{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9976580796252925,
  "eval_steps": 500,
  "global_step": 480,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0624512099921936,
      "grad_norm": 5.695734079803832,
      "learning_rate": 5e-06,
      "loss": 0.7013,
      "step": 10
    },
    {
      "epoch": 0.1249024199843872,
      "grad_norm": 1.6672905613542388,
      "learning_rate": 5e-06,
      "loss": 0.6275,
      "step": 20
    },
    {
      "epoch": 0.1873536299765808,
      "grad_norm": 1.231437836117211,
      "learning_rate": 5e-06,
      "loss": 0.6011,
      "step": 30
    },
    {
      "epoch": 0.2498048399687744,
      "grad_norm": 0.6660382816468988,
      "learning_rate": 5e-06,
      "loss": 0.5905,
      "step": 40
    },
    {
      "epoch": 0.312256049960968,
      "grad_norm": 0.6878662625368892,
      "learning_rate": 5e-06,
      "loss": 0.5739,
      "step": 50
    },
    {
      "epoch": 0.3747072599531616,
      "grad_norm": 0.8735325294404173,
      "learning_rate": 5e-06,
      "loss": 0.5545,
      "step": 60
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 0.865826564748345,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 70
    },
    {
      "epoch": 0.4996096799375488,
      "grad_norm": 0.6254769035827942,
      "learning_rate": 5e-06,
      "loss": 0.5474,
      "step": 80
    },
    {
      "epoch": 0.5620608899297423,
      "grad_norm": 0.633780736055842,
      "learning_rate": 5e-06,
      "loss": 0.5477,
      "step": 90
    },
    {
      "epoch": 0.624512099921936,
      "grad_norm": 0.429646086801005,
      "learning_rate": 5e-06,
      "loss": 0.5536,
      "step": 100
    },
    {
      "epoch": 0.6869633099141296,
      "grad_norm": 0.47226853053932544,
      "learning_rate": 5e-06,
      "loss": 0.547,
      "step": 110
    },
    {
      "epoch": 0.7494145199063232,
      "grad_norm": 0.5108448433850594,
      "learning_rate": 5e-06,
      "loss": 0.5456,
      "step": 120
    },
    {
      "epoch": 0.8118657298985168,
      "grad_norm": 0.5120890633578824,
      "learning_rate": 5e-06,
      "loss": 0.5338,
      "step": 130
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 0.5054688976629029,
      "learning_rate": 5e-06,
      "loss": 0.5415,
      "step": 140
    },
    {
      "epoch": 0.936768149882904,
      "grad_norm": 0.4546611078615034,
      "learning_rate": 5e-06,
      "loss": 0.5266,
      "step": 150
    },
    {
      "epoch": 0.9992193598750976,
      "grad_norm": 0.5777441256544157,
      "learning_rate": 5e-06,
      "loss": 0.5327,
      "step": 160
    },
    {
      "epoch": 0.9992193598750976,
      "eval_loss": 0.5309467315673828,
      "eval_runtime": 112.9263,
      "eval_samples_per_second": 38.193,
      "eval_steps_per_second": 0.602,
      "step": 160
    },
    {
      "epoch": 1.0616705698672912,
      "grad_norm": 0.56357097034926,
      "learning_rate": 5e-06,
      "loss": 0.5284,
      "step": 170
    },
    {
      "epoch": 1.1241217798594847,
      "grad_norm": 0.6406606004904944,
      "learning_rate": 5e-06,
      "loss": 0.491,
      "step": 180
    },
    {
      "epoch": 1.1865729898516784,
      "grad_norm": 0.4470486896482656,
      "learning_rate": 5e-06,
      "loss": 0.4924,
      "step": 190
    },
    {
      "epoch": 1.249024199843872,
      "grad_norm": 0.43090473351959857,
      "learning_rate": 5e-06,
      "loss": 0.4824,
      "step": 200
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.43197317838800425,
      "learning_rate": 5e-06,
      "loss": 0.4911,
      "step": 210
    },
    {
      "epoch": 1.3739266198282591,
      "grad_norm": 0.49491142532222065,
      "learning_rate": 5e-06,
      "loss": 0.4888,
      "step": 220
    },
    {
      "epoch": 1.4363778298204528,
      "grad_norm": 0.4582690739604794,
      "learning_rate": 5e-06,
      "loss": 0.4922,
      "step": 230
    },
    {
      "epoch": 1.4988290398126463,
      "grad_norm": 0.5179775405720543,
      "learning_rate": 5e-06,
      "loss": 0.4902,
      "step": 240
    },
    {
      "epoch": 1.56128024980484,
      "grad_norm": 0.46044165550988314,
      "learning_rate": 5e-06,
      "loss": 0.4853,
      "step": 250
    },
    {
      "epoch": 1.6237314597970336,
      "grad_norm": 0.49784346733707135,
      "learning_rate": 5e-06,
