{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.92436974789916,
  "eval_steps": 8,
  "global_step": 87,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 0.115234375,
      "learning_rate": 2e-05,
      "loss": 1.768,
      "step": 1
    },
    {
      "epoch": 0.03361344537815126,
      "eval_loss": 1.8648816347122192,
      "eval_runtime": 18.2501,
      "eval_samples_per_second": 2.74,
      "eval_steps_per_second": 0.384,
      "step": 1
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 0.10888671875,
      "learning_rate": 4e-05,
      "loss": 1.7838,
      "step": 2
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 0.126953125,
      "learning_rate": 6e-05,
      "loss": 1.9413,
      "step": 3
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 0.0986328125,
      "learning_rate": 8e-05,
      "loss": 1.7757,
      "step": 4
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 0.12255859375,
      "learning_rate": 0.0001,
      "loss": 1.735,
      "step": 5
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.00012,
      "loss": 1.8269,
      "step": 6
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.00014,
      "loss": 1.8552,
      "step": 7
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": 0.119140625,
      "learning_rate": 0.00016,
      "loss": 1.8084,
      "step": 8
    },
    {
      "epoch": 0.2689075630252101,
      "eval_loss": 1.8317129611968994,
      "eval_runtime": 19.6984,
      "eval_samples_per_second": 2.538,
      "eval_steps_per_second": 0.355,
      "step": 8
    },
    {
      "epoch": 0.3025210084033613,
      "grad_norm": 0.12255859375,
      "learning_rate": 0.00018,
      "loss": 1.7158,
      "step": 9
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.134765625,
      "learning_rate": 0.0002,
      "loss": 1.8702,
      "step": 10
    },
    {
      "epoch": 0.3697478991596639,
      "grad_norm": 0.12890625,
      "learning_rate": 0.00019995608365087946,
      "loss": 1.8307,
      "step": 11
    },
    {
      "epoch": 0.40336134453781514,
      "grad_norm": 0.11474609375,
      "learning_rate": 0.00019982437317643217,
      "loss": 1.6583,
      "step": 12
    },
    {
      "epoch": 0.4369747899159664,
      "grad_norm": 0.134765625,
      "learning_rate": 0.0001996049842615217,
      "loss": 1.6663,
      "step": 13
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.12060546875,
      "learning_rate": 0.00019929810960135172,
      "loss": 1.7388,
      "step": 14
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 0.126953125,
      "learning_rate": 0.0001989040187322164,
      "loss": 1.7485,
      "step": 15
    },
    {
      "epoch": 0.5378151260504201,
      "grad_norm": 0.1259765625,
      "learning_rate": 0.00019842305779475968,
      "loss": 1.633,
      "step": 16
    },
    {
      "epoch": 0.5378151260504201,
      "eval_loss": 1.7832777500152588,
      "eval_runtime": 19.6833,
      "eval_samples_per_second": 2.54,
      "eval_steps_per_second": 0.356,
      "step": 16
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.12109375,
      "learning_rate": 0.0001978556492299504,
      "loss": 1.8373,
      "step": 17
    },
    {
      "epoch": 0.6050420168067226,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.0001972022914080411,
      "loss": 1.6552,
      "step": 18
    },
    {
      "epoch": 0.6386554621848739,
      "grad_norm": 0.126953125,
      "learning_rate": 0.00019646355819083589,
      "loss": 1.8113,
      "step": 19
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.00019564009842765225,
      "loss": 1.6544,
      "step": 20
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.00019473263538541914,
      "loss": 1.6649,
      "step": 21
    },
    {
      "epoch": 0.7394957983193278,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.0001937419661134121,
      "loss": 1.6868,
      "step": 22
    },
    {
      "epoch": 0.773109243697479,
      "grad_norm": 0.126953125,
      "learning_rate": 0.00019266896074318334,
      "loss": 1.7762,
      "step": 23
