{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006743088334457181,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.990784445942908e-05,
      "grad_norm": 15.35192584991455,
      "learning_rate": 1e-05,
      "loss": 12.6326,
      "step": 1
    },
    {
      "epoch": 8.990784445942908e-05,
      "eval_loss": 12.586104393005371,
      "eval_runtime": 276.5266,
      "eval_samples_per_second": 33.874,
      "eval_steps_per_second": 4.235,
      "step": 1
    },
    {
      "epoch": 0.00017981568891885816,
      "grad_norm": 16.091136932373047,
      "learning_rate": 2e-05,
      "loss": 12.5988,
      "step": 2
    },
    {
      "epoch": 0.00026972353337828726,
      "grad_norm": 14.455317497253418,
      "learning_rate": 3e-05,
      "loss": 12.5276,
      "step": 3
    },
    {
      "epoch": 0.0003596313778377163,
      "grad_norm": 15.562151908874512,
      "learning_rate": 4e-05,
      "loss": 12.5544,
      "step": 4
    },
    {
      "epoch": 0.0004495392222971454,
      "grad_norm": 13.742938995361328,
      "learning_rate": 5e-05,
      "loss": 12.5895,
      "step": 5
    },
    {
      "epoch": 0.0005394470667565745,
      "grad_norm": 14.714332580566406,
      "learning_rate": 6e-05,
      "loss": 12.6172,
      "step": 6
    },
    {
      "epoch": 0.0006293549112160036,
      "grad_norm": 11.049238204956055,
      "learning_rate": 7e-05,
      "loss": 12.4842,
      "step": 7
    },
    {
      "epoch": 0.0007192627556754326,
      "grad_norm": 13.16402816772461,
      "learning_rate": 8e-05,
      "loss": 12.302,
      "step": 8
    },
    {
      "epoch": 0.0008091706001348617,
      "grad_norm": 12.623836517333984,
      "learning_rate": 9e-05,
      "loss": 12.2529,
      "step": 9
    },
    {
      "epoch": 0.0008091706001348617,
      "eval_loss": 12.082995414733887,
      "eval_runtime": 277.7717,
      "eval_samples_per_second": 33.722,
      "eval_steps_per_second": 4.216,
      "step": 9
    },
    {
      "epoch": 0.0008990784445942908,
      "grad_norm": 10.00021743774414,
      "learning_rate": 0.0001,
      "loss": 12.0075,
      "step": 10
    },
    {
      "epoch": 0.0009889862890537198,
      "grad_norm": 9.958125114440918,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.9523,
      "step": 11
    },
    {
      "epoch": 0.001078894133513149,
      "grad_norm": 10.316842079162598,
      "learning_rate": 9.987820251299122e-05,
      "loss": 11.8709,
      "step": 12
    },
    {
      "epoch": 0.001168801977972578,
      "grad_norm": 10.072561264038086,
      "learning_rate": 9.972609476841367e-05,
      "loss": 11.7194,
      "step": 13
    },
    {
      "epoch": 0.0012587098224320073,
      "grad_norm": 9.017184257507324,
      "learning_rate": 9.951340343707852e-05,
      "loss": 11.5661,
      "step": 14
    },
    {
      "epoch": 0.0013486176668914363,
      "grad_norm": 8.668551445007324,
      "learning_rate": 9.924038765061042e-05,
      "loss": 11.4991,
      "step": 15
    },
    {
      "epoch": 0.0014385255113508653,
      "grad_norm": 8.481941223144531,
      "learning_rate": 9.890738003669029e-05,
      "loss": 11.3203,
      "step": 16
    },
    {
      "epoch": 0.0015284333558102945,
      "grad_norm": 7.682249546051025,
      "learning_rate": 9.851478631379982e-05,
      "loss": 11.2815,
      "step": 17
    },
    {
      "epoch": 0.0016183412002697235,
      "grad_norm": 7.486232280731201,
      "learning_rate": 9.806308479691595e-05,
      "loss": 11.1782,
      "step": 18
    },
    {
      "epoch": 0.0016183412002697235,
      "eval_loss": 11.049551010131836,
      "eval_runtime": 277.8127,
      "eval_samples_per_second": 33.717,
      "eval_steps_per_second": 4.215,
