{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.260869565217392,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 1.5445711612701416,
      "learning_rate": 2e-05,
      "loss": 2.0466,
      "step": 1
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.4774067401885986,
      "learning_rate": 4e-05,
      "loss": 2.1015,
      "step": 2
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 1.7667168378829956,
      "learning_rate": 6e-05,
      "loss": 2.0117,
      "step": 3
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 1.5769754648208618,
      "learning_rate": 8e-05,
      "loss": 2.1177,
      "step": 4
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 1.312828779220581,
      "learning_rate": 0.0001,
      "loss": 1.7612,
      "step": 5
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 2.5360119342803955,
      "learning_rate": 0.00012,
      "loss": 2.9041,
      "step": 6
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 1.1877645254135132,
      "learning_rate": 0.00014,
      "loss": 1.3141,
      "step": 7
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 1.410666584968567,
      "learning_rate": 0.00016,
      "loss": 1.1241,
      "step": 8
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.8428862690925598,
      "learning_rate": 0.00018,
      "loss": 0.683,
      "step": 9
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.9450931549072266,
      "learning_rate": 0.0002,
      "loss": 0.5753,
      "step": 10
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 1.5233032703399658,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.5675,
      "step": 11
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.6204625368118286,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.2438,
      "step": 12
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.45535916090011597,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.2288,
      "step": 13
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.4980858266353607,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.1948,
      "step": 14
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.5140542984008789,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.1636,
      "step": 15
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.3663245737552643,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.144,
      "step": 16
    },
    {
      "epoch": 3.0869565217391304,
      "grad_norm": 0.35473620891571045,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.2038,
      "step": 17
    },
    {
      "epoch": 3.260869565217391,
      "grad_norm": 0.20651406049728394,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0866,
      "step": 18
    },
    {
      "epoch": 3.4347826086956523,
      "grad_norm": 0.23146343231201172,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0891,
      "step": 19
    },
    {
      "epoch": 3.608695652173913,
      "grad_norm": 0.21453891694545746,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0938,
      "step": 20
    },
    {
      "epoch": 3.782608695652174,
      "grad_norm": 0.238055020570755,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.0856,
      "step": 21
    },
    {
      "epoch": 3.9565217391304346,
      "grad_norm": 0.30295759439468384,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.1121,
      "step": 22
    },
    {
      "epoch": 4.173913043478261,
      "grad_norm": 0.1274573802947998,
      "learning_rate": 0.00012079116908177593,
      "loss": 0.0548,
      "step": 23
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 0.35317644476890564,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.075,
      "step": 24
    },
    {
      "epoch": 4.521739130434782,
      "grad_norm": 0.20967158675193787,
      "learning_rate": 0.0001,
      "loss": 0.0641,
      "step": 25
    },
    {
      "epoch": 4.695652173913043,
      "grad_norm": 0.19848443567752838,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0559,
      "step": 26
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 0.3084442913532257,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.0654,
      "step": 27
    },
    {
      "epoch": 5.086956521739131,
      "grad_norm": 0.30316388607025146,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0989,
      "step": 28
    },
    {
      "epoch": 5.260869565217392,
      "grad_norm": 0.11200349032878876,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 0.0356,
      "step": 29
    },
    {
      "epoch": 5.434782608695652,
      "grad_norm": 0.10763353109359741,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0498,
      "step": 30
    },
    {
      "epoch": 5.608695652173913,
      "grad_norm": 0.1339104175567627,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0457,
      "step": 31
    },
    {
      "epoch": 5.782608695652174,
      "grad_norm": 0.1716516762971878,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.0445,
      "step": 32
    },
    {
      "epoch": 5.956521739130435,
      "grad_norm": 0.26181846857070923,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.0672,
      "step": 33
    },
    {
      "epoch": 6.173913043478261,
      "grad_norm": 0.21127818524837494,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0499,
      "step": 34
    },
    {
      "epoch": 6.3478260869565215,
      "grad_norm": 0.14111244678497314,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0429,
      "step": 35
    },
    {
      "epoch": 6.521739130434782,
      "grad_norm": 0.06796476244926453,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.0362,
      "step": 36
    },
    {
      "epoch": 6.695652173913043,
      "grad_norm": 0.2198614478111267,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.054,
      "step": 37
    },
    {
      "epoch": 6.869565217391305,
      "grad_norm": 0.1897715926170349,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0548,
      "step": 38
    },
    {
      "epoch": 7.086956521739131,
      "grad_norm": 0.13412117958068848,
      "learning_rate": 5.478104631726711e-07,
      "loss": 0.0578,
      "step": 39
    },
    {
      "epoch": 7.260869565217392,
      "grad_norm": 0.1075892448425293,
      "learning_rate": 0.0,
      "loss": 0.0321,
      "step": 40
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 225228890308608.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}