{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 1080,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.0880818367004395,
      "learning_rate": 3.6e-05,
      "loss": 3.2849,
      "step": 36
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.010123239436619719,
      "eval_bleu": 0.10518697359828132,
      "eval_f1": 0.010153581748448041,
      "eval_loss": 2.6219797134399414,
      "eval_precision": 0.010202794685557478,
      "eval_recall": 0.010123239436619719,
      "eval_runtime": 6.2453,
      "eval_samples_per_second": 22.737,
      "eval_steps_per_second": 2.882,
      "step": 36
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.915263652801514,
      "learning_rate": 4.893203883495146e-05,
      "loss": 2.2637,
      "step": 72
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.01248899647887324,
      "eval_bleu": 0.13792868891001447,
      "eval_f1": 0.010680838430589857,
      "eval_loss": 2.017970561981201,
      "eval_precision": 0.009509030569956453,
      "eval_recall": 0.012488996478873238,
      "eval_runtime": 7.0653,
      "eval_samples_per_second": 20.098,
      "eval_steps_per_second": 2.548,
      "step": 72
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.544444561004639,
      "learning_rate": 4.718446601941748e-05,
      "loss": 1.789,
      "step": 108
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.012654049295774648,
      "eval_bleu": 0.17566093139607744,
      "eval_f1": 0.011466852239797607,
      "eval_loss": 1.7966645956039429,
      "eval_precision": 0.01049697288064746,
      "eval_recall": 0.012654049295774647,
      "eval_runtime": 6.0435,
      "eval_samples_per_second": 23.496,
      "eval_steps_per_second": 2.978,
      "step": 108
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.955804347991943,
      "learning_rate": 4.543689320388349e-05,
      "loss": 1.5522,
      "step": 144
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.012378961267605635,
      "eval_bleu": 0.20413318737157596,
      "eval_f1": 0.011132478900133054,
      "eval_loss": 1.6657302379608154,
      "eval_precision": 0.010120661403149588,
      "eval_recall": 0.012378961267605633,
      "eval_runtime": 6.1905,
      "eval_samples_per_second": 22.938,
      "eval_steps_per_second": 2.908,
      "step": 144
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.229798793792725,
      "learning_rate": 4.368932038834951e-05,
      "loss": 1.3885,
      "step": 180
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.012378961267605635,
      "eval_bleu": 0.2305940937780942,
      "eval_f1": 0.011073979352246164,
      "eval_loss": 1.5827170610427856,
      "eval_precision": 0.010022195626080541,
      "eval_recall": 0.012378961267605633,
      "eval_runtime": 6.9109,
      "eval_samples_per_second": 20.547,
      "eval_steps_per_second": 2.605,
      "step": 180
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.714682102203369,
      "learning_rate": 4.194174757281554e-05,
      "loss": 1.2561,
      "step": 216
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.25012821385731565,
      "eval_f1": 0.01143102719262594,
      "eval_loss": 1.5294432640075684,
      "eval_precision": 0.010707247710344536,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.5697,
      "eval_samples_per_second": 21.614,
      "eval_steps_per_second": 2.74,
      "step": 216
    },
    {
      "epoch": 7.0,
      "grad_norm": 6.063908100128174,
      "learning_rate": 4.019417475728156e-05,
      "loss": 1.1466,
      "step": 252
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.2719546447213355,
      "eval_f1": 0.01116903184495446,
      "eval_loss": 1.4926397800445557,
      "eval_precision": 0.010253161244814542,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.4161,
      "eval_samples_per_second": 22.132,
      "eval_steps_per_second": 2.805,
      "step": 252
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.155008316040039,
      "learning_rate": 3.844660194174757e-05,
      "loss": 1.0616,
      "step": 288
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.012378961267605635,
      "eval_bleu": 0.28742380325292655,
      "eval_f1": 0.01144092667248244,
      "eval_loss": 1.4650629758834839,
      "eval_precision": 0.010640060069611993,
      "eval_recall": 0.012378961267605633,
      "eval_runtime": 6.3235,
      "eval_samples_per_second": 22.456,
      "eval_steps_per_second": 2.847,
      "step": 288
    },
    {
      "epoch": 9.0,
      "grad_norm": 5.874176979064941,
      "learning_rate": 3.6699029126213596e-05,
      "loss": 0.9821,
      "step": 324
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.30478814512361185,
      "eval_f1": 0.011331946253740536,
      "eval_loss": 1.4492626190185547,
      "eval_precision": 0.010531151474565863,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.2565,
      "eval_samples_per_second": 22.696,
      "eval_steps_per_second": 2.877,
      "step": 324
    },
    {
      "epoch": 10.0,
      "grad_norm": 5.705406665802002,
      "learning_rate": 3.4951456310679615e-05,
      "loss": 0.9071,
      "step": 360
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.3250108739654091,
      "eval_f1": 0.011214281037053235,
      "eval_loss": 1.4369895458221436,
      "eval_precision": 0.010327542425543311,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.1165,
      "eval_samples_per_second": 23.216,