      "loss": 0.4885,
      "step": 260
    },
    {
      "epoch": 1.6861826697892273,
      "grad_norm": 0.45069349680457893,
      "learning_rate": 5e-06,
      "loss": 0.486,
      "step": 270
    },
    {
      "epoch": 1.748633879781421,
      "grad_norm": 0.44312447239988956,
      "learning_rate": 5e-06,
      "loss": 0.4865,
      "step": 280
    },
    {
      "epoch": 1.8110850897736144,
      "grad_norm": 0.5540661328732004,
      "learning_rate": 5e-06,
      "loss": 0.4917,
      "step": 290
    },
    {
      "epoch": 1.8735362997658078,
      "grad_norm": 0.4234046253558461,
      "learning_rate": 5e-06,
      "loss": 0.4828,
      "step": 300
    },
    {
      "epoch": 1.9359875097580015,
      "grad_norm": 0.4388004925712562,
      "learning_rate": 5e-06,
      "loss": 0.4789,
      "step": 310
    },
    {
      "epoch": 1.9984387197501952,
      "grad_norm": 0.5610659198792445,
      "learning_rate": 5e-06,
      "loss": 0.4787,
      "step": 320
    },
    {
      "epoch": 1.9984387197501952,
      "eval_loss": 0.5198609828948975,
      "eval_runtime": 110.8922,
      "eval_samples_per_second": 38.894,
      "eval_steps_per_second": 0.613,
      "step": 320
    },
    {
      "epoch": 2.060889929742389,
      "grad_norm": 0.5484717697155285,
      "learning_rate": 5e-06,
      "loss": 0.4873,
      "step": 330
    },
    {
      "epoch": 2.1233411397345825,
      "grad_norm": 0.45228929433011156,
      "learning_rate": 5e-06,
      "loss": 0.4362,
      "step": 340
    },
    {
      "epoch": 2.185792349726776,
      "grad_norm": 0.5293854629631661,
      "learning_rate": 5e-06,
      "loss": 0.4425,
      "step": 350
    },
    {
      "epoch": 2.2482435597189694,
      "grad_norm": 0.6002239962428959,
      "learning_rate": 5e-06,
      "loss": 0.4355,
      "step": 360
    },
    {
      "epoch": 2.310694769711163,
      "grad_norm": 0.5258587782431947,
      "learning_rate": 5e-06,
      "loss": 0.4384,
      "step": 370
    },
    {
      "epoch": 2.3731459797033567,
      "grad_norm": 0.5243329962737817,
      "learning_rate": 5e-06,
      "loss": 0.4381,
      "step": 380
    },
    {
      "epoch": 2.4355971896955504,
      "grad_norm": 0.5890309295737689,
      "learning_rate": 5e-06,
      "loss": 0.4425,
      "step": 390
    },
    {
      "epoch": 2.498048399687744,
      "grad_norm": 0.5358514650116517,
      "learning_rate": 5e-06,
      "loss": 0.4439,
      "step": 400
    },
    {
      "epoch": 2.5604996096799377,
      "grad_norm": 0.4710746244266771,
      "learning_rate": 5e-06,
      "loss": 0.4434,
      "step": 410
    },
    {
      "epoch": 2.6229508196721314,
      "grad_norm": 0.4783994299645445,
      "learning_rate": 5e-06,
      "loss": 0.4376,
      "step": 420
    },
    {
      "epoch": 2.6854020296643246,
      "grad_norm": 0.5532060358770908,
      "learning_rate": 5e-06,
      "loss": 0.4418,
      "step": 430
    },
    {
      "epoch": 2.7478532396565183,
      "grad_norm": 0.5357167310213664,
      "learning_rate": 5e-06,
      "loss": 0.4489,
      "step": 440
    },
    {
      "epoch": 2.810304449648712,
      "grad_norm": 0.49033181773774204,
      "learning_rate": 5e-06,
      "loss": 0.4446,
      "step": 450
    },
    {
      "epoch": 2.8727556596409056,
      "grad_norm": 0.4295027030082963,
      "learning_rate": 5e-06,
      "loss": 0.4427,
      "step": 460
    },
    {
      "epoch": 2.9352068696330993,
      "grad_norm": 0.5261820799303164,
      "learning_rate": 5e-06,
      "loss": 0.4448,
      "step": 470
    },
    {
      "epoch": 2.9976580796252925,
      "grad_norm": 0.45577050194466817,
      "learning_rate": 5e-06,
      "loss": 0.443,
      "step": 480
    },
    {
      "epoch": 2.9976580796252925,
      "eval_loss": 0.5204988121986389,
      "eval_runtime": 106.3066,
      "eval_samples_per_second": 40.571,
      "eval_steps_per_second": 0.64,
      "step": 480
    },
    {
      "epoch": 2.9976580796252925,
      "step": 480,
      "total_flos": 803808498155520.0,
      "train_loss": 0.5004926055669785,
      "train_runtime": 16013.1849,
      "train_samples_per_second": 15.351,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 10,
  "max_steps": 480,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 803808498155520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}