{
  "best_global_step": 3496,
  "best_metric": 1.2915655374526978,
  "best_model_checkpoint": "/content/drive/MyDrive/mn_cpt_v3_ckpts_round3/checkpoint-3496",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 3496,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028604118993135013,
      "grad_norm": 6.078797817230225,
      "learning_rate": 7.984339485707839e-06,
      "loss": 1.3830328369140625,
      "step": 100
    },
    {
      "epoch": 0.057208237986270026,
      "grad_norm": 11.469399452209473,
      "learning_rate": 7.936850403747543e-06,
      "loss": 1.3727151489257812,
      "step": 200
    },
    {
      "epoch": 0.08581235697940504,
      "grad_norm": 1.8696019649505615,
      "learning_rate": 7.857914384244805e-06,
      "loss": 1.3639500427246094,
      "step": 300
    },
    {
      "epoch": 0.11441647597254005,
      "grad_norm": 6.118563652038574,
      "learning_rate": 7.748168427807287e-06,
      "loss": 1.3683242797851562,
      "step": 400
    },
    {
      "epoch": 0.14302059496567507,
      "grad_norm": 1.989322304725647,
      "learning_rate": 7.6084981661324e-06,
      "loss": 1.348068084716797,
      "step": 500
    },
    {
      "epoch": 0.14302059496567507,
      "eval_loss": 1.3118553161621094,
      "eval_runtime": 37.5468,
      "eval_samples_per_second": 10.653,
      "eval_steps_per_second": 1.332,
      "step": 500
    },
    {
      "epoch": 0.17162471395881007,
      "grad_norm": 3.678053617477417,
      "learning_rate": 7.440030715106141e-06,
      "loss": 1.358717041015625,
      "step": 600
    },
    {
      "epoch": 0.20022883295194507,
      "grad_norm": 2.4253056049346924,
      "learning_rate": 7.244125579164522e-06,
      "loss": 1.3532925415039063,
      "step": 700
    },
    {
      "epoch": 0.2288329519450801,
      "grad_norm": 2.376685380935669,
      "learning_rate": 7.022363680317857e-06,
      "loss": 1.3489190673828124,
      "step": 800
    },
    {
      "epoch": 0.2574370709382151,
      "grad_norm": 28.55396842956543,
      "learning_rate": 6.776534600371911e-06,
      "loss": 1.3533811950683594,
      "step": 900
    },
    {
      "epoch": 0.28604118993135014,
      "grad_norm": 2.7511420249938965,
      "learning_rate": 6.508622139299027e-06,
      "loss": 1.3458760070800782,
      "step": 1000
    },
    {
      "epoch": 0.28604118993135014,
      "eval_loss": 1.3045889139175415,
      "eval_runtime": 26.4006,
      "eval_samples_per_second": 15.151,
      "eval_steps_per_second": 1.894,
      "step": 1000
    },
    {
      "epoch": 0.3146453089244851,
      "grad_norm": 2.5689327716827393,
      "learning_rate": 6.220788306300811e-06,
      "loss": 1.355426025390625,
      "step": 1100
    },
    {
      "epoch": 0.34324942791762014,
      "grad_norm": 2.8054022789001465,
      "learning_rate": 5.915355872751861e-06,
      "loss": 1.3566339111328125,
      "step": 1200
    },
    {
      "epoch": 0.3718535469107552,
      "grad_norm": 2.5591626167297363,
      "learning_rate": 5.594789627819347e-06,
      "loss": 1.3423316955566407,
      "step": 1300
    },
    {
      "epoch": 0.40045766590389015,
      "grad_norm": 2.8826591968536377,
      "learning_rate": 5.2616764880225465e-06,
      "loss": 1.3401609802246093,
      "step": 1400
    },
    {
      "epoch": 0.4290617848970252,
      "grad_norm": 21.04686164855957,
      "learning_rate": 4.9187046212448575e-06,
      "loss": 1.33688720703125,
      "step": 1500
    },
    {
      "epoch": 0.4290617848970252,
      "eval_loss": 1.2993944883346558,
      "eval_runtime": 26.4569,
      "eval_samples_per_second": 15.119,
      "eval_steps_per_second": 1.89,
      "step": 1500
    },
    {
      "epoch": 0.4576659038901602,
      "grad_norm": 2.9225025177001953,
      "learning_rate": 4.568641753664065e-06,
      "loss": 1.3416923522949218,
      "step": 1600
    },
    {
      "epoch": 0.4862700228832952,
      "grad_norm": 3.0348072052001953,
      "learning_rate": 4.214312834660358e-06,
      "loss": 1.3445010375976563,
      "step": 1700
    },
    {
      "epoch": 0.5148741418764302,
      "grad_norm": 12.458765983581543,
