{
  "best_metric": 0.06478545069694519,
  "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": 2.219909191131592,
      "learning_rate": 1.9692307692307696e-05,
      "loss": 1.0246,
      "step": 10
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.867136001586914,
      "learning_rate": 1.9384615384615386e-05,
      "loss": 0.9458,
      "step": 20
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 2.014641761779785,
      "learning_rate": 1.907692307692308e-05,
      "loss": 0.843,
      "step": 30
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.621521234512329,
      "learning_rate": 1.876923076923077e-05,
      "loss": 0.6979,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 4.221485137939453,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.6615,
      "step": 50
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 2.189591646194458,
      "learning_rate": 1.8153846153846155e-05,
      "loss": 0.5827,
      "step": 60
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 1.8182183504104614,
      "learning_rate": 1.784615384615385e-05,
      "loss": 0.5204,
      "step": 70
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2810572385787964,
      "learning_rate": 1.753846153846154e-05,
      "loss": 0.3912,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 2.440126895904541,
      "learning_rate": 1.7230769230769234e-05,
      "loss": 0.3528,
      "step": 90
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.1179373264312744,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.3716,
      "step": 100
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 1.5854547023773193,
      "learning_rate": 1.6615384615384618e-05,
      "loss": 0.3316,
      "step": 110
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 2.5023155212402344,
      "learning_rate": 1.630769230769231e-05,
      "loss": 0.2475,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.7221198081970215,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2847,
      "step": 130
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9624060150375939,
      "eval_loss": 0.22239795327186584,
      "eval_runtime": 0.7797,
      "eval_samples_per_second": 170.573,
      "eval_steps_per_second": 21.803,
      "step": 130
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 1.5938633680343628,
      "learning_rate": 1.5692307692307693e-05,
      "loss": 0.2008,
      "step": 140
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 3.0165553092956543,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2277,
      "step": 150
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.384554386138916,
      "learning_rate": 1.5076923076923078e-05,
      "loss": 0.1995,
      "step": 160
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.5159196257591248,
      "learning_rate": 1.4769230769230772e-05,
      "loss": 0.2222,
      "step": 170
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.6363013982772827,
      "learning_rate": 1.4461538461538462e-05,
      "loss": 0.2024,
      "step": 180
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 3.1022887229919434,
      "learning_rate": 1.4153846153846156e-05,
      "loss": 0.1607,
      "step": 190
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.47201454639434814,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.2507,
      "step": 200
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.7038330435752869,
      "learning_rate": 1.353846153846154e-05,
      "loss": 0.1852,
      "step": 210
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 3.549431324005127,
      "learning_rate": 1.3230769230769231e-05,
      "loss": 0.2212,
      "step": 220
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 1.6958942413330078,
      "learning_rate": 1.2923076923076925e-05,
      "loss": 0.1714,
      "step": 230
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 3.431950092315674,
      "learning_rate": 1.2615384615384616e-05,
      "loss": 0.2637,
      "step": 240
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.3859943449497223,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.1358,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.34817659854888916,
      "learning_rate": 1.2e-05,
      "loss": 0.1328,
      "step": 260
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.12943199276924133,
      "eval_runtime": 0.7353,
      "eval_samples_per_second": 180.87,
      "eval_steps_per_second": 23.119,
      "step": 260
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.41414371132850647,
      "learning_rate": 1.1692307692307694e-05,
      "loss": 0.0937,
      "step": 270
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.3361707925796509,
      "learning_rate": 1.1384615384615385e-05,
      "loss": 0.1422,
      "step": 280
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 7.347569942474365,
      "learning_rate": 1.1076923076923079e-05,
      "loss": 0.1324,
      "step": 290
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 8.774317741394043,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.144,
      "step": 300
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 4.386533737182617,
      "learning_rate": 1.0461538461538463e-05,
      "loss": 0.1713,
      "step": 310
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.32739436626434326,
      "learning_rate": 1.0153846153846154e-05,
      "loss": 0.1524,
      "step": 320
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 5.0895609855651855,
      "learning_rate": 9.846153846153848e-06,
      "loss": 0.1797,
      "step": 330
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 1.0622847080230713,
      "learning_rate": 9.53846153846154e-06,
      "loss": 0.0728,
      "step": 340
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.4119308292865753,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.1317,
