{
  "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": 0.39029014110565186,
      "learning_rate": 0.0,
      "loss": 1.74072265625,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.3977895975112915,
      "learning_rate": 2.5e-05,
      "loss": 1.8193359375,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.2535572648048401,
      "learning_rate": 5e-05,
      "loss": 1.408203125,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.21865864098072052,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.54248046875,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.14044301211833954,
      "learning_rate": 0.0001,
      "loss": 1.357666015625,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.11468952149152756,
      "learning_rate": 9.99362213054543e-05,
      "loss": 1.414794921875,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.15838299691677094,
      "learning_rate": 9.974506600945618e-05,
      "loss": 1.346435546875,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.18158257007598877,
      "learning_rate": 9.942707596246052e-05,
      "loss": 1.345703125,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.183410406112671,
      "learning_rate": 9.8983152541804e-05,
      "loss": 0.7744140625,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.11678645759820938,
      "learning_rate": 9.841455409665323e-05,
      "loss": 1.285888671875,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.08664851635694504,
      "learning_rate": 9.772289238107715e-05,
      "loss": 1.1910400390625,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.07821615040302277,
      "learning_rate": 9.691012798535524e-05,
      "loss": 1.207763671875,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.07503138482570648,
      "learning_rate": 9.59785647784711e-05,
      "loss": 1.2236328125,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.0798412635922432,
      "learning_rate": 9.493084337754573e-05,
      "loss": 1.28759765625,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.08004077523946762,
      "learning_rate": 9.376993366272128e-05,
      "loss": 1.1826171875,
      "step": 15
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 1.216796875,
      "eval_runtime": 5.4909,
      "eval_samples_per_second": 0.364,
      "eval_steps_per_second": 0.182,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.06384038925170898,
      "learning_rate": 9.249912635871318e-05,
      "loss": 1.1982421875,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.06806826591491699,
      "learning_rate": 9.112202370689337e-05,
      "loss": 1.1966552734375,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.06299256533384323,
      "learning_rate": 8.964252925434579e-05,
      "loss": 1.2159423828125,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.04804723337292671,
      "learning_rate": 8.806483678883803e-05,
      "loss": 1.00927734375,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.060130614787340164,
      "learning_rate": 8.639341845107433e-05,
      "loss": 1.214599609375,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.086543969810009,
      "learning_rate": 8.463301205792675e-05,
      "loss": 1.171630859375,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.0662260353565216,
      "learning_rate": 8.278860767257865e-05,
      "loss": 1.19677734375,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.05612208694219589,
      "learning_rate": 8.086543345964832e-05,
      "loss": 1.294921875,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.04827860742807388,
      "learning_rate": 7.886894086538841e-05,
      "loss": 1.03564453125,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.0562213771045208,
      "learning_rate": 7.680478916496926e-05,
      "loss": 1.2347412109375,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.05600786581635475,
      "learning_rate": 7.46788294206485e-05,
      "loss": 1.1312255859375,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.05734400078654289,
      "learning_rate": 7.249708789629944e-05,
      "loss": 1.21484375,
      "step": 27
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": 1.169921875,
      "eval_runtime": 5.4973,
      "eval_samples_per_second": 0.364,
      "eval_steps_per_second": 0.182,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.04520232975482941,
      "learning_rate": 7.026574897531137e-05,
      "loss": 1.19384765625,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.0506543330848217,
      "learning_rate": 6.799113763028295e-05,
      "loss": 1.1943359375,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.018054485321045,
      "learning_rate": 6.567970149420018e-05,
      "loss": 0.64453125,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.06562633067369461,
      "learning_rate": 6.333799258392015e-05,
      "loss": 1.1578369140625,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.04868047311902046,
      "learning_rate": 6.097264872776749e-05,
      "loss": 1.0946044921875,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.055948544293642044,
      "learning_rate": 5.859037474988874e-05,
