{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.976,
  "eval_steps": 500,
  "global_step": 93,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032,
      "grad_norm": 5.84940669389189,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8186,
      "step": 1
    },
    {
      "epoch": 0.064,
      "grad_norm": 5.896903453045604,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8458,
      "step": 2
    },
    {
      "epoch": 0.096,
      "grad_norm": 5.37344284173292,
      "learning_rate": 6e-06,
      "loss": 0.8188,
      "step": 3
    },
    {
      "epoch": 0.128,
      "grad_norm": 4.074873898614128,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8172,
      "step": 4
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.5041237379672117,
      "learning_rate": 1e-05,
      "loss": 0.7248,
      "step": 5
    },
    {
      "epoch": 0.192,
      "grad_norm": 4.734108824557778,
      "learning_rate": 1.2e-05,
      "loss": 0.8667,
      "step": 6
    },
    {
      "epoch": 0.224,
      "grad_norm": 4.9352242442739644,
      "learning_rate": 1.4e-05,
      "loss": 0.8164,
      "step": 7
    },
    {
      "epoch": 0.256,
      "grad_norm": 5.9000233595966245,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7703,
      "step": 8
    },
    {
      "epoch": 0.288,
      "grad_norm": 4.734616460225017,
      "learning_rate": 1.8e-05,
      "loss": 0.7283,
      "step": 9
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.69112201268641,
      "learning_rate": 2e-05,
      "loss": 0.7136,
      "step": 10
    },
    {
      "epoch": 0.352,
      "grad_norm": 2.8584464139967802,
      "learning_rate": 1.9992837548163315e-05,
      "loss": 0.7436,
      "step": 11
    },
    {
      "epoch": 0.384,
      "grad_norm": 2.2914048959495643,
      "learning_rate": 1.9971360452796523e-05,
      "loss": 0.6954,
      "step": 12
    },
    {
      "epoch": 0.416,
      "grad_norm": 1.5463017334976934,
      "learning_rate": 1.993559947963185e-05,
      "loss": 0.6304,
      "step": 13
    },
    {
      "epoch": 0.448,
      "grad_norm": 1.6244483288113523,
      "learning_rate": 1.9885605855918887e-05,
      "loss": 0.661,
      "step": 14
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.3804731125445038,
      "learning_rate": 1.9821451197042028e-05,
      "loss": 0.621,
      "step": 15
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.2049483348062489,
      "learning_rate": 1.9743227403932135e-05,
      "loss": 0.6491,
      "step": 16
    },
    {
      "epoch": 0.544,
      "grad_norm": 1.0219653970996074,
      "learning_rate": 1.9651046531419335e-05,
      "loss": 0.6351,
      "step": 17
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.9718497121562397,
      "learning_rate": 1.9545040627715554e-05,
      "loss": 0.6125,
      "step": 18
    },
    {
      "epoch": 0.608,
      "grad_norm": 1.1088690421377412,
      "learning_rate": 1.942536154525673e-05,
      "loss": 0.6397,
      "step": 19
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9455104536203861,
      "learning_rate": 1.9292180723175656e-05,
      "loss": 0.5623,
      "step": 20
    },
    {
      "epoch": 0.672,
      "grad_norm": 1.1136726884833483,
      "learning_rate": 1.9145688941717074e-05,
      "loss": 0.5951,
      "step": 21
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.9962571929358678,
      "learning_rate": 1.8986096048946826e-05,
      "loss": 0.6159,
      "step": 22
    },
    {
      "epoch": 0.736,
      "grad_norm": 1.0516488446346473,
      "learning_rate": 1.881363066014649e-05,
      "loss": 0.5522,
      "step": 23
    },
    {
      "epoch": 0.768,
      "grad_norm": 1.2789484698437357,
      "learning_rate": 1.862853983032423e-05,
      "loss": 0.6563,
      "step": 24
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9726925447037389,
      "learning_rate": 1.8431088700310846e-05,
      "loss": 0.5965,
      "step": 25
    },
    {
      "epoch": 0.832,
      "grad_norm": 1.3114557015981112,
      "learning_rate": 1.8221560116948103e-05,
      "loss": 0.6577,
      "step": 26
    },
    {
      "epoch": 0.864,
      "grad_norm": 1.2317571230112236,
      "learning_rate": 1.8000254227913346e-05,
      "loss": 0.5977,
      "step": 27
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.9966337703489971,
      "learning_rate": 1.7767488051760858e-05,
      "loss": 0.5929,
      "step": 28
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.9244122578843538,
      "learning_rate": 1.7523595023795814e-05,
      "loss": 0.6165,
      "step": 29
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9902344039161873,
      "learning_rate": 1.7268924518431437e-05,
      "loss": 0.6351,
      "step": 30
    },
    {
      "epoch": 0.992,
      "grad_norm": 1.1385173043161212,
      "learning_rate": 1.700384134871351e-05,
      "loss": 0.5994,
      "step": 31
    },
    {
      "epoch": 1.024,
      "grad_norm": 1.7131457418457308,
      "learning_rate": 1.672872524372919e-05,
