{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 13,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.06574621796607971,
      "learning_rate": 0.0,
      "loss": 0.683349609375,
      "step": 1
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.05150672793388367,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.66162109375,
      "step": 2
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.05505973473191261,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.66796875,
      "step": 3
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.0745709016919136,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.677734375,
      "step": 4
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.08272148668766022,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.6865234375,
      "step": 5
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.07590784132480621,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.6802978515625,
      "step": 6
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.07782676070928574,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.69140625,
      "step": 7
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.06320719420909882,
      "learning_rate": 1e-05,
      "loss": 0.691650390625,
      "step": 8
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.06206236779689789,
      "learning_rate": 9.994224282269737e-06,
      "loss": 0.685302734375,
      "step": 9
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.0787166878581047,
      "learning_rate": 9.976911955263528e-06,
      "loss": 0.66796875,
      "step": 10
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.0858655646443367,
      "learning_rate": 9.948107459476502e-06,
      "loss": 0.68408203125,
      "step": 11
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.05600776895880699,
      "learning_rate": 9.907884735636226e-06,
      "loss": 0.650146484375,
      "step": 12
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.09197074174880981,
      "learning_rate": 9.85634703489792e-06,
      "loss": 0.640380859375,
      "step": 13
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.051537591964006424,
      "learning_rate": 9.79362665380022e-06,
      "loss": 0.61328125,
      "step": 14
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.05343881994485855,
      "learning_rate": 9.719884594661864e-06,
      "loss": 0.65966796875,
      "step": 15
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.06316563487052917,
      "learning_rate": 9.635310152291038e-06,
      "loss": 0.634765625,
      "step": 16
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.04639754444360733,
      "learning_rate": 9.540120428068337e-06,
      "loss": 0.65234375,
      "step": 17
    },
    {
      "epoch": 0.7391304347826086,
      "eval_loss": 0.65130615234375,
      "eval_runtime": 2.0495,
      "eval_samples_per_second": 1.464,
      "eval_steps_per_second": 0.488,
      "step": 17
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.08494574576616287,
      "learning_rate": 9.43455977265062e-06,
      "loss": 0.680419921875,
      "step": 18
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.0556136891245842,
      "learning_rate": 9.31889915872638e-06,
      "loss": 0.654052734375,
      "step": 19
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.050713956356048584,
      "learning_rate": 9.193435485432744e-06,
      "loss": 0.66650390625,
      "step": 20
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.0457201823592186,
      "learning_rate": 9.058490816219644e-06,
      "loss": 0.643310546875,
      "step": 21
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.0635598674416542,
      "learning_rate": 8.91441155211756e-06,
      "loss": 0.654052734375,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.04849772900342941,
      "learning_rate": 8.76156754253104e-06,
      "loss": 0.65966796875,
      "step": 23
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.04802418127655983,
      "learning_rate": 8.60035113584059e-06,
      "loss": 0.65966796875,
      "step": 24
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.03913020342588425,
      "learning_rate": 8.431176172250002e-06,
      "loss": 0.643798828125,
      "step": 25
    },
    {
      "epoch": 1.1304347826086956,
      "grad_norm": 0.04047388955950737,
      "learning_rate": 8.254476921464483e-06,
      "loss": 0.64501953125,
      "step": 26
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 0.04983432590961456,
      "learning_rate": 8.070706967926565e-06,
      "loss": 0.64453125,
      "step": 27
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.053629934787750244,
      "learning_rate": 7.880338046471331e-06,
      "loss": 0.646484375,
      "step": 28
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 0.048355311155319214,
      "learning_rate": 7.683858831389866e-06,
      "loss": 0.64288330078125,
      "step": 29
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.04861477389931679,
      "learning_rate": 7.481773682009356e-06,
      "loss": 0.650146484375,
      "step": 30
    },
    {
      "epoch": 1.3043478260869565,
      "eval_loss": 0.6319580078125,
      "eval_runtime": 2.0542,
      "eval_samples_per_second": 1.46,
      "eval_steps_per_second": 0.487,
      "step": 30
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.04120055213570595,
      "learning_rate": 7.274601348009934e-06,
      "loss": 0.65966796875,
      "step": 31
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.04094763100147247,
      "learning_rate": 7.062873637801692e-06,
      "loss": 0.6552734375,
      "step": 32
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 0.045276131480932236,
      "learning_rate": 6.847134053380113e-06,
      "loss": 0.6279296875,
      "step": 33
    },
    {
      "epoch": 1.4782608695652173,
      "grad_norm": 0.047124769538640976,
      "learning_rate": 6.627936395164243e-06,
      "loss": 0.640625,
      "step": 34
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.03720078617334366,
      "learning_rate": 6.405843340398971e-06,
      "loss": 0.623291015625,
      "step": 35
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.04636256396770477,
      "learning_rate": 6.181424998770595e-06,
      "loss": 0.59619140625,
      "step": 36