    },
    {
      "epoch": 0.8067226890756303,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00019151456172430183,
      "loss": 1.6737,
      "step": 24
    },
    {
      "epoch": 0.8067226890756303,
      "eval_loss": 1.7643933296203613,
      "eval_runtime": 19.6308,
      "eval_samples_per_second": 2.547,
      "eval_steps_per_second": 0.357,
      "step": 24
    },
    {
      "epoch": 0.8403361344537815,
      "grad_norm": 0.1298828125,
      "learning_rate": 0.00019027978299657436,
      "loss": 1.6401,
      "step": 25
    },
    {
      "epoch": 0.8739495798319328,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00018896570909947475,
      "loss": 1.7068,
      "step": 26
    },
    {
      "epoch": 0.907563025210084,
      "grad_norm": 0.12060546875,
      "learning_rate": 0.0001875734942195637,
      "loss": 1.8112,
      "step": 27
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.00018610436117673555,
      "loss": 1.6596,
      "step": 28
    },
    {
      "epoch": 0.9747899159663865,
      "grad_norm": 0.12890625,
      "learning_rate": 0.0001845596003501826,
      "loss": 1.7936,
      "step": 29
    },
    {
      "epoch": 1.0084033613445378,
      "grad_norm": 0.1240234375,
      "learning_rate": 0.0001829405685450202,
      "loss": 1.7947,
      "step": 30
    },
    {
      "epoch": 1.0420168067226891,
      "grad_norm": 0.20703125,
      "learning_rate": 0.00018124868780056814,
      "loss": 1.6887,
      "step": 31
    },
    {
      "epoch": 1.0756302521008403,
      "grad_norm": 0.1455078125,
      "learning_rate": 0.00017948544414133534,
      "loss": 1.6722,
      "step": 32
    },
    {
      "epoch": 1.0756302521008403,
      "eval_loss": 1.7600828409194946,
      "eval_runtime": 19.7105,
      "eval_samples_per_second": 2.537,
      "eval_steps_per_second": 0.355,
      "step": 32
    },
    {
      "epoch": 1.1092436974789917,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00017765238627180424,
      "loss": 1.7145,
      "step": 33
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.00017575112421616202,
      "loss": 1.6609,
      "step": 34
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.00017378332790417273,
      "loss": 1.6681,
      "step": 35
    },
    {
      "epoch": 1.2100840336134453,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.00017175072570443312,
      "loss": 1.6641,
      "step": 36
    },
    {
      "epoch": 1.2436974789915967,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.00016965510290629972,
      "loss": 1.7011,
      "step": 37
    },
    {
      "epoch": 1.2773109243697478,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.00016749830015182107,
      "loss": 1.7171,
      "step": 38
    },
    {
      "epoch": 1.3109243697478992,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00016528221181905217,
      "loss": 1.6333,
      "step": 39
    },
    {
      "epoch": 1.3445378151260505,
      "grad_norm": 0.111328125,
      "learning_rate": 0.00016300878435817113,
      "loss": 1.7162,
      "step": 40
    },
    {
      "epoch": 1.3445378151260505,
      "eval_loss": 1.757140040397644,
      "eval_runtime": 19.6485,
      "eval_samples_per_second": 2.545,
      "eval_steps_per_second": 0.356,
      "step": 40
    },
    {
      "epoch": 1.3781512605042017,
      "grad_norm": 0.1484375,
      "learning_rate": 0.00016068001458185936,
      "loss": 1.6501,
      "step": 41
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.1240234375,
      "learning_rate": 0.0001582979479114472,
      "loss": 1.6446,
      "step": 42
    },
    {
      "epoch": 1.4453781512605042,
      "grad_norm": 0.119140625,
      "learning_rate": 0.00015586467658036524,
      "loss": 1.7104,
      "step": 43
    },
    {
      "epoch": 1.4789915966386555,
      "grad_norm": 0.109375,
      "learning_rate": 0.0001533823377964791,
      "loss": 1.6146,
      "step": 44
    },
    {
      "epoch": 1.5126050420168067,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.00015085311186492206,
