{
  "best_metric": 0.0667242482304573,
  "best_model_checkpoint": "./beans_outputs/checkpoint-520",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 650,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 2.219895124435425,
      "learning_rate": 1.9692307692307696e-05,
      "loss": 1.0246,
      "step": 10
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.8536828756332397,
      "learning_rate": 1.9384615384615386e-05,
      "loss": 0.9458,
      "step": 20
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 2.008911609649658,
      "learning_rate": 1.907692307692308e-05,
      "loss": 0.843,
      "step": 30
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.629420518875122,
      "learning_rate": 1.876923076923077e-05,
      "loss": 0.6982,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 4.437777519226074,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.6645,
      "step": 50
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 2.107313632965088,
      "learning_rate": 1.8153846153846155e-05,
      "loss": 0.589,
      "step": 60
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 1.8212175369262695,
      "learning_rate": 1.784615384615385e-05,
      "loss": 0.525,
      "step": 70
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2224074602127075,
      "learning_rate": 1.753846153846154e-05,
      "loss": 0.3951,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 3.238478660583496,
      "learning_rate": 1.7230769230769234e-05,
      "loss": 0.3553,
      "step": 90
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.0028467178344727,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.369,
      "step": 100
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 2.592329740524292,
      "learning_rate": 1.6615384615384618e-05,
      "loss": 0.3332,
      "step": 110
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 2.486928701400757,
      "learning_rate": 1.630769230769231e-05,
      "loss": 0.2444,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 6.724624156951904,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2797,
      "step": 130
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9624060150375939,
      "eval_loss": 0.2228858470916748,
      "eval_runtime": 1.6507,
      "eval_samples_per_second": 80.574,
      "eval_steps_per_second": 10.299,
      "step": 130
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 1.6424057483673096,
      "learning_rate": 1.5692307692307693e-05,
      "loss": 0.2005,
      "step": 140
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 2.9966392517089844,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2288,
      "step": 150
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.444819688796997,
      "learning_rate": 1.5076923076923078e-05,
      "loss": 0.1986,
      "step": 160
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.5145019292831421,
      "learning_rate": 1.4769230769230772e-05,
      "loss": 0.2204,
      "step": 170
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.6211402416229248,
      "learning_rate": 1.4461538461538462e-05,
      "loss": 0.202,
      "step": 180
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 3.140580415725708,
      "learning_rate": 1.4153846153846156e-05,
      "loss": 0.1613,
      "step": 190
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.4404226839542389,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.2497,
      "step": 200
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.7200615406036377,
      "learning_rate": 1.353846153846154e-05,
      "loss": 0.1831,
      "step": 210
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 2.9941678047180176,
      "learning_rate": 1.3230769230769231e-05,
      "loss": 0.2164,
      "step": 220
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 1.9048223495483398,
      "learning_rate": 1.2923076923076925e-05,
      "loss": 0.1766,
      "step": 230
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 3.728172779083252,
      "learning_rate": 1.2615384615384616e-05,
      "loss": 0.2649,
      "step": 240
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.38998943567276,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.1317,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3474988341331482,
      "learning_rate": 1.2e-05,
      "loss": 0.1283,
      "step": 260
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.12395505607128143,
      "eval_runtime": 1.5924,
      "eval_samples_per_second": 83.524,
      "eval_steps_per_second": 10.676,
      "step": 260
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.41058436036109924,
      "learning_rate": 1.1692307692307694e-05,
      "loss": 0.0964,
      "step": 270
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.33480939269065857,
      "learning_rate": 1.1384615384615385e-05,
      "loss": 0.1355,
      "step": 280
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 7.664273262023926,
      "learning_rate": 1.1076923076923079e-05,
      "loss": 0.1332,
      "step": 290
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 9.499696731567383,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.1403,
      "step": 300
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 6.171899795532227,
      "learning_rate": 1.0461538461538463e-05,
      "loss": 0.1711,
      "step": 310
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.33433911204338074,
      "learning_rate": 1.0153846153846154e-05,
      "loss": 0.1498,
      "step": 320
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 5.629538536071777,
      "learning_rate": 9.846153846153848e-06,
      "loss": 0.183,
      "step": 330
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 1.226122498512268,
      "learning_rate": 9.53846153846154e-06,
      "loss": 0.0756,
      "step": 340
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.3657732903957367,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.1332,