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.03454005345702171,
      "learning_rate": 5.955257448943446e-06,
      "loss": 0.588623046875,
      "step": 37
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.03595034033060074,
      "learning_rate": 5.727921259774208e-06,
      "loss": 0.6328125,
      "step": 38
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.03682588040828705,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.60498046875,
      "step": 39
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.03514236584305763,
      "learning_rate": 5.272078740225793e-06,
      "loss": 0.629638671875,
      "step": 40
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.04472735896706581,
      "learning_rate": 5.0447425510565564e-06,
      "loss": 0.641357421875,
      "step": 41
    },
    {
      "epoch": 1.8260869565217392,
      "grad_norm": 0.03495565056800842,
      "learning_rate": 4.818575001229406e-06,
      "loss": 0.626708984375,
      "step": 42
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.035717420279979706,
      "learning_rate": 4.594156659601029e-06,
      "loss": 0.643310546875,
      "step": 43
    },
    {
      "epoch": 1.8695652173913042,
      "eval_loss": 0.6201171875,
      "eval_runtime": 2.0449,
      "eval_samples_per_second": 1.467,
      "eval_steps_per_second": 0.489,
      "step": 43
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.03499886021018028,
      "learning_rate": 4.372063604835758e-06,
      "loss": 0.623046875,
      "step": 44
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 0.04084884747862816,
      "learning_rate": 4.15286594661989e-06,
      "loss": 0.62548828125,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.036120329052209854,
      "learning_rate": 3.93712636219831e-06,
      "loss": 0.6376953125,
      "step": 46
    },
    {
      "epoch": 2.0434782608695654,
      "grad_norm": 0.03603987395763397,
      "learning_rate": 3.7253986519900674e-06,
      "loss": 0.6376953125,
      "step": 47
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.03318258747458458,
      "learning_rate": 3.5182263179906462e-06,
      "loss": 0.62841796875,
      "step": 48
    },
    {
      "epoch": 2.130434782608696,
      "grad_norm": 0.03247852995991707,
      "learning_rate": 3.316141168610136e-06,
      "loss": 0.629638671875,
      "step": 49
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.03627059981226921,
      "learning_rate": 3.119661953528671e-06,
      "loss": 0.62451171875,
      "step": 50
    },
    {
      "epoch": 2.217391304347826,
      "grad_norm": 0.03881670534610748,
      "learning_rate": 2.9292930320734337e-06,
      "loss": 0.62548828125,
      "step": 51
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.03561678156256676,
      "learning_rate": 2.745523078535517e-06,
      "loss": 0.62567138671875,
      "step": 52
    },
    {
      "epoch": 2.3043478260869565,
      "grad_norm": 0.036425329744815826,
      "learning_rate": 2.568823827750001e-06,
      "loss": 0.633056640625,
      "step": 53
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.033790528774261475,
      "learning_rate": 2.3996488641594104e-06,
      "loss": 0.6455078125,
      "step": 54
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 0.03458794951438904,
      "learning_rate": 2.2384324574689614e-06,
      "loss": 0.64013671875,
      "step": 55
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.03604791685938835,
      "learning_rate": 2.085588447882441e-06,
      "loss": 0.612548828125,
      "step": 56
    },
    {
      "epoch": 2.4347826086956523,
      "eval_loss": 0.617156982421875,
      "eval_runtime": 2.0468,
      "eval_samples_per_second": 1.466,
      "eval_steps_per_second": 0.489,
      "step": 56
    },
    {
      "epoch": 2.4782608695652173,
      "grad_norm": 0.037638068199157715,
      "learning_rate": 1.9415091837803574e-06,
      "loss": 0.6259765625,
      "step": 57
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.032444193959236145,
      "learning_rate": 1.8065645145672578e-06,
      "loss": 0.61279296875,
      "step": 58
    },
    {
      "epoch": 2.5652173913043477,
      "grad_norm": 0.03685029596090317,
      "learning_rate": 1.6811008412736207e-06,
      "loss": 0.582763671875,
      "step": 59
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.030133027583360672,
      "learning_rate": 1.5654402273493808e-06,
      "loss": 0.57958984375,
      "step": 60
    },
    {
      "epoch": 2.6521739130434785,
      "grad_norm": 0.031628984957933426,
      "learning_rate": 1.459879571931663e-06,
      "loss": 0.6240234375,
      "step": 61
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.03223630040884018,
      "learning_rate": 1.3646898477089627e-06,
      "loss": 0.594970703125,
      "step": 62
    },
    {
      "epoch": 2.7391304347826084,
      "grad_norm": 0.03134209290146828,
      "learning_rate": 1.2801154053381386e-06,
      "loss": 0.621337890625,
      "step": 63
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.038812585175037384,
      "learning_rate": 1.2063733461997804e-06,
      "loss": 0.631103515625,
      "step": 64
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 0.031380850821733475,
      "learning_rate": 1.1436529651020813e-06,
      "loss": 0.619384765625,
      "step": 65
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.0320647768676281,
      "learning_rate": 1.092115264363775e-06,
      "loss": 0.636474609375,
      "step": 66
    },
    {
      "epoch": 2.9130434782608696,
      "grad_norm": 0.031743913888931274,
      "learning_rate": 1.0518925405234988e-06,
      "loss": 0.61572265625,
      "step": 67
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.037360724061727524,
      "learning_rate": 1.0230880447364719e-06,
      "loss": 0.619140625,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03293885663151741,
      "learning_rate": 1.0057757177302628e-06,
      "loss": 0.631103515625,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6156768798828125,
      "eval_runtime": 2.0475,
      "eval_samples_per_second": 1.465,
      "eval_steps_per_second": 0.488,
      "step": 69
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2309274178963374e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}