      "loss": 1.6448,
      "step": 45
    },
    {
      "epoch": 1.5462184873949578,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.00014827922027307451,
      "loss": 1.6735,
      "step": 46
    },
    {
      "epoch": 1.5798319327731094,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.0001456629237393713,
      "loss": 1.6604,
      "step": 47
    },
    {
      "epoch": 1.6134453781512605,
      "grad_norm": 0.12060546875,
      "learning_rate": 0.00014300652022765207,
      "loss": 1.7046,
      "step": 48
    },
    {
      "epoch": 1.6134453781512605,
      "eval_loss": 1.7558497190475464,
      "eval_runtime": 19.7723,
      "eval_samples_per_second": 2.529,
      "eval_steps_per_second": 0.354,
      "step": 48
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.1259765625,
      "learning_rate": 0.00014031234292879725,
      "loss": 1.694,
      "step": 49
    },
    {
      "epoch": 1.680672268907563,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.00013758275821142382,
      "loss": 1.625,
      "step": 50
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.123046875,
      "learning_rate": 0.0001348201635434399,
      "loss": 1.6919,
      "step": 51
    },
    {
      "epoch": 1.7478991596638656,
      "grad_norm": 0.1201171875,
      "learning_rate": 0.00013202698538628376,
      "loss": 1.6777,
      "step": 52
    },
    {
      "epoch": 1.7815126050420167,
      "grad_norm": 0.12890625,
      "learning_rate": 0.00012920567706369758,
      "loss": 1.7762,
      "step": 53
    },
    {
      "epoch": 1.815126050420168,
      "grad_norm": 0.126953125,
      "learning_rate": 0.00012635871660690676,
      "loss": 1.6668,
      "step": 54
    },
    {
      "epoch": 1.8487394957983194,
      "grad_norm": 0.125,
      "learning_rate": 0.00012348860457809838,
      "loss": 1.7061,
      "step": 55
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.1328125,
      "learning_rate": 0.00012059786187410984,
      "loss": 1.6714,
      "step": 56
    },
    {
      "epoch": 1.8823529411764706,
      "eval_loss": 1.7563551664352417,
      "eval_runtime": 19.6588,
      "eval_samples_per_second": 2.543,
      "eval_steps_per_second": 0.356,
      "step": 56
    },
    {
      "epoch": 1.9159663865546217,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.0001176890275122573,
      "loss": 1.6318,
      "step": 57
    },
    {
      "epoch": 1.949579831932773,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.00011476465640024814,
      "loss": 1.6693,
      "step": 58
    },
    {
      "epoch": 1.9831932773109244,
      "grad_norm": 0.12353515625,
      "learning_rate": 0.00011182731709213659,
      "loss": 1.5927,
      "step": 59
    },
    {
      "epoch": 2.0168067226890756,
      "grad_norm": 0.138671875,
      "learning_rate": 0.00010887958953229349,
      "loss": 1.6558,
      "step": 60
    },
    {
      "epoch": 2.0504201680672267,
      "grad_norm": 0.134765625,
      "learning_rate": 0.00010592406278937144,
      "loss": 1.7352,
      "step": 61
    },
    {
      "epoch": 2.0840336134453783,
      "grad_norm": 0.1328125,
      "learning_rate": 0.00010296333278225599,
      "loss": 1.6216,
      "step": 62
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.1201171875,
      "learning_rate": 0.0001,
      "loss": 1.6365,
      "step": 63
    },
    {
      "epoch": 2.1512605042016806,
      "grad_norm": 0.1298828125,
      "learning_rate": 9.703666721774402e-05,
      "loss": 1.6249,
      "step": 64
    },
    {
      "epoch": 2.1512605042016806,
      "eval_loss": 1.756639838218689,
      "eval_runtime": 19.5951,
      "eval_samples_per_second": 2.552,
      "eval_steps_per_second": 0.357,
      "step": 64
    },
    {
      "epoch": 2.184873949579832,
      "grad_norm": 0.1357421875,
      "learning_rate": 9.407593721062859e-05,
      "loss": 1.653,
      "step": 65
    },
    {
      "epoch": 2.2184873949579833,
      "grad_norm": 0.146484375,
      "learning_rate": 9.112041046770653e-05,
      "loss": 1.6545,
      "step": 66