      "step": 350
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 9.133737564086914,
      "learning_rate": 8.923076923076925e-06,
      "loss": 0.1113,
      "step": 360
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.3178321123123169,
      "learning_rate": 8.615384615384617e-06,
      "loss": 0.1476,
      "step": 370
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 1.165651559829712,
      "learning_rate": 8.307692307692309e-06,
      "loss": 0.1273,
      "step": 380
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.29111814498901367,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1325,
      "step": 390
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.09526458382606506,
      "eval_runtime": 1.633,
      "eval_samples_per_second": 81.444,
      "eval_steps_per_second": 10.41,
      "step": 390
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 2.0931763648986816,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1379,
      "step": 400
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 7.9508514404296875,
      "learning_rate": 7.384615384615386e-06,
      "loss": 0.1584,
      "step": 410
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 9.005721092224121,
      "learning_rate": 7.076923076923078e-06,
      "loss": 0.141,
      "step": 420
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 0.2301061898469925,
      "learning_rate": 6.76923076923077e-06,
      "loss": 0.0763,
      "step": 430
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 6.290613174438477,
      "learning_rate": 6.461538461538463e-06,
      "loss": 0.1248,
      "step": 440
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 5.136843681335449,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.0763,
      "step": 450
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 3.508342981338501,
      "learning_rate": 5.846153846153847e-06,
      "loss": 0.0988,
      "step": 460
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 8.985827445983887,
      "learning_rate": 5.538461538461539e-06,
      "loss": 0.0794,
      "step": 470
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.22434353828430176,
      "learning_rate": 5.230769230769232e-06,
      "loss": 0.0921,
      "step": 480
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.20995202660560608,
      "learning_rate": 4.923076923076924e-06,
      "loss": 0.0703,
      "step": 490
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.9496172666549683,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.1448,
      "step": 500
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.20678089559078217,
      "learning_rate": 4.307692307692308e-06,
      "loss": 0.1256,
      "step": 510
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.29890480637550354,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0809,
      "step": 520
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.0667242482304573,
      "eval_runtime": 1.6609,
      "eval_samples_per_second": 80.077,
      "eval_steps_per_second": 10.235,
      "step": 520
    },
    {
      "epoch": 4.076923076923077,
      "grad_norm": 8.196810722351074,
      "learning_rate": 3.692307692307693e-06,
      "loss": 0.0989,
      "step": 530
    },
    {
      "epoch": 4.153846153846154,
      "grad_norm": 1.6379270553588867,
      "learning_rate": 3.384615384615385e-06,
      "loss": 0.1574,
      "step": 540
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 0.3922630548477173,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.1542,
      "step": 550
    },
    {
      "epoch": 4.3076923076923075,
      "grad_norm": 1.2518798112869263,
      "learning_rate": 2.7692307692307697e-06,
      "loss": 0.0503,
      "step": 560
    },
    {
      "epoch": 4.384615384615385,
      "grad_norm": 0.36044520139694214,
      "learning_rate": 2.461538461538462e-06,
      "loss": 0.1316,
      "step": 570
    },
    {
      "epoch": 4.461538461538462,
      "grad_norm": 0.27382832765579224,
      "learning_rate": 2.153846153846154e-06,
      "loss": 0.0832,
      "step": 580
    },
    {
      "epoch": 4.538461538461538,
      "grad_norm": 8.751910209655762,
      "learning_rate": 1.8461538461538465e-06,
      "loss": 0.0673,
      "step": 590
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 3.928022861480713,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.0994,
      "step": 600
    },
    {
      "epoch": 4.6923076923076925,
      "grad_norm": 5.436663627624512,
      "learning_rate": 1.230769230769231e-06,
      "loss": 0.0907,
      "step": 610
    },
    {
      "epoch": 4.769230769230769,
      "grad_norm": 0.24947214126586914,
      "learning_rate": 9.230769230769232e-07,
      "loss": 0.0719,
      "step": 620
    },
    {
      "epoch": 4.846153846153846,
      "grad_norm": 0.2187993824481964,
      "learning_rate": 6.153846153846155e-07,
      "loss": 0.0604,
      "step": 630
    },
    {
      "epoch": 4.923076923076923,
      "grad_norm": 0.23066554963588715,
      "learning_rate": 3.0769230769230774e-07,
      "loss": 0.0797,
      "step": 640
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6189086437225342,
      "learning_rate": 0.0,
      "loss": 0.1164,
      "step": 650
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.08415611833333969,
      "eval_runtime": 1.6305,
      "eval_samples_per_second": 81.568,
      "eval_steps_per_second": 10.426,
      "step": 650
    },
    {
      "epoch": 5.0,
      "step": 650,
      "total_flos": 4.006371770595533e+17,
      "train_loss": 0.0,
      "train_runtime": 0.3159,
      "train_samples_per_second": 16363.748,
      "train_steps_per_second": 2057.338
    }
  ],
  "logging_steps": 10,
  "max_steps": 650,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.006371770595533e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}