{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04349086691794723,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005798782255726297,
      "grad_norm": 72.19591522216797,
      "learning_rate": 1e-05,
      "loss": 9.7221,
      "step": 1
    },
    {
      "epoch": 0.0005798782255726297,
      "eval_loss": 9.690610885620117,
      "eval_runtime": 20.6228,
      "eval_samples_per_second": 281.63,
      "eval_steps_per_second": 8.825,
      "step": 1
    },
    {
      "epoch": 0.0011597564511452595,
      "grad_norm": 84.83391571044922,
      "learning_rate": 2e-05,
      "loss": 9.8583,
      "step": 2
    },
    {
      "epoch": 0.0017396346767178893,
      "grad_norm": 76.03058624267578,
      "learning_rate": 3e-05,
      "loss": 9.6866,
      "step": 3
    },
    {
      "epoch": 0.002319512902290519,
      "grad_norm": 75.7887954711914,
      "learning_rate": 4e-05,
      "loss": 9.2374,
      "step": 4
    },
    {
      "epoch": 0.0028993911278631487,
      "grad_norm": 73.26809692382812,
      "learning_rate": 5e-05,
      "loss": 8.4066,
      "step": 5
    },
    {
      "epoch": 0.0034792693534357786,
      "grad_norm": 51.59004592895508,
      "learning_rate": 6e-05,
      "loss": 7.7976,
      "step": 6
    },
    {
      "epoch": 0.004059147579008408,
      "grad_norm": 41.35436248779297,
      "learning_rate": 7e-05,
      "loss": 7.2723,
      "step": 7
    },
    {
      "epoch": 0.004639025804581038,
      "grad_norm": 21.733489990234375,
      "learning_rate": 8e-05,
      "loss": 6.6234,
      "step": 8
    },
    {
      "epoch": 0.005218904030153668,
      "grad_norm": 29.629690170288086,
      "learning_rate": 9e-05,
      "loss": 5.7096,
      "step": 9
    },
    {
      "epoch": 0.005218904030153668,
      "eval_loss": 4.918065547943115,
      "eval_runtime": 20.5791,
      "eval_samples_per_second": 282.228,
      "eval_steps_per_second": 8.844,
      "step": 9
    },
    {
      "epoch": 0.0057987822557262975,
      "grad_norm": 24.306255340576172,
      "learning_rate": 0.0001,
      "loss": 4.5784,
      "step": 10
    },
    {
      "epoch": 0.006378660481298927,
      "grad_norm": 22.750164031982422,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.1386,
      "step": 11
    },
    {
      "epoch": 0.006958538706871557,
      "grad_norm": 16.85099983215332,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.424,
      "step": 12
    },
    {
      "epoch": 0.007538416932444187,
      "grad_norm": 11.644445419311523,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.5163,
      "step": 13
    },
    {
      "epoch": 0.008118295158016816,
      "grad_norm": 13.419211387634277,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.0114,
      "step": 14
    },
    {
      "epoch": 0.008698173383589447,
      "grad_norm": 11.04304313659668,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.1268,
      "step": 15
    },
    {
      "epoch": 0.009278051609162076,
      "grad_norm": 14.95022201538086,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.5739,
      "step": 16
    },
    {
      "epoch": 0.009857929834734706,
      "grad_norm": 8.970131874084473,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.9381,
      "step": 17
    },
    {
      "epoch": 0.010437808060307335,
      "grad_norm": 15.41360092163086,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1968,
      "step": 18
    },
    {
      "epoch": 0.010437808060307335,
      "eval_loss": 2.0878777503967285,
      "eval_runtime": 25.0521,
      "eval_samples_per_second": 231.837,
      "eval_steps_per_second": 7.265,
      "step": 18
    },
    {
      "epoch": 0.011017686285879966,
      "grad_norm": 26.915355682373047,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7957,
      "step": 19
    },
    {
      "epoch": 0.011597564511452595,
      "grad_norm": 14.224507331848145,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5277,
      "step": 20
    },
    {
      "epoch": 0.012177442737025224,
      "grad_norm": 15.548272132873535,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6963,
      "step": 21
    },
    {
      "epoch": 0.012757320962597855,
      "grad_norm": 20.450119018554688,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.0978,
      "step": 22
    },
    {
      "epoch": 0.013337199188170484,
      "grad_norm": 30.09837532043457,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7468,
      "step": 23
    },
    {
      "epoch": 0.013917077413743114,
      "grad_norm": 29.925216674804688,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5683,
      "step": 24
    },
    {
      "epoch": 0.014496955639315743,
      "grad_norm": 10.300623893737793,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.3637,
      "step": 25
