{
  "best_metric": 0.06447368860244751,
  "best_model_checkpoint": "runs/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": 2.198932409286499,
      "learning_rate": 1.9692307692307696e-05,
      "loss": 1.0245,
      "step": 10
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.8804973363876343,
      "learning_rate": 1.9384615384615386e-05,
      "loss": 0.9455,
      "step": 20
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 2.0275747776031494,
      "learning_rate": 1.907692307692308e-05,
      "loss": 0.8402,
      "step": 30
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.6169326305389404,
      "learning_rate": 1.876923076923077e-05,
      "loss": 0.6958,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 4.97913932800293,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.6621,
      "step": 50
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 2.330277681350708,
      "learning_rate": 1.8153846153846155e-05,
      "loss": 0.5817,
      "step": 60
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 1.8199760913848877,
      "learning_rate": 1.784615384615385e-05,
      "loss": 0.5207,
      "step": 70
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2205573320388794,
      "learning_rate": 1.753846153846154e-05,
      "loss": 0.3956,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 2.3881430625915527,
      "learning_rate": 1.7230769230769234e-05,
      "loss": 0.354,
      "step": 90
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.0776097774505615,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.3698,
      "step": 100
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 2.2470011711120605,
      "learning_rate": 1.6615384615384618e-05,
      "loss": 0.3316,
      "step": 110
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 2.575230836868286,
      "learning_rate": 1.630769230769231e-05,
      "loss": 0.247,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.0244927406311035,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2821,
      "step": 130
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9624060150375939,
      "eval_loss": 0.21702182292938232,
      "eval_runtime": 4.8414,
      "eval_samples_per_second": 27.471,
      "eval_steps_per_second": 3.511,
      "step": 130
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 1.5459403991699219,
      "learning_rate": 1.5692307692307693e-05,
      "loss": 0.1998,
      "step": 140
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 3.0010740756988525,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2238,
      "step": 150
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.4257588386535645,
      "learning_rate": 1.5076923076923078e-05,
      "loss": 0.2054,
      "step": 160
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.5266915559768677,
      "learning_rate": 1.4769230769230772e-05,
      "loss": 0.2185,
      "step": 170
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.6089905500411987,
      "learning_rate": 1.4461538461538462e-05,
      "loss": 0.2053,
      "step": 180
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 2.8735594749450684,
      "learning_rate": 1.4153846153846156e-05,
      "loss": 0.1624,
      "step": 190
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.4562249481678009,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.2551,
      "step": 200
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.5948198437690735,
      "learning_rate": 1.353846153846154e-05,
      "loss": 0.1809,
      "step": 210
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 3.139431953430176,
      "learning_rate": 1.3230769230769231e-05,
      "loss": 0.2144,
      "step": 220
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 1.9466521739959717,
      "learning_rate": 1.2923076923076925e-05,
      "loss": 0.1757,
      "step": 230
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 5.938401699066162,
      "learning_rate": 1.2615384615384616e-05,
      "loss": 0.2557,
      "step": 240
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.3760318160057068,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.1325,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.34790655970573425,
      "learning_rate": 1.2e-05,
      "loss": 0.1291,
      "step": 260
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.12987138330936432,
      "eval_runtime": 1.598,
      "eval_samples_per_second": 83.231,
      "eval_steps_per_second": 10.639,
      "step": 260
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.5149113535881042,
      "learning_rate": 1.1692307692307694e-05,
      "loss": 0.094,
      "step": 270
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.33900701999664307,
      "learning_rate": 1.1384615384615385e-05,
      "loss": 0.1408,
      "step": 280
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 9.22519588470459,
      "learning_rate": 1.1076923076923079e-05,
      "loss": 0.1303,
      "step": 290
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 14.370689392089844,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.1368,
      "step": 300
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 5.706496238708496,
      "learning_rate": 1.0461538461538463e-05,
      "loss": 0.176,
      "step": 310
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.3110077381134033,
      "learning_rate": 1.0153846153846154e-05,
      "loss": 0.1567,
      "step": 320
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 5.352679252624512,
      "learning_rate": 9.846153846153848e-06,
      "loss": 0.1918,
      "step": 330
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.9024627804756165,
      "learning_rate": 9.53846153846154e-06,
      "loss": 0.0693,
      "step": 340
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.35386863350868225,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.1379,
