{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.26501766784452296,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035335689045936395,
      "grad_norm": 3.620260000228882,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 4.8054,
      "step": 1
    },
    {
      "epoch": 0.0035335689045936395,
      "eval_loss": 4.703144550323486,
      "eval_runtime": 7.764,
      "eval_samples_per_second": 30.783,
      "eval_steps_per_second": 3.864,
      "step": 1
    },
    {
      "epoch": 0.007067137809187279,
      "grad_norm": 3.2298903465270996,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.9204,
      "step": 2
    },
    {
      "epoch": 0.01060070671378092,
      "grad_norm": 3.3276522159576416,
      "learning_rate": 6e-06,
      "loss": 4.9672,
      "step": 3
    },
    {
      "epoch": 0.014134275618374558,
      "grad_norm": 3.1870436668395996,
      "learning_rate": 8.000000000000001e-06,
      "loss": 4.4393,
      "step": 4
    },
    {
      "epoch": 0.0176678445229682,
      "grad_norm": 3.3669509887695312,
      "learning_rate": 1e-05,
      "loss": 4.8962,
      "step": 5
    },
    {
      "epoch": 0.02120141342756184,
      "grad_norm": 3.7465147972106934,
      "learning_rate": 1.2e-05,
      "loss": 4.7028,
      "step": 6
    },
    {
      "epoch": 0.024734982332155476,
      "grad_norm": 3.447338342666626,
      "learning_rate": 1.4e-05,
      "loss": 4.7122,
      "step": 7
    },
    {
      "epoch": 0.028268551236749116,
      "grad_norm": 3.4820032119750977,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 4.8886,
      "step": 8
    },
    {
      "epoch": 0.03180212014134275,
      "grad_norm": 3.2590105533599854,
      "learning_rate": 1.8e-05,
      "loss": 4.5295,
      "step": 9
    },
    {
      "epoch": 0.03180212014134275,
      "eval_loss": 4.659517765045166,
      "eval_runtime": 7.1618,
      "eval_samples_per_second": 33.372,
      "eval_steps_per_second": 4.189,
      "step": 9
    },
    {
      "epoch": 0.0353356890459364,
      "grad_norm": 4.073524475097656,
      "learning_rate": 2e-05,
      "loss": 5.081,
      "step": 10
    },
    {
      "epoch": 0.038869257950530034,
      "grad_norm": 3.5995664596557617,
      "learning_rate": 1.999390827019096e-05,
      "loss": 4.5881,
      "step": 11
    },
    {
      "epoch": 0.04240282685512368,
      "grad_norm": 3.6033053398132324,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 4.5807,
      "step": 12
    },
    {
      "epoch": 0.045936395759717315,
      "grad_norm": 3.8522286415100098,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 5.0651,
      "step": 13
    },
    {
      "epoch": 0.04946996466431095,
      "grad_norm": 3.7190427780151367,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 4.7079,
      "step": 14
    },
    {
      "epoch": 0.053003533568904596,
      "grad_norm": 3.25559663772583,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 4.6699,
      "step": 15
    },
    {
      "epoch": 0.05653710247349823,
      "grad_norm": 3.60125732421875,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 4.69,
      "step": 16
    },
    {
      "epoch": 0.06007067137809187,
      "grad_norm": 3.6664018630981445,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 4.2972,
      "step": 17
    },
    {
      "epoch": 0.0636042402826855,
      "grad_norm": 4.067839622497559,
      "learning_rate": 1.961261695938319e-05,
      "loss": 4.4407,
      "step": 18
    },
    {
      "epoch": 0.0636042402826855,
      "eval_loss": 4.355165004730225,
      "eval_runtime": 7.1612,
      "eval_samples_per_second": 33.374,
      "eval_steps_per_second": 4.189,
      "step": 18
