{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 12,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.7285156846046448,
      "learning_rate": 0.0,
      "loss": 2.265625,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.8744295835494995,
      "learning_rate": 2.5e-05,
      "loss": 2.2958984375,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.707972526550293,
      "learning_rate": 5e-05,
      "loss": 2.197509765625,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.47509288787841797,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9765625,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.15270085632801056,
      "learning_rate": 0.0001,
      "loss": 1.84521484375,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.10096657276153564,
      "learning_rate": 9.99362213054543e-05,
      "loss": 1.78857421875,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.11879778653383255,
      "learning_rate": 9.974506600945618e-05,
      "loss": 1.83447265625,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.1394820213317871,
      "learning_rate": 9.942707596246052e-05,
      "loss": 1.79443359375,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.12889999151229858,
      "learning_rate": 9.8983152541804e-05,
      "loss": 1.72900390625,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.11798744648694992,
      "learning_rate": 9.841455409665323e-05,
      "loss": 1.6611328125,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.10778991132974625,
      "learning_rate": 9.772289238107715e-05,
      "loss": 1.657958984375,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.11877302080392838,
      "learning_rate": 9.691012798535524e-05,
      "loss": 1.617919921875,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.11993581056594849,
      "learning_rate": 9.59785647784711e-05,
      "loss": 1.664794921875,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.10702720284461975,
      "learning_rate": 9.493084337754573e-05,
      "loss": 1.51708984375,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.0843004509806633,
      "learning_rate": 9.376993366272128e-05,
      "loss": 1.591796875,
      "step": 15
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 1.55517578125,
      "eval_runtime": 5.081,
      "eval_samples_per_second": 0.787,
      "eval_steps_per_second": 0.197,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.07435919344425201,
      "learning_rate": 9.249912635871318e-05,
      "loss": 1.574951171875,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.0768747329711914,
      "learning_rate": 9.112202370689337e-05,
      "loss": 1.6044921875,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.09450701624155045,
      "learning_rate": 8.964252925434579e-05,
      "loss": 1.5732421875,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.08037487417459488,
      "learning_rate": 8.806483678883803e-05,
      "loss": 1.53759765625,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.08016908168792725,
      "learning_rate": 8.639341845107433e-05,
      "loss": 1.48974609375,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.08489606529474258,
      "learning_rate": 8.463301205792675e-05,
      "loss": 1.484375,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.08712036162614822,
      "learning_rate": 8.278860767257865e-05,
      "loss": 1.51904296875,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.07777861505746841,
      "learning_rate": 8.086543345964832e-05,
      "loss": 1.52294921875,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.06942926347255707,
      "learning_rate": 7.886894086538841e-05,
      "loss": 1.4566650390625,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.06922606378793716,
      "learning_rate": 7.680478916496926e-05,
      "loss": 1.4736328125,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.10756262391805649,
      "learning_rate": 7.46788294206485e-05,
      "loss": 1.421630859375,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.0812968835234642,
      "learning_rate": 7.249708789629944e-05,
      "loss": 1.4189453125,
      "step": 27
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": 1.43017578125,
      "eval_runtime": 5.061,
      "eval_samples_per_second": 0.79,
      "eval_steps_per_second": 0.198,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.06487224251031876,
      "learning_rate": 7.026574897531137e-05,
      "loss": 1.484619140625,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.11446287482976913,
      "learning_rate": 6.799113763028295e-05,
      "loss": 1.4599609375,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.061298832297325134,
      "learning_rate": 6.567970149420018e-05,
      "loss": 1.4345703125,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.06884041428565979,
      "learning_rate": 6.333799258392015e-05,
      "loss": 1.37255859375,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.06530533730983734,
      "learning_rate": 6.097264872776749e-05,
      "loss": 1.3865966796875,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.07631056010723114,
      "learning_rate": 5.859037474988874e-05,