      "learning_rate": 3.858577239942556e-06,
      "loss": 1.3481927490234376,
      "step": 1800
    },
    {
      "epoch": 0.5434782608695652,
      "grad_norm": 2.9453368186950684,
      "learning_rate": 3.5043056968595864e-06,
      "loss": 1.3392031860351563,
      "step": 1900
    },
    {
      "epoch": 0.5720823798627003,
      "grad_norm": 3.372931480407715,
      "learning_rate": 3.154357118106089e-06,
      "loss": 1.342034912109375,
      "step": 2000
    },
    {
      "epoch": 0.5720823798627003,
      "eval_loss": 1.2956843376159668,
      "eval_runtime": 26.4388,
      "eval_samples_per_second": 15.129,
      "eval_steps_per_second": 1.891,
      "step": 2000
    },
    {
      "epoch": 0.6006864988558352,
      "grad_norm": 3.716198682785034,
      "learning_rate": 2.8115555307703415e-06,
      "loss": 1.3492497253417968,
      "step": 2100
    },
    {
      "epoch": 0.6292906178489702,
      "grad_norm": 10.484580993652344,
      "learning_rate": 2.478667286903224e-06,
      "loss": 1.3407521057128906,
      "step": 2200
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 3.459303140640259,
      "learning_rate": 2.1583787395152167e-06,
      "loss": 1.3312777709960937,
      "step": 2300
    },
    {
      "epoch": 0.6864988558352403,
      "grad_norm": 3.1813409328460693,
      "learning_rate": 1.8532745641523964e-06,
      "loss": 1.3426605224609376,
      "step": 2400
    },
    {
      "epoch": 0.7151029748283753,
      "grad_norm": 3.5617153644561768,
      "learning_rate": 1.5658169009927226e-06,
      "loss": 1.3322418212890625,
      "step": 2500
    },
    {
      "epoch": 0.7151029748283753,
      "eval_loss": 1.2930673360824585,
      "eval_runtime": 26.4629,
      "eval_samples_per_second": 15.116,
      "eval_steps_per_second": 1.889,
      "step": 2500
    },
    {
      "epoch": 0.7437070938215103,
      "grad_norm": 3.541377067565918,
      "learning_rate": 1.2983254857824741e-06,
      "loss": 1.341458740234375,
      "step": 2600
    },
    {
      "epoch": 0.7723112128146453,
      "grad_norm": 3.7203402519226074,
      "learning_rate": 1.0529589299528658e-06,
      "loss": 1.3305506896972656,
      "step": 2700
    },
    {
      "epoch": 0.8009153318077803,
      "grad_norm": 4.587987899780273,
      "learning_rate": 8.31697300983202e-07,
      "loss": 1.3313795471191405,
      "step": 2800
    },
    {
      "epoch": 0.8295194508009154,
      "grad_norm": 3.8108110427856445,
      "learning_rate": 6.363261435841683e-07,
      "loss": 1.3435818481445312,
      "step": 2900
    },
    {
      "epoch": 0.8581235697940504,
      "grad_norm": 3.4835927486419678,
      "learning_rate": 4.684220706476582e-07,
      "loss": 1.3480873107910156,
      "step": 3000
    },
    {
      "epoch": 0.8581235697940504,
      "eval_loss": 1.2919217348098755,
      "eval_runtime": 26.4704,
      "eval_samples_per_second": 15.111,
      "eval_steps_per_second": 1.889,
      "step": 3000
    },
    {
      "epoch": 0.8867276887871853,
      "grad_norm": 6.914333820343018,
      "learning_rate": 3.2934004024177475e-07,
      "loss": 1.3343791198730468,
      "step": 3100
    },
    {
      "epoch": 0.9153318077803204,
      "grad_norm": 3.2286205291748047,
      "learning_rate": 2.2020242132357386e-07,
      "loss": 1.3423574829101563,
      "step": 3200
    },
    {
      "epoch": 0.9439359267734554,
      "grad_norm": 3.048642873764038,
      "learning_rate": 1.418899364074088e-07,
      "loss": 1.337375946044922,
      "step": 3300
    },
    {
      "epoch": 0.9725400457665904,
      "grad_norm": 6.629016399383545,
      "learning_rate": 9.50345542800681e-08,
      "loss": 1.3348983764648437,
      "step": 3400
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2915655374526978,
      "eval_runtime": 26.4353,
      "eval_samples_per_second": 15.131,
      "eval_steps_per_second": 1.891,
      "step": 3496
    }
  ],
  "logging_steps": 100,
  "max_steps": 3496,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.6587806086441887e+18,
  "train_batch_size": 45,
  "trial_name": null,
  "trial_params": null
}