      "loss": 1.116943359375,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.050402332097291946,
      "learning_rate": 5.6197923464699875e-05,
      "loss": 1.1273193359375,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.061322227120399475,
      "learning_rate": 5.3802076535300135e-05,
      "loss": 1.176513671875,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.05519519001245499,
      "learning_rate": 5.140962525011126e-05,
      "loss": 1.0797119140625,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.049536723643541336,
      "learning_rate": 4.902735127223252e-05,
      "loss": 1.12481689453125,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.04784968122839928,
      "learning_rate": 4.6662007416079864e-05,
      "loss": 1.12640380859375,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.052412062883377075,
      "learning_rate": 4.432029850579983e-05,
      "loss": 1.136962890625,
      "step": 39
    },
    {
      "epoch": 1.8571428571428572,
      "eval_loss": 1.154296875,
      "eval_runtime": 5.4651,
      "eval_samples_per_second": 0.366,
      "eval_steps_per_second": 0.183,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.03997504711151123,
      "learning_rate": 4.2008862369717074e-05,
      "loss": 0.956787109375,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.05004314333200455,
      "learning_rate": 3.973425102468864e-05,
      "loss": 1.141845703125,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1028779074549675,
      "learning_rate": 3.750291210370057e-05,
      "loss": 1.067626953125,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.05941079929471016,
      "learning_rate": 3.5321170579351516e-05,
      "loss": 1.1151123046875,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.05426109582185745,
      "learning_rate": 3.319521083503075e-05,
      "loss": 1.222900390625,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.08989612013101578,
      "learning_rate": 3.113105913461159e-05,
      "loss": 0.981689453125,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.048075128346681595,
      "learning_rate": 2.9134566540351693e-05,
      "loss": 1.1778564453125,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.04994767904281616,
      "learning_rate": 2.721139232742137e-05,
      "loss": 1.0787353515625,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.05583450198173523,
      "learning_rate": 2.5366987942073267e-05,
      "loss": 1.1490478515625,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.04764580726623535,
      "learning_rate": 2.3606581548925695e-05,
      "loss": 1.14404296875,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.04863216355443001,
      "learning_rate": 2.1935163211161985e-05,
      "loss": 1.1456298828125,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.02937026508152485,
      "learning_rate": 2.0357470745654214e-05,
      "loss": 0.5966796875,
      "step": 51
    },
    {
      "epoch": 2.4285714285714284,
      "eval_loss": 1.146484375,
      "eval_runtime": 5.4773,
      "eval_samples_per_second": 0.365,
      "eval_steps_per_second": 0.183,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.06333017349243164,
      "learning_rate": 1.8877976293106646e-05,
      "loss": 1.1070556640625,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.04482894763350487,
      "learning_rate": 1.7500873641286825e-05,
      "loss": 1.0587158203125,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.040712468326091766,
      "learning_rate": 1.6230066337278724e-05,
      "loss": 1.081787109375,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.08906273543834686,
      "learning_rate": 1.5069156622454287e-05,
      "loss": 1.08984375,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.061274148523807526,
      "learning_rate": 1.4021435221528906e-05,
      "loss": 1.130615234375,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.054327286779880524,
      "learning_rate": 1.3089872014644771e-05,
      "loss": 1.0430908203125,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.04634387046098709,
      "learning_rate": 1.2277107618922843e-05,
      "loss": 1.09515380859375,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.0436868742108345,
      "learning_rate": 1.1585445903346783e-05,
      "loss": 1.10205078125,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.05037835240364075,
      "learning_rate": 1.1016847458196001e-05,
      "loss": 1.1044921875,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.03902503475546837,
      "learning_rate": 1.0572924037539496e-05,
      "loss": 0.937744140625,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.050203897058963776,
      "learning_rate": 1.0254933990543831e-05,
      "loss": 1.1142578125,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.07041402906179428,
      "learning_rate": 1.0063778694545714e-05,
      "loss": 1.0267333984375,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.142578125,
      "eval_runtime": 5.4813,
      "eval_samples_per_second": 0.365,
      "eval_steps_per_second": 0.182,
      "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": 1.3468496460722995e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}