    },
    {
      "epoch": 0.06713780918727916,
      "grad_norm": 3.291872024536133,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 4.2238,
      "step": 19
    },
    {
      "epoch": 0.0706713780918728,
      "grad_norm": 3.1632275581359863,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 4.1458,
      "step": 20
    },
    {
      "epoch": 0.07420494699646643,
      "grad_norm": 3.739023208618164,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 4.302,
      "step": 21
    },
    {
      "epoch": 0.07773851590106007,
      "grad_norm": 3.6874678134918213,
      "learning_rate": 1.913545457642601e-05,
      "loss": 4.3061,
      "step": 22
    },
    {
      "epoch": 0.0812720848056537,
      "grad_norm": 3.9015374183654785,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 4.5023,
      "step": 23
    },
    {
      "epoch": 0.08480565371024736,
      "grad_norm": 3.3470852375030518,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 4.0806,
      "step": 24
    },
    {
      "epoch": 0.08833922261484099,
      "grad_norm": 3.786510944366455,
      "learning_rate": 1.866025403784439e-05,
      "loss": 4.1044,
      "step": 25
    },
    {
      "epoch": 0.09187279151943463,
      "grad_norm": 3.945117712020874,
      "learning_rate": 1.848048096156426e-05,
      "loss": 4.1434,
      "step": 26
    },
    {
      "epoch": 0.09540636042402827,
      "grad_norm": 3.6443867683410645,
      "learning_rate": 1.8290375725550417e-05,
      "loss": 4.0989,
      "step": 27
    },
    {
      "epoch": 0.09540636042402827,
      "eval_loss": 3.9746689796447754,
      "eval_runtime": 7.1709,
      "eval_samples_per_second": 33.329,
      "eval_steps_per_second": 4.184,
      "step": 27
    },
    {
      "epoch": 0.0989399293286219,
      "grad_norm": 3.7102622985839844,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 4.301,
      "step": 28
    },
    {
      "epoch": 0.10247349823321555,
      "grad_norm": 3.6173665523529053,
      "learning_rate": 1.788010753606722e-05,
      "loss": 4.2593,
      "step": 29
    },
    {
      "epoch": 0.10600706713780919,
      "grad_norm": 4.246015548706055,
      "learning_rate": 1.766044443118978e-05,
      "loss": 4.1935,
      "step": 30
    },
    {
      "epoch": 0.10954063604240283,
      "grad_norm": 4.163142681121826,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 4.0349,
      "step": 31
    },
    {
      "epoch": 0.11307420494699646,
      "grad_norm": 4.6858696937561035,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 4.0095,
      "step": 32
    },
    {
      "epoch": 0.1166077738515901,
      "grad_norm": 3.9068796634674072,
      "learning_rate": 1.6946583704589973e-05,
      "loss": 3.6553,
      "step": 33
    },
    {
      "epoch": 0.12014134275618374,
      "grad_norm": 4.144792556762695,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 3.6503,
      "step": 34
    },
    {
      "epoch": 0.12367491166077739,
      "grad_norm": 3.6011180877685547,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 3.4449,
      "step": 35
    },
    {
      "epoch": 0.127208480565371,
      "grad_norm": 4.0844407081604,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 3.7941,
      "step": 36
    },
    {
      "epoch": 0.127208480565371,
      "eval_loss": 3.6412363052368164,
      "eval_runtime": 7.1728,
      "eval_samples_per_second": 33.32,
      "eval_steps_per_second": 4.182,
      "step": 36
    },
    {
      "epoch": 0.13074204946996468,
      "grad_norm": 3.8344345092773438,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 4.0356,
      "step": 37
    },
    {
      "epoch": 0.13427561837455831,