      "step": 350
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 8.73006820678711,
      "learning_rate": 8.923076923076925e-06,
      "loss": 0.112,
      "step": 360
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.2961794435977936,
      "learning_rate": 8.615384615384617e-06,
      "loss": 0.1513,
      "step": 370
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 1.1893236637115479,
      "learning_rate": 8.307692307692309e-06,
      "loss": 0.1276,
      "step": 380
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2919400930404663,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1384,
      "step": 390
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.09896980971097946,
      "eval_runtime": 0.7991,
      "eval_samples_per_second": 166.447,
      "eval_steps_per_second": 21.275,
      "step": 390
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 2.167959451675415,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1367,
      "step": 400
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 8.037406921386719,
      "learning_rate": 7.384615384615386e-06,
      "loss": 0.1591,
      "step": 410
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 9.303949356079102,
      "learning_rate": 7.076923076923078e-06,
      "loss": 0.1398,
      "step": 420
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 0.23276376724243164,
      "learning_rate": 6.76923076923077e-06,
      "loss": 0.0785,
      "step": 430
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 5.628683090209961,
      "learning_rate": 6.461538461538463e-06,
      "loss": 0.1223,
      "step": 440
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 6.672430515289307,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.076,
      "step": 450
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 4.811165809631348,
      "learning_rate": 5.846153846153847e-06,
      "loss": 0.0961,
      "step": 460
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 8.391487121582031,
      "learning_rate": 5.538461538461539e-06,
      "loss": 0.0771,
      "step": 470
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.22789998352527618,
      "learning_rate": 5.230769230769232e-06,
      "loss": 0.0883,
      "step": 480
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.21091216802597046,
      "learning_rate": 4.923076923076924e-06,
      "loss": 0.0707,
      "step": 490
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.8983242511749268,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.1468,
      "step": 500
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.20578838884830475,
      "learning_rate": 4.307692307692308e-06,
      "loss": 0.1325,
      "step": 510
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.30200502276420593,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0844,
      "step": 520
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.06478545069694519,
      "eval_runtime": 0.7315,
      "eval_samples_per_second": 181.826,
      "eval_steps_per_second": 23.241,
      "step": 520
    },
    {
      "epoch": 4.076923076923077,
      "grad_norm": 6.120011806488037,
      "learning_rate": 3.692307692307693e-06,
      "loss": 0.0974,
      "step": 530
    },
    {
      "epoch": 4.153846153846154,
      "grad_norm": 2.1523544788360596,
      "learning_rate": 3.384615384615385e-06,
      "loss": 0.1584,
      "step": 540
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 0.3640580475330353,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.1557,
      "step": 550
    },
    {
      "epoch": 4.3076923076923075,
      "grad_norm": 1.332091212272644,
      "learning_rate": 2.7692307692307697e-06,
      "loss": 0.0508,
      "step": 560
    },
    {
      "epoch": 4.384615384615385,
      "grad_norm": 0.43990302085876465,
      "learning_rate": 2.461538461538462e-06,
      "loss": 0.1368,
      "step": 570
    },
    {
      "epoch": 4.461538461538462,
      "grad_norm": 0.2979348599910736,
      "learning_rate": 2.153846153846154e-06,
      "loss": 0.081,
      "step": 580
    },
    {
      "epoch": 4.538461538461538,
      "grad_norm": 9.099878311157227,
      "learning_rate": 1.8461538461538465e-06,
      "loss": 0.0729,
      "step": 590
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 2.3992621898651123,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.0983,
      "step": 600
    },
    {
      "epoch": 4.6923076923076925,
      "grad_norm": 5.635377883911133,
      "learning_rate": 1.230769230769231e-06,
      "loss": 0.0917,
      "step": 610
    },
    {
      "epoch": 4.769230769230769,
      "grad_norm": 0.24102216958999634,
      "learning_rate": 9.230769230769232e-07,
      "loss": 0.0741,
      "step": 620
    },
    {
      "epoch": 4.846153846153846,
      "grad_norm": 0.21987579762935638,
      "learning_rate": 6.153846153846155e-07,
      "loss": 0.0622,
      "step": 630
    },
    {
      "epoch": 4.923076923076923,
      "grad_norm": 0.23225535452365875,
      "learning_rate": 3.0769230769230774e-07,
      "loss": 0.0781,
      "step": 640
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.604479968547821,
      "learning_rate": 0.0,
      "loss": 0.1204,
      "step": 650
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.08407622575759888,
      "eval_runtime": 1.0496,
      "eval_samples_per_second": 126.711,
      "eval_steps_per_second": 16.196,
      "step": 650
    },
    {
      "epoch": 5.0,
      "step": 650,
      "total_flos": 4.006371770595533e+17,
      "train_loss": 0.2194705743973072,
      "train_runtime": 108.8731,
      "train_samples_per_second": 47.486,
      "train_steps_per_second": 5.97
    }
  ],
  "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
}