      "eval_steps_per_second": 2.943,
      "step": 360
    },
    {
      "epoch": 11.0,
      "grad_norm": 5.345541000366211,
      "learning_rate": 3.3203883495145634e-05,
      "loss": 0.8445,
      "step": 396
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.32825465058506376,
      "eval_f1": 0.011419929314754076,
      "eval_loss": 1.4337056875228882,
      "eval_precision": 0.010683679060359908,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.9862,
      "eval_samples_per_second": 20.326,
      "eval_steps_per_second": 2.577,
      "step": 396
    },
    {
      "epoch": 12.0,
      "grad_norm": 4.928064346313477,
      "learning_rate": 3.145631067961165e-05,
      "loss": 0.7869,
      "step": 432
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.34315751189373966,
      "eval_f1": 0.011425905613358798,
      "eval_loss": 1.431230902671814,
      "eval_precision": 0.010692912514740159,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.3375,
      "eval_samples_per_second": 22.406,
      "eval_steps_per_second": 2.84,
      "step": 432
    },
    {
      "epoch": 13.0,
      "grad_norm": 4.787758827209473,
      "learning_rate": 2.9708737864077673e-05,
      "loss": 0.7388,
      "step": 468
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.3506530097105922,
      "eval_f1": 0.011567695105672023,
      "eval_loss": 1.432782530784607,
      "eval_precision": 0.010942929955906473,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.6203,
      "eval_samples_per_second": 21.449,
      "eval_steps_per_second": 2.719,
      "step": 468
    },
    {
      "epoch": 14.0,
      "grad_norm": 4.721966743469238,
      "learning_rate": 2.7961165048543692e-05,
      "loss": 0.6948,
      "step": 504
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.36203576750790184,
      "eval_f1": 0.011535961695115268,
      "eval_loss": 1.4401381015777588,
      "eval_precision": 0.010887377543860504,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.8054,
      "eval_samples_per_second": 20.866,
      "eval_steps_per_second": 2.645,
      "step": 504
    },
    {
      "epoch": 15.0,
      "grad_norm": 3.970003128051758,
      "learning_rate": 2.6213592233009708e-05,
      "loss": 0.646,
      "step": 540
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.37067819665088503,
      "eval_f1": 0.011355838282605724,
      "eval_loss": 1.4626511335372925,
      "eval_precision": 0.010738384191565671,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.6898,
      "eval_samples_per_second": 21.226,
      "eval_steps_per_second": 2.691,
      "step": 540
    },
    {
      "epoch": 16.0,
      "grad_norm": 3.967465877532959,
      "learning_rate": 2.446601941747573e-05,
      "loss": 0.6137,
      "step": 576
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.3721186663899375,
      "eval_f1": 0.01150499351512691,
      "eval_loss": 1.460695505142212,
      "eval_precision": 0.01100817275358665,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.1473,
      "eval_samples_per_second": 23.1,
      "eval_steps_per_second": 2.928,
      "step": 576
    },
    {
      "epoch": 17.0,
      "grad_norm": 3.9431395530700684,
      "learning_rate": 2.2718446601941746e-05,
      "loss": 0.5833,
      "step": 612
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.3782352067209992,
      "eval_f1": 0.011355838282605724,
      "eval_loss": 1.4740684032440186,
      "eval_precision": 0.010738384191565671,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.2111,
      "eval_samples_per_second": 22.862,
      "eval_steps_per_second": 2.898,
      "step": 612
    },
    {
      "epoch": 18.0,
      "grad_norm": 4.299834251403809,
      "learning_rate": 2.097087378640777e-05,
      "loss": 0.5523,
      "step": 648
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.38158208167842117,
      "eval_f1": 0.011454837538514543,
      "eval_loss": 1.4804751873016357,
      "eval_precision": 0.010916734980993936,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.2563,
      "eval_samples_per_second": 22.697,
      "eval_steps_per_second": 2.877,
      "step": 648
    },
    {
      "epoch": 19.0,
      "grad_norm": 3.584228038787842,
      "learning_rate": 1.9223300970873785e-05,
      "loss": 0.5282,
      "step": 684
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 0.012268926056338027,
      "eval_bleu": 0.38941442914279584,
      "eval_f1": 0.011665531630013295,
      "eval_loss": 1.4897931814193726,
      "eval_precision": 0.011119728166708294,
      "eval_recall": 0.012268926056338027,
      "eval_runtime": 6.1705,
      "eval_samples_per_second": 23.013,
      "eval_steps_per_second": 2.917,
      "step": 684
    },
    {
      "epoch": 20.0,
      "grad_norm": 3.575045108795166,
      "learning_rate": 1.7475728155339808e-05,
      "loss": 0.5047,
      "step": 720
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.01210387323943662,
      "eval_bleu": 0.3904044704756756,
      "eval_f1": 0.011583122303403293,
      "eval_loss": 1.4997267723083496,
      "eval_precision": 0.011105397197031464,
      "eval_recall": 0.01210387323943662,
      "eval_runtime": 6.3359,
      "eval_samples_per_second": 22.412,
      "eval_steps_per_second": 2.841,
      "step": 720
    },
    {
      "epoch": 21.0,
      "grad_norm": 3.5939736366271973,
      "learning_rate": 1.5728155339805823e-05,