      "grad_norm": 4.485532760620117,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 3.733,
      "step": 38
    },
    {
      "epoch": 0.13780918727915195,
      "grad_norm": 4.423894882202148,
      "learning_rate": 1.529919264233205e-05,
      "loss": 3.6177,
      "step": 39
    },
    {
      "epoch": 0.1413427561837456,
      "grad_norm": 3.844165325164795,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 3.6761,
      "step": 40
    },
    {
      "epoch": 0.14487632508833923,
      "grad_norm": 3.5136537551879883,
      "learning_rate": 1.469471562785891e-05,
      "loss": 3.6134,
      "step": 41
    },
    {
      "epoch": 0.14840989399293286,
      "grad_norm": 3.5087645053863525,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 3.557,
      "step": 42
    },
    {
      "epoch": 0.1519434628975265,
      "grad_norm": 3.902492046356201,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 3.6009,
      "step": 43
    },
    {
      "epoch": 0.15547703180212014,
      "grad_norm": 3.4406399726867676,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 3.4341,
      "step": 44
    },
    {
      "epoch": 0.15901060070671377,
      "grad_norm": 3.278090715408325,
      "learning_rate": 1.342020143325669e-05,
      "loss": 3.1567,
      "step": 45
    },
    {
      "epoch": 0.15901060070671377,
      "eval_loss": 3.398796796798706,
      "eval_runtime": 7.1641,
      "eval_samples_per_second": 33.361,
      "eval_steps_per_second": 4.188,
      "step": 45
    },
    {
      "epoch": 0.1625441696113074,
      "grad_norm": 3.7867252826690674,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 3.3983,
      "step": 46
    },
    {
      "epoch": 0.16607773851590105,
      "grad_norm": 4.200196743011475,
      "learning_rate": 1.2756373558169992e-05,
      "loss": 3.6074,
      "step": 47
    },
    {
      "epoch": 0.1696113074204947,
      "grad_norm": 3.7975761890411377,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 3.6216,
      "step": 48
    },
    {
      "epoch": 0.17314487632508835,
      "grad_norm": 3.228562355041504,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 3.2195,
      "step": 49
    },
    {
      "epoch": 0.17667844522968199,
      "grad_norm": 3.666325092315674,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 3.2573,
      "step": 50
    },
    {
      "epoch": 0.18021201413427562,
      "grad_norm": 3.6461217403411865,
      "learning_rate": 1.1391731009600655e-05,
      "loss": 3.2947,
      "step": 51
    },
    {
      "epoch": 0.18374558303886926,
      "grad_norm": 3.643479347229004,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 3.2125,
      "step": 52
    },
    {
      "epoch": 0.1872791519434629,
      "grad_norm": 3.4164750576019287,
      "learning_rate": 1.0697564737441254e-05,
      "loss": 3.3438,
      "step": 53
    },
    {
      "epoch": 0.19081272084805653,
      "grad_norm": 3.781705856323242,
      "learning_rate": 1.0348994967025012e-05,
      "loss": 3.251,
      "step": 54
    },
    {
      "epoch": 0.19081272084805653,
      "eval_loss": 3.2505455017089844,
      "eval_runtime": 7.1694,
      "eval_samples_per_second": 33.336,
      "eval_steps_per_second": 4.184,
      "step": 54
    },
    {
      "epoch": 0.19434628975265017,
      "grad_norm": 3.5788426399230957,
      "learning_rate": 1e-05,
      "loss": 3.3719,
      "step": 55
    },
    {
      "epoch": 0.1978798586572438,
      "grad_norm": 3.601278305053711,
      "learning_rate": 9.651005032974994e-06,
      "loss": 3.2865,
      "step": 56
    },
    {
      "epoch": 0.20141342756183744,
      "grad_norm": 3.5564422607421875,
      "learning_rate": 9.302435262558748e-06,
