{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16181229773462782,
  "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": 1.9981,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9999675930251536e-05,
      "loss": 2.0613,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.99987037294078e-05,
      "loss": 1.8228,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.99970834226737e-05,
      "loss": 1.707,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999481505205661e-05,
      "loss": 1.5271,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999189867636535e-05,
      "loss": 1.4562,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998833437120866e-05,
      "loss": 1.3805,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998412222899321e-05,
      "loss": 1.2998,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.997926235892124e-05,
      "loss": 1.4383,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997375488698769e-05,
      "loss": 1.2441,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996759995597697e-05,
      "loss": 1.2275,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996079772545923e-05,
      "loss": 1.2233,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.995334837178625e-05,
      "loss": 1.1886,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9945252088086825e-05,
      "loss": 1.1779,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.993650908426182e-05,
      "loss": 1.1122,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992711958697868e-05,
      "loss": 1.0766,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.991708383966556e-05,
      "loss": 1.0836,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9906402102505026e-05,
      "loss": 0.9728,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.989507465242732e-05,
      "loss": 0.9883,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.988310178310315e-05,
      "loss": 1.0307,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9870483804936084e-05,
      "loss": 0.9613,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9857221045054535e-05,
      "loss": 1.1038,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9843313847303246e-05,
      "loss": 0.9206,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9828762572234374e-05,
      "loss": 0.9893,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9813567597098166e-05,
      "loss": 0.8328,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.979772931583317e-05,
      "loss": 0.8712,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.978124813905599e-05,
      "loss": 0.8031,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976412449405072e-05,
      "loss": 0.7675,
      "step": 28
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.974635882475778e-05,
      "loss": 0.7851,
      "step": 29
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.972795159176243e-05,
      "loss": 0.7447,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9708903272282884e-05,
      "loss": 0.7719,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9689214360157844e-05,
      "loss": 0.7142,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9668885365833795e-05,
      "loss": 0.8649,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.96479168163517e-05,
      "loss": 0.7574,
      "step": 34
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9626309255333346e-05,
      "loss": 0.9205,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9604063242967315e-05,
      "loss": 0.7987,
      "step": 36
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.958117935599434e-05,
      "loss": 0.7626,
      "step": 37
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.955765818769249e-05,
      "loss": 0.8332,
      "step": 38
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9533500347861675e-05,
      "loss": 0.9178,
      "step": 39
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.950870646280791e-05,
      "loss": 0.9919,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.948327717532705e-05,
      "loss": 0.7098,
      "step": 41
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9457213144688095e-05,
      "loss": 0.7552,
      "step": 42
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9430515046616175e-05,
      "loss": 0.7496,
      "step": 43
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.940318357327495e-05,
      "loss": 0.7667,
      "step": 44
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.937521943324873e-05,
      "loss": 0.8685,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.934662335152405e-05,
      "loss": 0.6715,
      "step": 46
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.931739606947091e-05,
      "loss": 0.8149,
      "step": 47
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9287538344823544e-05,
      "loss": 0.7346,
      "step": 48
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.925705095166079e-05,
      "loss": 0.7803,
      "step": 49
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.922593468038599e-05,
      "loss": 0.7451,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.919419033770652e-05,
      "loss": 0.8402,
      "step": 51
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.916181874661286e-05,
      "loss": 0.7988,
      "step": 52
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.91288207463573e-05,
      "loss": 0.7444,
      "step": 53
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9095197192432105e-05,
      "loss": 0.8545,
      "step": 54
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.906094895654744e-05,
      "loss": 0.761,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.902607692660865e-05,
      "loss": 0.6741,
      "step": 56
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8990582006693365e-05,
      "loss": 0.8457,
      "step": 57
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.895446511702793e-05,
      "loss": 0.8096,
      "step": 58
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.891772719396369e-05,
      "loss": 0.7989,
      "step": 59
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.888036918995258e-05,
      "loss": 0.7683,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.884239207352252e-05,
      "loss": 0.7912,
      "step": 61
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.880379682925228e-05,
      "loss": 0.7417,
      "step": 62
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.876458445774594e-05,
      "loss": 0.7511,
      "step": 63
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.872475597560699e-05,
      "loss": 0.8021,
      "step": 64
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8684312415411897e-05,
      "loss": 0.8154,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.864325482568344e-05,
      "loss": 0.7109,
      "step": 66
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.860158427086341e-05,
      "loss": 0.7915,
      "step": 67
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.855930183128513e-05,
      "loss": 0.6363,
      "step": 68
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.851640860314536e-05,
      "loss": 0.6987,
      "step": 69
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8472905698475906e-05,
      "loss": 0.6498,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.84287942451148e-05,
      "loss": 0.7768,
      "step": 71
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8384075386677054e-05,
      "loss": 0.7979,
      "step": 72
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.833875028252499e-05,
      "loss": 0.7611,
      "step": 73
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8292820107738235e-05,
      "loss": 0.7889,
      "step": 74
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.824628605308319e-05,
      "loss": 0.6706,
      "step": 75
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.819914932498222e-05,
      "loss": 0.7762,
      "step": 76
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.815141114548232e-05,
      "loss": 0.7517,
      "step": 77
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8103072752223486e-05,
      "loss": 0.7793,
      "step": 78
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.805413539840659e-05,
      "loss": 0.7306,
      "step": 79
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.80046003527609e-05,
      "loss": 0.834,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7954468899511215e-05,
      "loss": 0.8076,
      "step": 81
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.790374233834452e-05,
      "loss": 0.8375,
      "step": 82
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7852421984376324e-05,
      "loss": 0.7839,
      "step": 83
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.780050916811658e-05,
      "loss": 0.6221,
      "step": 84
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7748005235435137e-05,
      "loss": 0.7212,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.76949115475269e-05,
      "loss": 0.6369,
      "step": 86
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7641229480876515e-05,
      "loss": 0.7167,
      "step": 87
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.758696042722269e-05,
      "loss": 0.6908,
      "step": 88
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.753210579352211e-05,
      "loss": 0.6681,
      "step": 89
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.747666700191297e-05,
      "loss": 0.6566,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7420645489678076e-05,
      "loss": 0.6869,
      "step": 91
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7364042709207626e-05,
      "loss": 0.7106,
      "step": 92
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.730686012796153e-05,
      "loss": 0.6782,
      "step": 93
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.724909922843136e-05,
      "loss": 0.7148,
      "step": 94
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.719076150810193e-05,
      "loss": 0.8887,
      "step": 95
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7131848479412476e-05,
      "loss": 0.7408,
      "step": 96
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.707236166971742e-05,
      "loss": 0.7046,
      "step": 97
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7012302621246804e-05,
      "loss": 0.7657,
      "step": 98
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.695167289106629e-05,
      "loss": 0.8138,
      "step": 99
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.689047405103678e-05,
      "loss": 0.6964,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.796372652053833,
      "eval_runtime": 5.3558,
      "eval_samples_per_second": 1.867,
      "eval_steps_per_second": 0.373,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 618,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 2.520597053571072e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}