{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5463,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018304960644334616,
      "grad_norm": 0.11226867139339447,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.4178,
      "step": 100
    },
    {
      "epoch": 0.03660992128866923,
      "grad_norm": 0.19307924807071686,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4311,
      "step": 200
    },
    {
      "epoch": 0.054914881933003847,
      "grad_norm": 0.1868831366300583,
      "learning_rate": 6e-06,
      "loss": 2.4251,
      "step": 300
    },
    {
      "epoch": 0.07321984257733846,
      "grad_norm": 0.2497679591178894,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.4004,
      "step": 400
    },
    {
      "epoch": 0.09152480322167307,
      "grad_norm": 0.3507976830005646,
      "learning_rate": 1e-05,
      "loss": 2.3282,
      "step": 500
    },
    {
      "epoch": 0.10982976386600769,
      "grad_norm": 0.40492674708366394,
      "learning_rate": 1.2e-05,
      "loss": 2.2985,
      "step": 600
    },
    {
      "epoch": 0.1281347245103423,
      "grad_norm": 0.449167400598526,
      "learning_rate": 1.4e-05,
      "loss": 2.2815,
      "step": 700
    },
    {
      "epoch": 0.14643968515467692,
      "grad_norm": 0.510024905204773,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.2252,
      "step": 800
    },
    {
      "epoch": 0.16474464579901152,
      "grad_norm": 0.5523568987846375,
      "learning_rate": 1.8e-05,
      "loss": 2.222,
      "step": 900
    },
    {
      "epoch": 0.18304960644334614,
      "grad_norm": 0.6460111141204834,
      "learning_rate": 2e-05,
      "loss": 2.2266,
      "step": 1000
    },
    {
      "epoch": 0.20135456708768076,
      "grad_norm": 0.6135373711585999,
      "learning_rate": 1.9975235096487343e-05,
      "loss": 2.1631,
      "step": 1100
    },
    {
      "epoch": 0.21965952773201539,
      "grad_norm": 0.750421941280365,
      "learning_rate": 1.990106304603857e-05,
      "loss": 2.1781,
      "step": 1200
    },
    {
      "epoch": 0.23796448837634998,
      "grad_norm": 0.6863061189651489,
      "learning_rate": 1.9777851221388214e-05,
      "loss": 2.1576,
      "step": 1300
    },
    {
      "epoch": 0.2562694490206846,
      "grad_norm": 0.592878520488739,
      "learning_rate": 1.9606209888326098e-05,
      "loss": 2.142,
      "step": 1400
    },
    {
      "epoch": 0.2745744096650192,
      "grad_norm": 0.9680142998695374,
      "learning_rate": 1.9386989183062637e-05,
      "loss": 2.1088,
      "step": 1500
    },
    {
      "epoch": 0.29287937030935385,
      "grad_norm": 0.8196300864219666,
      "learning_rate": 1.9121274901520593e-05,
      "loss": 2.0937,
      "step": 1600
    },
    {
      "epoch": 0.31118433095368847,
      "grad_norm": 0.935396671295166,
      "learning_rate": 1.881038312140883e-05,
      "loss": 2.0938,
      "step": 1700
    },
    {
      "epoch": 0.32948929159802304,
      "grad_norm": 0.7880417704582214,
      "learning_rate": 1.8455853683714823e-05,
      "loss": 2.0672,
      "step": 1800
    },
    {
      "epoch": 0.34779425224235766,
      "grad_norm": 0.8693708777427673,
      "learning_rate": 1.805944256590194e-05,
      "loss": 2.0529,
      "step": 1900
    },
    {
      "epoch": 0.3660992128866923,
      "grad_norm": 0.7159385681152344,
      "learning_rate": 1.7623113184586985e-05,
      "loss": 2.0298,
      "step": 2000
    },
    {
      "epoch": 0.3844041735310269,
      "grad_norm": 0.7743539214134216,
      "learning_rate": 1.7149026670775558e-05,
      "loss": 2.0681,
      "step": 2100
    },
    {
      "epoch": 0.4027091341753615,
      "grad_norm": 0.892536997795105,
      "learning_rate": 1.6639531165821896e-05,
      "loss": 2.0808,
      "step": 2200
    },
    {
      "epoch": 0.42101409481969615,
      "grad_norm": 1.1176153421401978,
      "learning_rate": 1.6097150191130056e-05,
      "loss": 2.0381,
      "step": 2300
    },
    {
      "epoch": 0.43931905546403077,
      "grad_norm": 1.0423996448516846,
      "learning_rate": 1.5524570149201115e-05,
      "loss": 2.0246,
      "step": 2400
    },
    {
      "epoch": 0.4576240161083654,
      "grad_norm": 0.8842440843582153,
      "learning_rate": 1.4924627017933402e-05,
      "loss": 2.0534,
      "step": 2500
    },
    {
      "epoch": 0.47592897675269996,
      "grad_norm": 0.8251581192016602,
      "learning_rate": 1.4300292304078696e-05,
      "loss": 2.0748,
      "step": 2600
    },
    {
      "epoch": 0.4942339373970346,
      "grad_norm": 0.9325842261314392,
      "learning_rate": 1.3654658325426641e-05,
      "loss": 2.0505,
      "step": 2700
    },
    {
      "epoch": 0.5125388980413692,
      "grad_norm": 0.882586658000946,
      "learning_rate": 1.2990922894614404e-05,
      "loss": 2.0338,
      "step": 2800
    },
    {
      "epoch": 0.5308438586857038,