      "loss": 3.2639,
      "step": 57
    },
    {
      "epoch": 0.2049469964664311,
      "grad_norm": 3.8267316818237305,
      "learning_rate": 8.954715367323468e-06,
      "loss": 3.5431,
      "step": 58
    },
    {
      "epoch": 0.20848056537102475,
      "grad_norm": 3.9242968559265137,
      "learning_rate": 8.60826899039935e-06,
      "loss": 3.1809,
      "step": 59
    },
    {
      "epoch": 0.21201413427561838,
      "grad_norm": 3.4202167987823486,
      "learning_rate": 8.263518223330698e-06,
      "loss": 3.4313,
      "step": 60
    },
    {
      "epoch": 0.21554770318021202,
      "grad_norm": 3.4609107971191406,
      "learning_rate": 7.92088309182241e-06,
      "loss": 3.0355,
      "step": 61
    },
    {
      "epoch": 0.21908127208480566,
      "grad_norm": 3.4130520820617676,
      "learning_rate": 7.580781044003324e-06,
      "loss": 3.4006,
      "step": 62
    },
    {
      "epoch": 0.2226148409893993,
      "grad_norm": 3.4137520790100098,
      "learning_rate": 7.243626441830009e-06,
      "loss": 3.4577,
      "step": 63
    },
    {
      "epoch": 0.2226148409893993,
      "eval_loss": 3.1747097969055176,
      "eval_runtime": 7.17,
      "eval_samples_per_second": 33.333,
      "eval_steps_per_second": 4.184,
      "step": 63
    },
    {
      "epoch": 0.22614840989399293,
      "grad_norm": 3.42524790763855,
      "learning_rate": 6.909830056250527e-06,
      "loss": 3.074,
      "step": 64
    },
    {
      "epoch": 0.22968197879858657,
      "grad_norm": 3.5621337890625,
      "learning_rate": 6.579798566743314e-06,
      "loss": 3.0764,
      "step": 65
    },
    {
      "epoch": 0.2332155477031802,
      "grad_norm": 3.954556465148926,
      "learning_rate": 6.25393406584088e-06,
      "loss": 3.2832,
      "step": 66
    },
    {
      "epoch": 0.23674911660777384,
      "grad_norm": 3.518817663192749,
      "learning_rate": 5.932633569242e-06,
      "loss": 3.0194,
      "step": 67
    },
    {
      "epoch": 0.24028268551236748,
      "grad_norm": 3.8170769214630127,
      "learning_rate": 5.616288532109225e-06,
      "loss": 3.2752,
      "step": 68
    },
    {
      "epoch": 0.24381625441696114,
      "grad_norm": 3.3504433631896973,
      "learning_rate": 5.305284372141095e-06,
      "loss": 3.2076,
      "step": 69
    },
    {
      "epoch": 0.24734982332155478,
      "grad_norm": 3.452834129333496,
      "learning_rate": 5.000000000000003e-06,
      "loss": 3.356,
      "step": 70
    },
    {
      "epoch": 0.2508833922261484,
      "grad_norm": 4.365915775299072,
      "learning_rate": 4.700807357667953e-06,
      "loss": 3.3366,
      "step": 71
    },
    {
      "epoch": 0.254416961130742,
      "grad_norm": 3.3894336223602295,
      "learning_rate": 4.408070965292534e-06,
      "loss": 3.413,
      "step": 72
    },
    {
      "epoch": 0.254416961130742,
      "eval_loss": 3.1335721015930176,
      "eval_runtime": 7.1737,
      "eval_samples_per_second": 33.316,
      "eval_steps_per_second": 4.182,
      "step": 72
    },
    {
      "epoch": 0.2579505300353357,
      "grad_norm": 3.383213996887207,
      "learning_rate": 4.12214747707527e-06,
      "loss": 3.1959,
      "step": 73
    },
    {
      "epoch": 0.26148409893992935,
      "grad_norm": 3.5894997119903564,
      "learning_rate": 3.8433852467434175e-06,
      "loss": 3.3013,
      "step": 74
    },
    {
      "epoch": 0.26501766784452296,
      "grad_norm": 3.3693082332611084,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 3.1231,
      "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": 7257919271731200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}