      "step": 18
    },
    {
      "epoch": 0.0017082490447291527,
      "grad_norm": 7.089673042297363,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.9657,
      "step": 19
    },
    {
      "epoch": 0.0017981568891885817,
      "grad_norm": 6.506858825683594,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.9544,
      "step": 20
    },
    {
      "epoch": 0.001888064733648011,
      "grad_norm": 6.114770412445068,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.8534,
      "step": 21
    },
    {
      "epoch": 0.0019779725781074397,
      "grad_norm": 5.774037837982178,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.7668,
      "step": 22
    },
    {
      "epoch": 0.002067880422566869,
      "grad_norm": 5.377146244049072,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.7447,
      "step": 23
    },
    {
      "epoch": 0.002157788267026298,
      "grad_norm": 4.897111892700195,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.5888,
      "step": 24
    },
    {
      "epoch": 0.0022476961114857273,
      "grad_norm": 4.556328773498535,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.5711,
      "step": 25
    },
    {
      "epoch": 0.002337603955945156,
      "grad_norm": 4.229061126708984,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.4582,
      "step": 26
    },
    {
      "epoch": 0.0024275118004045853,
      "grad_norm": 3.9010009765625,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3399,
      "step": 27
    },
    {
      "epoch": 0.0024275118004045853,
      "eval_loss": 10.372447967529297,
      "eval_runtime": 278.6935,
      "eval_samples_per_second": 33.61,
      "eval_steps_per_second": 4.202,
      "step": 27
    },
    {
      "epoch": 0.0025174196448640145,
      "grad_norm": 3.8348143100738525,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.368,
      "step": 28
    },
    {
      "epoch": 0.0026073274893234433,
      "grad_norm": 3.8159286975860596,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3203,
      "step": 29
    },
    {
      "epoch": 0.0026972353337828725,
      "grad_norm": 3.768986701965332,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.229,
      "step": 30
    },
    {
      "epoch": 0.0027871431782423017,
      "grad_norm": 3.285841226577759,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.2177,
      "step": 31
    },
    {
      "epoch": 0.0028770510227017305,
      "grad_norm": 3.159271717071533,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.2111,
      "step": 32
    },
    {
      "epoch": 0.0029669588671611597,
      "grad_norm": 3.253580093383789,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.1252,
      "step": 33
    },
    {
      "epoch": 0.003056866711620589,
      "grad_norm": 2.9121267795562744,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.0366,
      "step": 34
    },
    {
      "epoch": 0.003146774556080018,
      "grad_norm": 3.051910877227783,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.0212,
      "step": 35
    },
    {
      "epoch": 0.003236682400539447,
      "grad_norm": 2.968033790588379,
      "learning_rate": 8.07830737662829e-05,
      "loss": 9.9681,
      "step": 36
    },
    {
      "epoch": 0.003236682400539447,
      "eval_loss": 9.952634811401367,
      "eval_runtime": 277.8158,
      "eval_samples_per_second": 33.717,
      "eval_steps_per_second": 4.215,
      "step": 36
    },
    {
      "epoch": 0.003326590244998876,
      "grad_norm": 3.547006368637085,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.0527,
      "step": 37
    },
    {
      "epoch": 0.0034164980894583054,
      "grad_norm": 2.7204442024230957,