      "loss": 0.8536,
      "step": 32
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.9887680712926848,
      "learning_rate": 1.644397030464877e-05,
      "loss": 0.4804,
      "step": 33
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.7381068345404209,
      "learning_rate": 1.614998444017954e-05,
      "loss": 0.4955,
      "step": 34
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.9618580890399832,
      "learning_rate": 1.5847188782240473e-05,
      "loss": 0.5212,
      "step": 35
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.8787637974871335,
      "learning_rate": 1.5536017082694846e-05,
      "loss": 0.4318,
      "step": 36
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.9577670072498041,
      "learning_rate": 1.5216915092004847e-05,
      "loss": 0.5298,
      "step": 37
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.9473329613695382,
      "learning_rate": 1.4890339920698334e-05,
      "loss": 0.5354,
      "step": 38
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.8919615677703958,
      "learning_rate": 1.4556759384562418e-05,
      "loss": 0.4242,
      "step": 39
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.8567752824441381,
      "learning_rate": 1.421665133450184e-05,
      "loss": 0.4599,
      "step": 40
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.7949595792187416,
      "learning_rate": 1.3870502972022175e-05,
      "loss": 0.4125,
      "step": 41
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 1.3123308076615146,
      "learning_rate": 1.351881015131833e-05,
      "loss": 0.5169,
      "step": 42
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.7318049114768788,
      "learning_rate": 1.316207666896824e-05,
      "loss": 0.4106,
      "step": 43
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.9425576795296489,
      "learning_rate": 1.2800813542249073e-05,
      "loss": 0.5101,
      "step": 44
    },
    {
      "epoch": 1.44,
      "grad_norm": 1.021797619309871,
      "learning_rate": 1.2435538277109919e-05,
      "loss": 0.5469,
      "step": 45
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.7986312330336192,
      "learning_rate": 1.206677412684953e-05,
      "loss": 0.4318,
      "step": 46
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.9215393491076125,
      "learning_rate": 1.1695049342560969e-05,
      "loss": 0.4563,
      "step": 47
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.9830101157364164,
      "learning_rate": 1.1320896416417026e-05,
      "loss": 0.5076,
      "step": 48
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.8438722321960386,
      "learning_rate": 1.0944851318880314e-05,
      "loss": 0.516,
      "step": 49
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.8787060713492011,
      "learning_rate": 1.0567452730930743e-05,
      "loss": 0.462,
      "step": 50
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.9033596868361128,
      "learning_rate": 1.0189241272410191e-05,
      "loss": 0.4514,
      "step": 51
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.8693144222274771,
      "learning_rate": 9.810758727589814e-06,
      "loss": 0.5001,
      "step": 52
    },
    {
      "epoch": 1.696,
      "grad_norm": 1.1029488992826821,
      "learning_rate": 9.43254726906926e-06,
      "loss": 0.4482,
      "step": 53
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.9000678022323099,
      "learning_rate": 9.055148681119688e-06,
      "loss": 0.4322,
      "step": 54
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.7216561884978123,
      "learning_rate": 8.67910358358298e-06,
      "loss": 0.4316,
      "step": 55
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.8319129824124409,
      "learning_rate": 8.304950657439034e-06,
      "loss": 0.4805,
      "step": 56
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.7932990650658038,
      "learning_rate": 7.93322587315047e-06,
      "loss": 0.433,
      "step": 57
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.7262577838163997,
      "learning_rate": 7.564461722890082e-06,
      "loss": 0.4647,
      "step": 58
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.6953985526658658,
      "learning_rate": 7.199186457750931e-06,
      "loss": 0.3784,
      "step": 59
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.6944361567845883,
      "learning_rate": 6.837923331031761e-06,
      "loss": 0.4661,
      "step": 60
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.8214460648196689,
      "learning_rate": 6.48118984868167e-06,
      "loss": 0.4882,
      "step": 61
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.6777654072216326,
      "learning_rate": 6.129497027977829e-06,
      "loss": 0.4669,
      "step": 62
    },
    {
      "epoch": 2.016,
      "grad_norm": 1.2880141378220575,
      "learning_rate": 5.78334866549816e-06,
      "loss": 0.6206,
      "step": 63
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.7107669765897068,
      "learning_rate": 5.443240615437586e-06,