    },
    {
      "epoch": 0.015076833864888374,
      "grad_norm": 12.566941261291504,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5909,
      "step": 26
    },
    {
      "epoch": 0.015656712090461003,
      "grad_norm": 11.902721405029297,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3469,
      "step": 27
    },
    {
      "epoch": 0.015656712090461003,
      "eval_loss": 1.393225073814392,
      "eval_runtime": 45.6636,
      "eval_samples_per_second": 127.191,
      "eval_steps_per_second": 3.986,
      "step": 27
    },
    {
      "epoch": 0.016236590316033632,
      "grad_norm": 6.123865604400635,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.4863,
      "step": 28
    },
    {
      "epoch": 0.016816468541606264,
      "grad_norm": 10.206008911132812,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.3196,
      "step": 29
    },
    {
      "epoch": 0.017396346767178893,
      "grad_norm": 9.587065696716309,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1059,
      "step": 30
    },
    {
      "epoch": 0.017976224992751522,
      "grad_norm": 9.408559799194336,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.5897,
      "step": 31
    },
    {
      "epoch": 0.01855610321832415,
      "grad_norm": 6.678525447845459,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1822,
      "step": 32
    },
    {
      "epoch": 0.01913598144389678,
      "grad_norm": 5.290743827819824,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.9327,
      "step": 33
    },
    {
      "epoch": 0.019715859669469413,
      "grad_norm": 5.287943363189697,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.9831,
      "step": 34
    },
    {
      "epoch": 0.02029573789504204,
      "grad_norm": 4.547323226928711,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.0122,
      "step": 35
    },
    {
      "epoch": 0.02087561612061467,
      "grad_norm": 4.139932155609131,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.9118,
      "step": 36
    },
    {
      "epoch": 0.02087561612061467,
      "eval_loss": 0.9454571008682251,
      "eval_runtime": 20.6133,
      "eval_samples_per_second": 281.76,
      "eval_steps_per_second": 8.829,
      "step": 36
    },
    {
      "epoch": 0.0214554943461873,
      "grad_norm": 4.820893287658691,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7848,
      "step": 37
    },
    {
      "epoch": 0.022035372571759932,
      "grad_norm": 7.449838638305664,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.1475,
      "step": 38
    },
    {
      "epoch": 0.02261525079733256,
      "grad_norm": 6.734663963317871,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.9721,
      "step": 39
    },
    {
      "epoch": 0.02319512902290519,
      "grad_norm": 4.044934272766113,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8632,
      "step": 40
    },
    {
      "epoch": 0.02377500724847782,
      "grad_norm": 6.2852702140808105,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.8913,
      "step": 41
    },
    {
      "epoch": 0.024354885474050448,
      "grad_norm": 5.198728561401367,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.9631,
      "step": 42
    },
    {
      "epoch": 0.02493476369962308,
      "grad_norm": 12.389552116394043,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.8648,
      "step": 43
    },
    {
      "epoch": 0.02551464192519571,
      "grad_norm": 16.09233856201172,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.2013,
      "step": 44
    },
    {
      "epoch": 0.02609452015076834,
      "grad_norm": 9.62452507019043,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.8578,
      "step": 45
    },
    {
      "epoch": 0.02609452015076834,
      "eval_loss": 0.8617116808891296,
      "eval_runtime": 20.6142,
      "eval_samples_per_second": 281.747,
      "eval_steps_per_second": 8.829,
      "step": 45
    },
    {
      "epoch": 0.026674398376340967,
      "grad_norm": 5.45116662979126,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8589,
      "step": 46
    },
    {
      "epoch": 0.0272542766019136,
      "grad_norm": 8.586546897888184,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.0707,
      "step": 47
    },
    {
      "epoch": 0.02783415482748623,
      "grad_norm": 7.391688823699951,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.0134,
      "step": 48
    },
    {
      "epoch": 0.028414033053058858,
      "grad_norm": 6.437960624694824,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.877,
      "step": 49
    },
    {
      "epoch": 0.028993911278631487,
      "grad_norm": 3.7490339279174805,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8931,
      "step": 50
    },
    {
      "epoch": 0.029573789504204116,