      "learning_rate": 7.795964517353735e-05,
      "loss": 9.9405,
      "step": 38
    },
    {
      "epoch": 0.003506405933917734,
      "grad_norm": 2.5418879985809326,
      "learning_rate": 7.649596321166024e-05,
      "loss": 9.9415,
      "step": 39
    },
    {
      "epoch": 0.0035963137783771634,
      "grad_norm": 2.5071489810943604,
      "learning_rate": 7.500000000000001e-05,
      "loss": 9.8407,
      "step": 40
    },
    {
      "epoch": 0.0036862216228365926,
      "grad_norm": 2.51804256439209,
      "learning_rate": 7.347357813929454e-05,
      "loss": 9.839,
      "step": 41
    },
    {
      "epoch": 0.003776129467296022,
      "grad_norm": 2.4780120849609375,
      "learning_rate": 7.191855733945387e-05,
      "loss": 9.7702,
      "step": 42
    },
    {
      "epoch": 0.0038660373117554506,
      "grad_norm": 2.4401473999023438,
      "learning_rate": 7.033683215379002e-05,
      "loss": 9.7464,
      "step": 43
    },
    {
      "epoch": 0.003955945156214879,
      "grad_norm": 2.6967058181762695,
      "learning_rate": 6.873032967079561e-05,
      "loss": 9.7149,
      "step": 44
    },
    {
      "epoch": 0.004045853000674309,
      "grad_norm": 2.307387590408325,
      "learning_rate": 6.710100716628344e-05,
      "loss": 9.7137,
      "step": 45
    },
    {
      "epoch": 0.004045853000674309,
      "eval_loss": 9.660048484802246,
      "eval_runtime": 277.8194,
      "eval_samples_per_second": 33.716,
      "eval_steps_per_second": 4.215,
      "step": 45
    },
    {
      "epoch": 0.004135760845133738,
      "grad_norm": 3.0555312633514404,
      "learning_rate": 6.545084971874738e-05,
      "loss": 9.6815,
      "step": 46
    },
    {
      "epoch": 0.004225668689593167,
      "grad_norm": 2.2399892807006836,
      "learning_rate": 6.378186779084995e-05,
      "loss": 9.5969,
      "step": 47
    },
    {
      "epoch": 0.004315576534052596,
      "grad_norm": 2.142436981201172,
      "learning_rate": 6.209609477998338e-05,
      "loss": 9.6154,
      "step": 48
    },
    {
      "epoch": 0.004405484378512025,
      "grad_norm": 2.128260850906372,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 9.5917,
      "step": 49
    },
    {
      "epoch": 0.004495392222971455,
      "grad_norm": 2.3412411212921143,
      "learning_rate": 5.868240888334653e-05,
      "loss": 9.56,
      "step": 50
    },
    {
      "epoch": 0.004585300067430883,
      "grad_norm": 1.991762638092041,
      "learning_rate": 5.695865504800327e-05,
      "loss": 9.5354,
      "step": 51
    },
    {
      "epoch": 0.004675207911890312,
      "grad_norm": 1.9422123432159424,
      "learning_rate": 5.522642316338268e-05,
      "loss": 9.4861,
      "step": 52
    },
    {
      "epoch": 0.004765115756349742,
      "grad_norm": 2.228233814239502,
      "learning_rate": 5.348782368720626e-05,
      "loss": 9.5084,
      "step": 53
    },
    {
      "epoch": 0.004855023600809171,
      "grad_norm": 1.9608817100524902,
      "learning_rate": 5.174497483512506e-05,
      "loss": 9.5101,
      "step": 54
    },
    {
      "epoch": 0.004855023600809171,
      "eval_loss": 9.457647323608398,
      "eval_runtime": 277.828,
      "eval_samples_per_second": 33.715,
      "eval_steps_per_second": 4.215,
      "step": 54
    },
    {
      "epoch": 0.004944931445268599,
      "grad_norm": 2.0444347858428955,
      "learning_rate": 5e-05,
      "loss": 9.4672,
      "step": 55
    },
    {
      "epoch": 0.005034839289728029,
      "grad_norm": 1.891008734703064,
      "learning_rate": 4.825502516487497e-05,
      "loss": 9.4241,
      "step": 56
    },
    {
      "epoch": 0.005124747134187458,