      "grad_norm": 1.3278307914733887,
      "learning_rate": 1.2312373480422384e-05,
      "loss": 2.0244,
      "step": 2900
    },
    {
      "epoch": 0.5491488193300385,
      "grad_norm": 1.3495004177093506,
      "learning_rate": 1.1622370925004782e-05,
      "loss": 2.0226,
      "step": 3000
    },
    {
      "epoch": 0.5674537799743731,
      "grad_norm": 0.730983316898346,
      "learning_rate": 1.0924332797703284e-05,
      "loss": 1.9642,
      "step": 3100
    },
    {
      "epoch": 0.5857587406187077,
      "grad_norm": 1.0524176359176636,
      "learning_rate": 1.0221716467892045e-05,
      "loss": 2.0393,
      "step": 3200
    },
    {
      "epoch": 0.6040637012630423,
      "grad_norm": 0.8124818205833435,
      "learning_rate": 9.518001980693905e-06,
      "loss": 2.0066,
      "step": 3300
    },
    {
      "epoch": 0.6223686619073769,
      "grad_norm": 0.9999445676803589,
      "learning_rate": 8.816674820384044e-06,
      "loss": 2.0355,
      "step": 3400
    },
    {
      "epoch": 0.6406736225517116,
      "grad_norm": 1.3435726165771484,
      "learning_rate": 8.121208646853637e-06,
      "loss": 2.0393,
      "step": 3500
    },
    {
      "epoch": 0.6589785831960461,
      "grad_norm": 1.0357476472854614,
      "learning_rate": 7.435048090639456e-06,
      "loss": 2.0351,
      "step": 3600
    },
    {
      "epoch": 0.6772835438403807,
      "grad_norm": 1.3906038999557495,
      "learning_rate": 6.7615916917352545e-06,
      "loss": 2.0292,
      "step": 3700
    },
    {
      "epoch": 0.6955885044847153,
      "grad_norm": 1.0058213472366333,
      "learning_rate": 6.104175066688805e-06,
      "loss": 2.0046,
      "step": 3800
    },
    {
      "epoch": 0.7138934651290499,
      "grad_norm": 0.9746403694152832,
      "learning_rate": 5.466054387357491e-06,
      "loss": 2.0278,
      "step": 3900
    },
    {
      "epoch": 0.7321984257733846,
      "grad_norm": 0.7524260878562927,
      "learning_rate": 4.8503902531519224e-06,
      "loss": 2.026,
      "step": 4000
    },
    {
      "epoch": 0.7505033864177192,
      "grad_norm": 0.848231852054596,
      "learning_rate": 4.260232036648057e-06,
      "loss": 1.994,
      "step": 4100
    },
    {
      "epoch": 0.7688083470620538,
      "grad_norm": 0.9133473634719849,
      "learning_rate": 3.6985027801036876e-06,
      "loss": 2.0077,
      "step": 4200
    },
    {
      "epoch": 0.7871133077063884,
      "grad_norm": 1.1169400215148926,
      "learning_rate": 3.167984717686521e-06,
      "loss": 2.0371,
      "step": 4300
    },
    {
      "epoch": 0.805418268350723,
      "grad_norm": 1.1980133056640625,
      "learning_rate": 2.6713054951220497e-06,
      "loss": 2.0253,
      "step": 4400
    },
    {
      "epoch": 0.8237232289950577,
      "grad_norm": 0.8313106894493103,
      "learning_rate": 2.2109251550149922e-06,
      "loss": 1.9908,
      "step": 4500
    },
    {
      "epoch": 0.8420281896393923,
      "grad_norm": 0.9666856527328491,
      "learning_rate": 1.7891239523057202e-06,
      "loss": 1.9913,
      "step": 4600
    },
    {
      "epoch": 0.8603331502837269,
      "grad_norm": 0.9010581970214844,
      "learning_rate": 1.4079910602115544e-06,
      "loss": 1.9869,
      "step": 4700
    },
    {
      "epoch": 0.8786381109280615,
      "grad_norm": 1.0931150913238525,
      "learning_rate": 1.0694142225921444e-06,
      "loss": 1.9533,
      "step": 4800
    },
    {
      "epoch": 0.8969430715723962,
      "grad_norm": 0.984924852848053,
      "learning_rate": 7.750704039905343e-07,
      "loss": 2.0316,
      "step": 4900
    },
    {
      "epoch": 0.9152480322167308,
      "grad_norm": 0.9124763011932373,
      "learning_rate": 5.264174836601732e-07,
      "loss": 2.0208,
      "step": 5000
    },
    {
      "epoch": 0.9335529928610653,
      "grad_norm": 1.179923176765442,
      "learning_rate": 3.24687034717085e-07,
      "loss": 2.0175,
      "step": 5100
    },
    {
      "epoch": 0.9518579535053999,
      "grad_norm": 1.0648012161254883,
      "learning_rate": 1.7087822418199506e-07,
      "loss": 2.0134,
      "step": 5200
    },
    {
      "epoch": 0.9701629141497345,
      "grad_norm": 0.8695976734161377,
      "learning_rate": 6.575286412536686e-08,
      "loss": 2.0041,
      "step": 5300
    },
    {
      "epoch": 0.9884678747940692,
      "grad_norm": 1.045597791671753,
      "learning_rate": 9.831638426904821e-09,
      "loss": 2.0033,
      "step": 5400
    },
    {
      "epoch": 1.0,
      "step": 5463,
      "total_flos": 9.9498061824e+16,
      "train_loss": 2.0932261693746033,
      "train_runtime": 883.1108,
      "train_samples_per_second": 12.371,
      "train_steps_per_second": 6.186
    }
  ],
  "logging_steps": 100,
  "max_steps": 5463,
  "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": 9.9498061824e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}