      "loss": 0.4854,
      "step": 756
    },
    {
      "epoch": 21.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.38824458290957736,
      "eval_f1": 0.011442367439933718,
      "eval_loss": 1.5054779052734375,
      "eval_precision": 0.010894114653359857,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.2963,
      "eval_samples_per_second": 22.553,
      "eval_steps_per_second": 2.859,
      "step": 756
    },
    {
      "epoch": 22.0,
      "grad_norm": 3.807431697845459,
      "learning_rate": 1.3980582524271846e-05,
      "loss": 0.4697,
      "step": 792
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.3905756115063895,
      "eval_f1": 0.011442367439933718,
      "eval_loss": 1.5122706890106201,
      "eval_precision": 0.010894114653359857,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 7.012,
      "eval_samples_per_second": 20.251,
      "eval_steps_per_second": 2.567,
      "step": 792
    },
    {
      "epoch": 23.0,
      "grad_norm": 3.8207340240478516,
      "learning_rate": 1.2233009708737865e-05,
      "loss": 0.4547,
      "step": 828
    },
    {
      "epoch": 23.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.39316674027140547,
      "eval_f1": 0.011517601862123769,
      "eval_loss": 1.5183604955673218,
      "eval_precision": 0.011031274351852924,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.8261,
      "eval_samples_per_second": 20.803,
      "eval_steps_per_second": 2.637,
      "step": 828
    },
    {
      "epoch": 24.0,
      "grad_norm": 3.831852912902832,
      "learning_rate": 1.0485436893203885e-05,
      "loss": 0.4413,
      "step": 864
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.3956605229111985,
      "eval_f1": 0.011392759914288347,
      "eval_loss": 1.5295231342315674,
      "eval_precision": 0.010804571945629947,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.289,
      "eval_samples_per_second": 22.579,
      "eval_steps_per_second": 2.862,
      "step": 864
    },
    {
      "epoch": 25.0,
      "grad_norm": 3.056539297103882,
      "learning_rate": 8.737864077669904e-06,
      "loss": 0.4325,
      "step": 900
    },
    {
      "epoch": 25.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.39496386454550636,
      "eval_f1": 0.0114798602280593,
      "eval_loss": 1.535691738128662,
      "eval_precision": 0.010962261366716413,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.1059,
      "eval_samples_per_second": 23.256,
      "eval_steps_per_second": 2.948,
      "step": 900
    },
    {
      "epoch": 26.0,
      "grad_norm": 3.1146154403686523,
      "learning_rate": 6.990291262135923e-06,
      "loss": 0.4188,
      "step": 936
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.3960440421138887,
      "eval_f1": 0.011517601862123769,
      "eval_loss": 1.5396318435668945,
      "eval_precision": 0.011031274351852924,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 7.2756,
      "eval_samples_per_second": 19.517,
      "eval_steps_per_second": 2.474,
      "step": 936
    },
    {
      "epoch": 27.0,
      "grad_norm": 3.4233100414276123,
      "learning_rate": 5.242718446601942e-06,
      "loss": 0.4131,
      "step": 972
    },
    {
      "epoch": 27.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.4001388307186371,
      "eval_f1": 0.011492413001125629,
      "eval_loss": 1.5463387966156006,
      "eval_precision": 0.010985168630418547,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 7.2564,
      "eval_samples_per_second": 19.569,
      "eval_steps_per_second": 2.481,
      "step": 972
    },
    {
      "epoch": 28.0,
      "grad_norm": 2.70424485206604,
      "learning_rate": 3.4951456310679615e-06,
      "loss": 0.4089,
      "step": 1008
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.39854032138633055,
      "eval_f1": 0.011492413001125629,
      "eval_loss": 1.544076681137085,
      "eval_precision": 0.010985168630418547,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 7.0435,
      "eval_samples_per_second": 20.16,
      "eval_steps_per_second": 2.556,
      "step": 1008
    },
    {
      "epoch": 29.0,
      "grad_norm": 3.052654266357422,
      "learning_rate": 1.7475728155339808e-06,
      "loss": 0.4026,
      "step": 1044
    },
    {
      "epoch": 29.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.3987203294842987,
      "eval_f1": 0.01150499351512691,
      "eval_loss": 1.5447367429733276,
      "eval_precision": 0.01100817275358665,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.3248,
      "eval_samples_per_second": 22.451,
      "eval_steps_per_second": 2.846,
      "step": 1044
    },
    {
      "epoch": 30.0,
      "grad_norm": 3.11586856842041,
      "learning_rate": 0.0,
      "loss": 0.3999,
      "step": 1080
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.012048855633802816,
      "eval_bleu": 0.398637528263251,
      "eval_f1": 0.011517601862123769,
      "eval_loss": 1.5456310510635376,
      "eval_precision": 0.011031274351852924,
      "eval_recall": 0.012048855633802815,
      "eval_runtime": 6.2921,
      "eval_samples_per_second": 22.568,
      "eval_steps_per_second": 2.861,
      "step": 1080
    }
  ],
  "logging_steps": 500,
  "max_steps": 1080,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1113104056320000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}