      "grad_norm": 1.8363993167877197,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 9.3972,
      "step": 57
    },
    {
      "epoch": 0.005214654978646887,
      "grad_norm": 2.2685086727142334,
      "learning_rate": 4.477357683661734e-05,
      "loss": 9.397,
      "step": 58
    },
    {
      "epoch": 0.005304562823106316,
      "grad_norm": 1.9216326475143433,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 9.3545,
      "step": 59
    },
    {
      "epoch": 0.005394470667565745,
      "grad_norm": 2.332538604736328,
      "learning_rate": 4.131759111665349e-05,
      "loss": 9.405,
      "step": 60
    },
    {
      "epoch": 0.005484378512025174,
      "grad_norm": 1.7659024000167847,
      "learning_rate": 3.960441545911204e-05,
      "loss": 9.3803,
      "step": 61
    },
    {
      "epoch": 0.0055742863564846035,
      "grad_norm": 1.8336716890335083,
      "learning_rate": 3.790390522001662e-05,
      "loss": 9.3318,
      "step": 62
    },
    {
      "epoch": 0.005664194200944032,
      "grad_norm": 2.0182368755340576,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 9.3278,
      "step": 63
    },
    {
      "epoch": 0.005664194200944032,
      "eval_loss": 9.32175064086914,
      "eval_runtime": 277.826,
      "eval_samples_per_second": 33.715,
      "eval_steps_per_second": 4.215,
      "step": 63
    },
    {
      "epoch": 0.005754102045403461,
      "grad_norm": 1.7670087814331055,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 9.3028,
      "step": 64
    },
    {
      "epoch": 0.005844009889862891,
      "grad_norm": 1.8420675992965698,
      "learning_rate": 3.289899283371657e-05,
      "loss": 9.3358,
      "step": 65
    },
    {
      "epoch": 0.0059339177343223195,
      "grad_norm": 1.6964224576950073,
      "learning_rate": 3.12696703292044e-05,
      "loss": 9.269,
      "step": 66
    },
    {
      "epoch": 0.006023825578781749,
      "grad_norm": 1.6834877729415894,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 9.2445,
      "step": 67
    },
    {
      "epoch": 0.006113733423241178,
      "grad_norm": 1.7772903442382812,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 9.2601,
      "step": 68
    },
    {
      "epoch": 0.006203641267700607,
      "grad_norm": 1.563933253288269,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 9.2604,
      "step": 69
    },
    {
      "epoch": 0.006293549112160036,
      "grad_norm": 1.5275280475616455,
      "learning_rate": 2.500000000000001e-05,
      "loss": 9.2818,
      "step": 70
    },
    {
      "epoch": 0.006383456956619465,
      "grad_norm": 1.6983492374420166,
      "learning_rate": 2.350403678833976e-05,
      "loss": 9.2964,
      "step": 71
    },
    {
      "epoch": 0.006473364801078894,
      "grad_norm": 1.6340742111206055,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 9.2188,
      "step": 72
    },
    {
      "epoch": 0.006473364801078894,
      "eval_loss": 9.23674488067627,
      "eval_runtime": 277.8141,
      "eval_samples_per_second": 33.717,
      "eval_steps_per_second": 4.215,
      "step": 72
    },
    {
      "epoch": 0.0065632726455383235,
      "grad_norm": 1.6606789827346802,
      "learning_rate": 2.061073738537635e-05,
      "loss": 9.2576,
      "step": 73
    },
    {
      "epoch": 0.006653180489997752,
      "grad_norm": 1.682219386100769,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 9.2142,
      "step": 74
    },
    {
      "epoch": 0.006743088334457181,
      "grad_norm": 2.0931785106658936,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 9.1882,
      "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": 39909794512896.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}