    },
    {
      "epoch": 2.2521008403361344,
      "grad_norm": 0.13671875,
      "learning_rate": 8.817268290786343e-05,
      "loss": 1.5787,
      "step": 67
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.1328125,
      "learning_rate": 8.523534359975189e-05,
      "loss": 1.6532,
      "step": 68
    },
    {
      "epoch": 2.3193277310924367,
      "grad_norm": 0.1396484375,
      "learning_rate": 8.231097248774274e-05,
      "loss": 1.6784,
      "step": 69
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.1337890625,
      "learning_rate": 7.940213812589018e-05,
      "loss": 1.5721,
      "step": 70
    },
    {
      "epoch": 2.3865546218487395,
      "grad_norm": 0.1416015625,
      "learning_rate": 7.651139542190164e-05,
      "loss": 1.5836,
      "step": 71
    },
    {
      "epoch": 2.4201680672268906,
      "grad_norm": 0.146484375,
      "learning_rate": 7.364128339309326e-05,
      "loss": 1.5604,
      "step": 72
    },
    {
      "epoch": 2.4201680672268906,
      "eval_loss": 1.7598735094070435,
      "eval_runtime": 19.7508,
      "eval_samples_per_second": 2.532,
      "eval_steps_per_second": 0.354,
      "step": 72
    },
    {
      "epoch": 2.453781512605042,
      "grad_norm": 0.1455078125,
      "learning_rate": 7.079432293630244e-05,
      "loss": 1.6259,
      "step": 73
    },
    {
      "epoch": 2.4873949579831933,
      "grad_norm": 0.1484375,
      "learning_rate": 6.797301461371625e-05,
      "loss": 1.5811,
      "step": 74
    },
    {
      "epoch": 2.5210084033613445,
      "grad_norm": 0.14453125,
      "learning_rate": 6.517983645656014e-05,
      "loss": 1.4929,
      "step": 75
    },
    {
      "epoch": 2.5546218487394956,
      "grad_norm": 0.1572265625,
      "learning_rate": 6.24172417885762e-05,
      "loss": 1.7014,
      "step": 76
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.1484375,
      "learning_rate": 5.96876570712028e-05,
      "loss": 1.5623,
      "step": 77
    },
    {
      "epoch": 2.6218487394957983,
      "grad_norm": 0.1474609375,
      "learning_rate": 5.699347977234799e-05,
      "loss": 1.6006,
      "step": 78
    },
    {
      "epoch": 2.6554621848739495,
      "grad_norm": 0.150390625,
      "learning_rate": 5.43370762606287e-05,
      "loss": 1.6641,
      "step": 79
    },
    {
      "epoch": 2.689075630252101,
      "grad_norm": 0.15234375,
      "learning_rate": 5.172077972692553e-05,
      "loss": 1.7003,
      "step": 80
    },
    {
      "epoch": 2.689075630252101,
      "eval_loss": 1.761399269104004,
      "eval_runtime": 19.6692,
      "eval_samples_per_second": 2.542,
      "eval_steps_per_second": 0.356,
      "step": 80
    },
    {
      "epoch": 2.722689075630252,
      "grad_norm": 0.154296875,
      "learning_rate": 4.914688813507797e-05,
      "loss": 1.6923,
      "step": 81
    },
    {
      "epoch": 2.7563025210084033,
      "grad_norm": 0.158203125,
      "learning_rate": 4.661766220352097e-05,
      "loss": 1.6819,
      "step": 82
    },
    {
      "epoch": 2.7899159663865545,
      "grad_norm": 0.1513671875,
      "learning_rate": 4.4135323419634766e-05,
      "loss": 1.5649,
      "step": 83
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.1494140625,
      "learning_rate": 4.170205208855281e-05,
      "loss": 1.608,
      "step": 84
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.1611328125,
      "learning_rate": 3.931998541814069e-05,
      "loss": 1.5474,
      "step": 85
    },
    {
      "epoch": 2.8907563025210083,
      "grad_norm": 0.1552734375,
      "learning_rate": 3.69912156418289e-05,
      "loss": 1.6484,
      "step": 86
    },
    {
      "epoch": 2.92436974789916,
      "grad_norm": 0.1484375,
      "learning_rate": 3.471778818094785e-05,
      "loss": 1.6145,
      "step": 87
    }
  ],
  "logging_steps": 1,
  "max_steps": 116,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 29,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9933851341357056.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}