      "step": 350
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 11.4584379196167,
      "learning_rate": 8.923076923076925e-06,
      "loss": 0.1184,
      "step": 360
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.31197383999824524,
      "learning_rate": 8.615384615384617e-06,
      "loss": 0.1491,
      "step": 370
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 1.1729108095169067,
      "learning_rate": 8.307692307692309e-06,
      "loss": 0.1374,
      "step": 380
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.29289594292640686,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.1379,
      "step": 390
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.09719473123550415,
      "eval_runtime": 1.6898,
      "eval_samples_per_second": 78.709,
      "eval_steps_per_second": 10.061,
      "step": 390
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 2.651108741760254,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1398,
      "step": 400
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 7.282815933227539,
      "learning_rate": 7.384615384615386e-06,
      "loss": 0.1577,
      "step": 410
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 9.063953399658203,
      "learning_rate": 7.076923076923078e-06,
      "loss": 0.1402,
      "step": 420
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 0.23233899474143982,
      "learning_rate": 6.76923076923077e-06,
      "loss": 0.0767,
      "step": 430
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 6.015790939331055,
      "learning_rate": 6.461538461538463e-06,
      "loss": 0.1157,
      "step": 440
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 12.260323524475098,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.0839,
      "step": 450
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 4.703426837921143,
      "learning_rate": 5.846153846153847e-06,
      "loss": 0.0988,
      "step": 460
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 9.774993896484375,
      "learning_rate": 5.538461538461539e-06,
      "loss": 0.0759,
      "step": 470
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.22184737026691437,
      "learning_rate": 5.230769230769232e-06,
      "loss": 0.0985,
      "step": 480
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.21117015182971954,
      "learning_rate": 4.923076923076924e-06,
      "loss": 0.0741,
      "step": 490
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.9010984897613525,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.1356,
      "step": 500
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.20677432417869568,
      "learning_rate": 4.307692307692308e-06,
      "loss": 0.1337,
      "step": 510
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3007451593875885,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0803,
      "step": 520
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9849624060150376,
      "eval_loss": 0.06447368860244751,
      "eval_runtime": 1.7388,
      "eval_samples_per_second": 76.491,
      "eval_steps_per_second": 9.777,
      "step": 520
    },
    {
      "epoch": 4.076923076923077,
      "grad_norm": 6.4211835861206055,
      "learning_rate": 3.692307692307693e-06,
      "loss": 0.0977,
      "step": 530
    },
    {
      "epoch": 4.153846153846154,
      "grad_norm": 1.6094409227371216,
      "learning_rate": 3.384615384615385e-06,
      "loss": 0.1672,
      "step": 540
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 0.3714386522769928,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.1514,
      "step": 550
    },
    {
      "epoch": 4.3076923076923075,
      "grad_norm": 1.195460557937622,
      "learning_rate": 2.7692307692307697e-06,
      "loss": 0.0497,
      "step": 560
    },
    {
      "epoch": 4.384615384615385,
      "grad_norm": 0.2668437659740448,
      "learning_rate": 2.461538461538462e-06,
      "loss": 0.1348,
      "step": 570
    },
    {
      "epoch": 4.461538461538462,
      "grad_norm": 0.26586711406707764,
      "learning_rate": 2.153846153846154e-06,
      "loss": 0.0843,
      "step": 580
    },
    {
      "epoch": 4.538461538461538,
      "grad_norm": 8.662138938903809,
      "learning_rate": 1.8461538461538465e-06,
      "loss": 0.0777,
      "step": 590
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 1.8624422550201416,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.0838,
      "step": 600
    },
    {
      "epoch": 4.6923076923076925,
      "grad_norm": 5.394564628601074,
      "learning_rate": 1.230769230769231e-06,
      "loss": 0.0872,
      "step": 610
    },
    {
      "epoch": 4.769230769230769,
      "grad_norm": 0.24372971057891846,
      "learning_rate": 9.230769230769232e-07,
      "loss": 0.0838,
      "step": 620
    },
    {
      "epoch": 4.846153846153846,
      "grad_norm": 0.2118876874446869,
      "learning_rate": 6.153846153846155e-07,
      "loss": 0.0674,
      "step": 630
    },
    {
      "epoch": 4.923076923076923,
      "grad_norm": 0.2302178144454956,
      "learning_rate": 3.0769230769230774e-07,
      "loss": 0.0807,
      "step": 640
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5646482110023499,
      "learning_rate": 0.0,
      "loss": 0.1123,
      "step": 650
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.07908037304878235,
      "eval_runtime": 1.654,
      "eval_samples_per_second": 80.413,
      "eval_steps_per_second": 10.278,
      "step": 650
    },
    {
      "epoch": 5.0,
      "step": 650,
      "total_flos": 4.006371770595533e+17,
      "train_loss": 0.21960490552278666,
      "train_runtime": 192.2421,
      "train_samples_per_second": 26.893,
      "train_steps_per_second": 3.381
    }
  ],
  "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
}