      "loss": 0.3816,
      "step": 64
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.801586001212043,
      "learning_rate": 5.109660079301668e-06,
      "loss": 0.402,
      "step": 65
    },
    {
      "epoch": 2.112,
      "grad_norm": 0.564818291485468,
      "learning_rate": 4.783084907995156e-06,
      "loss": 0.3663,
      "step": 66
    },
    {
      "epoch": 2.144,
      "grad_norm": 0.6168891844281424,
      "learning_rate": 4.463982917305155e-06,
      "loss": 0.3979,
      "step": 67
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.5270099669215162,
      "learning_rate": 4.152811217759529e-06,
      "loss": 0.2757,
      "step": 68
    },
    {
      "epoch": 2.208,
      "grad_norm": 0.5965579042575382,
      "learning_rate": 3.850015559820465e-06,
      "loss": 0.3429,
      "step": 69
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.7256008814807648,
      "learning_rate": 3.5560296953512296e-06,
      "loss": 0.3981,
      "step": 70
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.7161869101911601,
      "learning_rate": 3.2712747562708115e-06,
      "loss": 0.37,
      "step": 71
    },
    {
      "epoch": 2.304,
      "grad_norm": 0.7454025067253681,
      "learning_rate": 2.9961586512864947e-06,
      "loss": 0.4165,
      "step": 72
    },
    {
      "epoch": 2.336,
      "grad_norm": 0.5449062983518381,
      "learning_rate": 2.7310754815685627e-06,
      "loss": 0.3389,
      "step": 73
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.5651340234901367,
      "learning_rate": 2.4764049762041874e-06,
      "loss": 0.3643,
      "step": 74
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.5223439740041005,
      "learning_rate": 2.2325119482391466e-06,
      "loss": 0.2996,
      "step": 75
    },
    {
      "epoch": 2.432,
      "grad_norm": 0.6691922082645556,
      "learning_rate": 1.9997457720866554e-06,
      "loss": 0.4327,
      "step": 76
    },
    {
      "epoch": 2.464,
      "grad_norm": 0.5466794083662679,
      "learning_rate": 1.7784398830519002e-06,
      "loss": 0.315,
      "step": 77
    },
    {
      "epoch": 2.496,
      "grad_norm": 0.513132554481501,
      "learning_rate": 1.5689112996891576e-06,
      "loss": 0.343,
      "step": 78
    },
    {
      "epoch": 2.528,
      "grad_norm": 0.5748198370777368,
      "learning_rate": 1.3714601696757713e-06,
      "loss": 0.3484,
      "step": 79
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.6254281609397252,
      "learning_rate": 1.1863693398535115e-06,
      "loss": 0.4159,
      "step": 80
    },
    {
      "epoch": 2.592,
      "grad_norm": 0.6161841782227268,
      "learning_rate": 1.01390395105318e-06,
      "loss": 0.384,
      "step": 81
    },
    {
      "epoch": 2.624,
      "grad_norm": 0.5502099035422106,
      "learning_rate": 8.543110582829272e-07,
      "loss": 0.3486,
      "step": 82
    },
    {
      "epoch": 2.656,
      "grad_norm": 0.5545865136491874,
      "learning_rate": 7.078192768243486e-07,
      "loss": 0.3445,
      "step": 83
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 0.5443978320460648,
      "learning_rate": 5.746384547432738e-07,
      "loss": 0.3915,
      "step": 84
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.5314622355578005,
      "learning_rate": 4.549593722844492e-07,
      "loss": 0.4302,
      "step": 85
    },
    {
      "epoch": 2.752,
      "grad_norm": 0.4457783159087401,
      "learning_rate": 3.4895346858066723e-07,
      "loss": 0.2589,
      "step": 86
    },
    {
      "epoch": 2.784,
      "grad_norm": 0.5941803419468483,
      "learning_rate": 2.5677259606786686e-07,
      "loss": 0.3742,
      "step": 87
    },
    {
      "epoch": 2.816,
      "grad_norm": 0.5084378111189841,
      "learning_rate": 1.7854880295797406e-07,
      "loss": 0.3535,
      "step": 88
    },
    {
      "epoch": 2.848,
      "grad_norm": 0.4740275071409764,
      "learning_rate": 1.1439414408111471e-07,
      "loss": 0.3458,
      "step": 89
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.6664191454899007,
      "learning_rate": 6.440052036815081e-08,
      "loss": 0.4665,
      "step": 90
    },
    {
      "epoch": 2.912,
      "grad_norm": 0.4715443059942868,
      "learning_rate": 2.86395472034795e-08,
      "loss": 0.3022,
      "step": 91
    },
    {
      "epoch": 2.944,
      "grad_norm": 0.5808333713792009,
      "learning_rate": 7.162451836685291e-09,
      "loss": 0.3701,
      "step": 92
    },
    {
      "epoch": 2.976,
      "grad_norm": 0.5008683379834068,
      "learning_rate": 0.0,
      "loss": 0.295,
      "step": 93
    },
    {
      "epoch": 2.976,
      "step": 93,
      "total_flos": 5.107931021941146e+16,
      "train_loss": 0.5110146377676277,
      "train_runtime": 3237.991,
      "train_samples_per_second": 0.923,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 93,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.107931021941146e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}