      "loss": 1.355712890625,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.07293955236673355,
      "learning_rate": 5.6197923464699875e-05,
      "loss": 1.431884765625,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.08120140433311462,
      "learning_rate": 5.3802076535300135e-05,
      "loss": 1.27734375,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.06899567693471909,
      "learning_rate": 5.140962525011126e-05,
      "loss": 1.392578125,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.06586313992738724,
      "learning_rate": 4.902735127223252e-05,
      "loss": 1.38916015625,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.0632728636264801,
      "learning_rate": 4.6662007416079864e-05,
      "loss": 1.43505859375,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.06368006765842438,
      "learning_rate": 4.432029850579983e-05,
      "loss": 1.4033203125,
      "step": 39
    },
    {
      "epoch": 1.8571428571428572,
      "eval_loss": 1.36083984375,
      "eval_runtime": 5.0652,
      "eval_samples_per_second": 0.79,
      "eval_steps_per_second": 0.197,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.06019105762243271,
      "learning_rate": 4.2008862369717074e-05,
      "loss": 1.37841796875,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.06852934509515762,
      "learning_rate": 3.973425102468864e-05,
      "loss": 1.324951171875,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07731995731592178,
      "learning_rate": 3.750291210370057e-05,
      "loss": 1.33251953125,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.06647676974534988,
      "learning_rate": 3.5321170579351516e-05,
      "loss": 1.37451171875,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.06389626860618591,
      "learning_rate": 3.319521083503075e-05,
      "loss": 1.386962890625,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.06924697011709213,
      "learning_rate": 3.113105913461159e-05,
      "loss": 1.33056640625,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.06576833128929138,
      "learning_rate": 2.9134566540351693e-05,
      "loss": 1.358642578125,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.06895660609006882,
      "learning_rate": 2.721139232742137e-05,
      "loss": 1.3031005859375,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.09544253349304199,
      "learning_rate": 2.5366987942073267e-05,
      "loss": 1.299560546875,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.06581106781959534,
      "learning_rate": 2.3606581548925695e-05,
      "loss": 1.381591796875,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.06757261604070663,
      "learning_rate": 2.1935163211161985e-05,
      "loss": 1.36279296875,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.06766699999570847,
      "learning_rate": 2.0357470745654214e-05,
      "loss": 1.34130859375,
      "step": 51
    },
    {
      "epoch": 2.4285714285714284,
      "eval_loss": 1.328125,
      "eval_runtime": 5.0567,
      "eval_samples_per_second": 0.791,
      "eval_steps_per_second": 0.198,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.07995021343231201,
      "learning_rate": 1.8877976293106646e-05,
      "loss": 1.28076171875,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.06969735026359558,
      "learning_rate": 1.7500873641286825e-05,
      "loss": 1.30712890625,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.06776302307844162,
      "learning_rate": 1.6230066337278724e-05,
      "loss": 1.2781982421875,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.07185522466897964,
      "learning_rate": 1.5069156622454287e-05,
      "loss": 1.357177734375,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.07692070305347443,
      "learning_rate": 1.4021435221528906e-05,
      "loss": 1.1956787109375,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.06928940117359161,
      "learning_rate": 1.3089872014644771e-05,
      "loss": 1.32763671875,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.06275974214076996,
      "learning_rate": 1.2277107618922843e-05,
      "loss": 1.3272705078125,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.07041693478822708,
      "learning_rate": 1.1585445903346783e-05,
      "loss": 1.37841796875,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.06966356188058853,
      "learning_rate": 1.1016847458196001e-05,
      "loss": 1.3466796875,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.0679149404168129,
      "learning_rate": 1.0572924037539496e-05,
      "loss": 1.3291015625,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.06559661775827408,
      "learning_rate": 1.0254933990543831e-05,
      "loss": 1.273193359375,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0778159499168396,
      "learning_rate": 1.0063778694545714e-05,
      "loss": 1.28759765625,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3125,
      "eval_runtime": 5.0513,
      "eval_samples_per_second": 0.792,
      "eval_steps_per_second": 0.198,
      "step": 63
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.53785675170159e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}