      "grad_norm": 5.76321268081665,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8438,
      "step": 51
    },
    {
      "epoch": 0.030153667729776748,
      "grad_norm": 6.54787540435791,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.8288,
      "step": 52
    },
    {
      "epoch": 0.030733545955349377,
      "grad_norm": 5.9420084953308105,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.8325,
      "step": 53
    },
    {
      "epoch": 0.031313424180922006,
      "grad_norm": 4.388433456420898,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.806,
      "step": 54
    },
    {
      "epoch": 0.031313424180922006,
      "eval_loss": 0.8188083171844482,
      "eval_runtime": 20.6473,
      "eval_samples_per_second": 281.296,
      "eval_steps_per_second": 8.815,
      "step": 54
    },
    {
      "epoch": 0.031893302406494635,
      "grad_norm": 4.667327404022217,
      "learning_rate": 5e-05,
      "loss": 0.8285,
      "step": 55
    },
    {
      "epoch": 0.032473180632067264,
      "grad_norm": 4.210194110870361,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8421,
      "step": 56
    },
    {
      "epoch": 0.03305305885763989,
      "grad_norm": 6.773632049560547,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.8522,
      "step": 57
    },
    {
      "epoch": 0.03363293708321253,
      "grad_norm": 4.837597846984863,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7556,
      "step": 58
    },
    {
      "epoch": 0.03421281530878516,
      "grad_norm": 7.49063777923584,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.8624,
      "step": 59
    },
    {
      "epoch": 0.03479269353435779,
      "grad_norm": 2.9477198123931885,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7574,
      "step": 60
    },
    {
      "epoch": 0.035372571759930416,
      "grad_norm": 4.244167327880859,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.8535,
      "step": 61
    },
    {
      "epoch": 0.035952449985503045,
      "grad_norm": 4.019453525543213,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.7877,
      "step": 62
    },
    {
      "epoch": 0.036532328211075674,
      "grad_norm": 4.17199182510376,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.8334,
      "step": 63
    },
    {
      "epoch": 0.036532328211075674,
      "eval_loss": 0.789574921131134,
      "eval_runtime": 20.9404,
      "eval_samples_per_second": 277.358,
      "eval_steps_per_second": 8.691,
      "step": 63
    },
    {
      "epoch": 0.0371122064366483,
      "grad_norm": 3.5703322887420654,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8385,
      "step": 64
    },
    {
      "epoch": 0.03769208466222093,
      "grad_norm": 3.0590972900390625,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8761,
      "step": 65
    },
    {
      "epoch": 0.03827196288779356,
      "grad_norm": 3.206594944000244,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7679,
      "step": 66
    },
    {
      "epoch": 0.038851841113366196,
      "grad_norm": 2.16125750541687,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8023,
      "step": 67
    },
    {
      "epoch": 0.039431719338938825,
      "grad_norm": 3.744929313659668,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.7697,
      "step": 68
    },
    {
      "epoch": 0.040011597564511454,
      "grad_norm": 4.342959403991699,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.8038,
      "step": 69
    },
    {
      "epoch": 0.04059147579008408,
      "grad_norm": 2.113845109939575,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7157,
      "step": 70
    },
    {
      "epoch": 0.04117135401565671,
      "grad_norm": 3.42581844329834,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7877,
      "step": 71
    },
    {
      "epoch": 0.04175123224122934,
      "grad_norm": 3.2024004459381104,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.8178,
      "step": 72
    },
    {
      "epoch": 0.04175123224122934,
      "eval_loss": 0.757203996181488,
      "eval_runtime": 20.7013,
      "eval_samples_per_second": 280.562,
      "eval_steps_per_second": 8.792,
      "step": 72
    },
    {
      "epoch": 0.04233111046680197,
      "grad_norm": 3.951155662536621,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7732,
      "step": 73
    },
    {
      "epoch": 0.0429109886923746,
      "grad_norm": 2.8352742195129395,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.7979,
      "step": 74
    },
    {
      "epoch": 0.04349086691794723,
      "grad_norm": 3.528505563735962,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.836,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.08810631610368e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}