
      "step": 27
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.27066999673843384,
      "learning_rate": 0.00017706331492031995,
      "loss": 0.4559,
      "step": 28
    },
    {
      "epoch": 0.6304347826086957,
      "grad_norm": 0.22570188343524933,
      "learning_rate": 0.0001619217781670663,
      "loss": 0.4743,
      "step": 29
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.23569968342781067,
      "learning_rate": 0.0001470036995606677,
      "loss": 0.478,
      "step": 30
    },
    {
      "epoch": 0.6739130434782609,
      "grad_norm": 0.29840192198753357,
      "learning_rate": 0.0001323966243182995,
      "loss": 0.4915,
      "step": 31
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.22925806045532227,
      "learning_rate": 0.00011818627256573203,
      "loss": 0.4438,
      "step": 32
    },
    {
      "epoch": 0.717391304347826,
      "grad_norm": 0.23691901564598083,
      "learning_rate": 0.00010445603629754738,
      "loss": 0.4096,
      "step": 33
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.2998674213886261,
      "learning_rate": 9.12864899997558e-05,
      "loss": 0.5025,
      "step": 34
    },
    {
      "epoch": 0.7608695652173914,
      "grad_norm": 0.21318762004375458,
      "learning_rate": 7.875491780667246e-05,
      "loss": 0.424,
      "step": 35
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.2458743005990982,
      "learning_rate": 6.693485996688696e-05,
      "loss": 0.505,
      "step": 36
    },
    {
      "epoch": 0.8043478260869565,
      "grad_norm": 0.22771987318992615,
      "learning_rate": 5.589568127984262e-05,
      "loss": 0.4847,
      "step": 37
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.23360995948314667,
      "learning_rate": 4.5702164035611406e-05,
      "loss": 0.5909,
      "step": 38
    },
    {
      "epoch": 0.8478260869565217,
      "grad_norm": 0.23350945115089417,
      "learning_rate": 3.641412784665647e-05,
      "loss": 0.4595,
      "step": 39
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.24031572043895721,
      "learning_rate": 2.8086078602559806e-05,
      "loss": 0.531,
      "step": 40
    },
    {
      "epoch": 0.8913043478260869,
      "grad_norm": 0.21330903470516205,
      "learning_rate": 2.0766888607788904e-05,
      "loss": 0.4063,
      "step": 41
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.24683713912963867,
      "learning_rate": 1.4499509779581078e-05,
      "loss": 0.5228,
      "step": 42
    },
    {
      "epoch": 0.9347826086956522,
      "grad_norm": 0.21736790239810944,
      "learning_rate": 9.320721589013892e-06,
      "loss": 0.5032,
      "step": 43
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.2305678129196167,
      "learning_rate": 5.260915224444207e-06,
      "loss": 0.4663,
      "step": 44
    },
    {
      "epoch": 0.9782608695652174,
      "grad_norm": 0.23209130764007568,
      "learning_rate": 2.343915243930317e-06,
      "loss": 0.504,
      "step": 45
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.23025843501091003,
      "learning_rate": 5.868397632519118e-07,
      "loss": 0.3984,
      "step": 46
    }
  ],
  "logging_steps": 1,
  "max_steps": 46,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.779203528306688e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}