{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.043094160741219564,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5e-05,
      "loss": 1.5475,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.999997705921923e-05,
      "loss": 1.4738,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9999908236919016e-05,
      "loss": 1.709,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.999979353322567e-05,
      "loss": 1.3682,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.99996329483497e-05,
      "loss": 1.4525,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.999942648258581e-05,
      "loss": 1.2902,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.999917413631294e-05,
      "loss": 1.2581,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9998875909994206e-05,
      "loss": 1.1363,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9998531804176926e-05,
      "loss": 1.0479,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.999814181949263e-05,
      "loss": 1.0362,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.999770595665704e-05,
      "loss": 0.9415,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999722421647006e-05,
      "loss": 1.0849,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999669659981584e-05,
      "loss": 0.8538,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999612310766268e-05,
      "loss": 0.9404,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9995503741063096e-05,
      "loss": 0.9645,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999483850115379e-05,
      "loss": 1.0898,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9994127389155623e-05,
      "loss": 0.9545,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9993370406373705e-05,
      "loss": 0.8432,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999256755419729e-05,
      "loss": 0.9946,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999171883409982e-05,
      "loss": 0.7908,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999082424763891e-05,
      "loss": 0.8971,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998988379645638e-05,
      "loss": 0.85,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998889748227819e-05,
      "loss": 0.8626,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9987865306914495e-05,
      "loss": 0.8335,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9986787272259596e-05,
      "loss": 0.9314,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998566338029198e-05,
      "loss": 0.8645,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998449363307428e-05,
      "loss": 0.9316,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998327803275328e-05,
      "loss": 0.805,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998201658155994e-05,
      "loss": 1.0418,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998070928180935e-05,
      "loss": 0.649,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.997935613590075e-05,
      "loss": 0.8,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.997795714631751e-05,
      "loss": 0.8014,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.997651231562715e-05,
      "loss": 0.7854,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9975021646481315e-05,
      "loss": 0.8782,
      "step": 34
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997348514161576e-05,
      "loss": 0.7564,
      "step": 35
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997190280385039e-05,
      "loss": 0.9438,
      "step": 36
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997027463608921e-05,
      "loss": 0.9248,
      "step": 37
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996860064132033e-05,
      "loss": 0.76,
      "step": 38
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9966880822615965e-05,
      "loss": 0.8834,
      "step": 39
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996511518313244e-05,
      "loss": 0.8928,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996330372611017e-05,
      "loss": 0.8857,
      "step": 41
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996144645487364e-05,
      "loss": 0.7975,
      "step": 42
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.995954337283145e-05,
      "loss": 0.7815,
      "step": 43
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9957594483476236e-05,
      "loss": 0.8869,
      "step": 44
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.995559979038474e-05,
      "loss": 0.9173,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.995355929721773e-05,
      "loss": 0.9258,
      "step": 46
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.995147300772006e-05,
      "loss": 0.896,
      "step": 47
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.994934092572061e-05,
      "loss": 0.893,
      "step": 48
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.994716305513232e-05,
      "loss": 0.8257,
      "step": 49
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.994493939995214e-05,
      "loss": 0.8759,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.994266996426107e-05,
      "loss": 0.9216,
      "step": 51
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.994035475222412e-05,
      "loss": 0.9097,
      "step": 52
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9937993768090306e-05,
      "loss": 1.015,
      "step": 53
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.993558701619266e-05,
      "loss": 0.8633,
      "step": 54
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9933134500948205e-05,
      "loss": 0.928,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.993063622685794e-05,
      "loss": 0.8069,
      "step": 56
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9928092198506866e-05,
      "loss": 0.885,
      "step": 57
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.992550242056393e-05,
      "loss": 0.7342,
      "step": 58
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992286689778207e-05,
      "loss": 0.8593,
      "step": 59
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992018563499814e-05,
      "loss": 0.9458,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.991745863713299e-05,
      "loss": 0.9511,
      "step": 61
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.991468590919135e-05,
      "loss": 0.8605,
      "step": 62
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9911867456261916e-05,
      "loss": 0.76,
      "step": 63
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9909003283517283e-05,
      "loss": 0.8037,
      "step": 64
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.990609339621397e-05,
      "loss": 0.8945,
      "step": 65
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.990313779969237e-05,
      "loss": 0.7774,
      "step": 66
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.990013649937679e-05,
      "loss": 0.8737,
      "step": 67
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.989708950077541e-05,
      "loss": 0.8914,
      "step": 68
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9893996809480246e-05,
      "loss": 0.8682,
      "step": 69
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9890858431167226e-05,
      "loss": 0.7745,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.988767437159608e-05,
      "loss": 1.0306,
      "step": 71
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.988444463661041e-05,
      "loss": 0.904,
      "step": 72
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.98811692321376e-05,
      "loss": 0.8478,
      "step": 73
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9877848164188904e-05,
      "loss": 0.7117,
      "step": 74
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.987448143885933e-05,
      "loss": 0.6789,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.987106906232773e-05,
      "loss": 0.9385,
      "step": 76
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9867611040856695e-05,
      "loss": 1.049,
      "step": 77
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9864107380792594e-05,
      "loss": 0.8914,
      "step": 78
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.986055808856558e-05,
      "loss": 0.8211,
      "step": 79
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9856963170689525e-05,
      "loss": 0.9007,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9853322633762045e-05,
      "loss": 0.832,
      "step": 81
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984963648446449e-05,
      "loss": 0.807,
      "step": 82
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984590472956191e-05,
      "loss": 0.7031,
      "step": 83
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.984212737590304e-05,
      "loss": 0.9261,
      "step": 84
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.983830443042033e-05,
      "loss": 0.7759,
      "step": 85
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.983443590012989e-05,
      "loss": 0.7147,
      "step": 86
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9830521792131484e-05,
      "loss": 0.8554,
      "step": 87
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.982656211360852e-05,
      "loss": 0.8052,
      "step": 88
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.982255687182806e-05,
      "loss": 0.8408,
      "step": 89
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.981850607414077e-05,
      "loss": 0.7086,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.981440972798092e-05,
      "loss": 0.7808,
      "step": 91
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.981026784086639e-05,
      "loss": 0.8632,
      "step": 92
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.980608042039862e-05,
      "loss": 0.8798,
      "step": 93
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.980184747426263e-05,
      "loss": 0.9253,
      "step": 94
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9797569010226995e-05,
      "loss": 0.8305,
      "step": 95
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.979324503614381e-05,
      "loss": 0.9474,
      "step": 96
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.97888755599487e-05,
      "loss": 0.8102,
      "step": 97
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.978446058966081e-05,
      "loss": 0.6445,
      "step": 98
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.978000013338277e-05,
      "loss": 0.8123,
      "step": 99
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.977549419930067e-05,
      "loss": 0.9368,
      "step": 100
    },
    {
      "epoch": 0.04,
      "eval_loss": 0.8984958529472351,
      "eval_runtime": 10.1685,
      "eval_samples_per_second": 3.639,
      "eval_steps_per_second": 0.492,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 2320,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 1.406258997362688e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}