{
  "best_metric": 0.06292294710874557,
  "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": 2.1983349323272705,
      "learning_rate": 1.9692307692307696e-05,
      "loss": 1.0245,
      "step": 10
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.8458256721496582,
      "learning_rate": 1.9384615384615386e-05,
      "loss": 0.9453,
      "step": 20
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 2.11714506149292,
      "learning_rate": 1.907692307692308e-05,
      "loss": 0.8403,
      "step": 30
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.609548568725586,
      "learning_rate": 1.876923076923077e-05,
      "loss": 0.6945,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 4.101930141448975,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.6609,
      "step": 50
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 2.092031240463257,
      "learning_rate": 1.8153846153846155e-05,
      "loss": 0.5821,
      "step": 60
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 1.7685494422912598,
      "learning_rate": 1.784615384615385e-05,
      "loss": 0.5198,
      "step": 70
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.2733267545700073,
      "learning_rate": 1.753846153846154e-05,
      "loss": 0.3941,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 2.5028107166290283,
      "learning_rate": 1.7230769230769234e-05,
      "loss": 0.3534,
      "step": 90
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.1141440868377686,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.3682,
      "step": 100
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 1.8950222730636597,
      "learning_rate": 1.6615384615384618e-05,
      "loss": 0.3325,
      "step": 110
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 2.5763683319091797,
      "learning_rate": 1.630769230769231e-05,
      "loss": 0.2458,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 6.5957489013671875,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2828,
      "step": 130
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9624060150375939,
      "eval_loss": 0.21589645743370056,
      "eval_runtime": 1.5419,
      "eval_samples_per_second": 86.258,
      "eval_steps_per_second": 11.025,
      "step": 130
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 1.598761796951294,
      "learning_rate": 1.5692307692307693e-05,
      "loss": 0.1992,
      "step": 140
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 3.098740339279175,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.2215,
      "step": 150
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.4490207433700562,
      "learning_rate": 1.5076923076923078e-05,
      "loss": 0.2059,
      "step": 160
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.5195011496543884,
      "learning_rate": 1.4769230769230772e-05,
      "loss": 0.2213,
      "step": 170
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.60326087474823,
      "learning_rate": 1.4461538461538462e-05,
      "loss": 0.214,
      "step": 180
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 3.9015231132507324,
      "learning_rate": 1.4153846153846156e-05,
      "loss": 0.1661,
      "step": 190
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.4572608172893524,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.2508,
      "step": 200
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.5710081458091736,
      "learning_rate": 1.353846153846154e-05,
      "loss": 0.1814,
      "step": 210
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 1.9736721515655518,
      "learning_rate": 1.3230769230769231e-05,
      "loss": 0.2111,
      "step": 220
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 1.846712350845337,
      "learning_rate": 1.2923076923076925e-05,
      "loss": 0.1819,
      "step": 230
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 5.21742057800293,
      "learning_rate": 1.2615384615384616e-05,
      "loss": 0.2542,
      "step": 240
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.40760770440101624,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.1354,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.34861046075820923,
      "learning_rate": 1.2e-05,
      "loss": 0.1295,
      "step": 260
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.12973816692829132,
      "eval_runtime": 1.5053,
      "eval_samples_per_second": 88.352,
      "eval_steps_per_second": 11.293,
      "step": 260
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.5309385657310486,
      "learning_rate": 1.1692307692307694e-05,
      "loss": 0.0918,
      "step": 270
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.3377753794193268,
      "learning_rate": 1.1384615384615385e-05,
      "loss": 0.1414,
      "step": 280
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 6.888655662536621,
      "learning_rate": 1.1076923076923079e-05,
      "loss": 0.124,
      "step": 290
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 8.263748168945312,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.1357,
      "step": 300
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 6.341168403625488,
      "learning_rate": 1.0461538461538463e-05,
      "loss": 0.1744,
      "step": 310
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.3566319942474365,
      "learning_rate": 1.0153846153846154e-05,
      "loss": 0.1598,
      "step": 320
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 5.753101348876953,
      "learning_rate": 9.846153846153848e-06,
      "loss": 0.1895,
      "step": 330
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 1.0042563676834106,
      "learning_rate": 9.53846153846154e-06,
      "loss": 0.0703,
      "step": 340
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.33628159761428833,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.1344,
      "step": 350
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 10.987286567687988,
      "learning_rate": 8.923076923076925e-06,
      "loss": 0.1197,
      "step": 360
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.33592140674591064,
      "learning_rate": 8.615384615384617e-06,
      "loss": 0.1516,
      "step": 370
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 1.3044095039367676,
      "learning_rate": 8.307692307692309e-06,
      "loss": 0.1302,
      "step": 380
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2922639548778534,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.147,
      "step": 390
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.09676244854927063,
      "eval_runtime": 1.5806,
      "eval_samples_per_second": 84.147,
      "eval_steps_per_second": 10.756,
      "step": 390
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 2.564885377883911,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.1312,
      "step": 400
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 7.473449230194092,
      "learning_rate": 7.384615384615386e-06,
      "loss": 0.1566,
      "step": 410
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 9.141277313232422,
      "learning_rate": 7.076923076923078e-06,
      "loss": 0.1439,
      "step": 420
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 0.23374924063682556,
      "learning_rate": 6.76923076923077e-06,
      "loss": 0.0727,
      "step": 430
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 4.644994258880615,
      "learning_rate": 6.461538461538463e-06,
      "loss": 0.1133,
      "step": 440
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 11.91666316986084,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.0784,
      "step": 450
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 3.7880263328552246,
      "learning_rate": 5.846153846153847e-06,
      "loss": 0.0993,
      "step": 460
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 8.291254043579102,
      "learning_rate": 5.538461538461539e-06,
      "loss": 0.0784,
      "step": 470
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.2228500247001648,
      "learning_rate": 5.230769230769232e-06,
      "loss": 0.0896,
      "step": 480
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 0.211690753698349,
      "learning_rate": 4.923076923076924e-06,
      "loss": 0.0747,
      "step": 490
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.866194486618042,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.1353,
      "step": 500
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.20909492671489716,
      "learning_rate": 4.307692307692308e-06,
      "loss": 0.1283,
      "step": 510
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3001326620578766,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0814,
      "step": 520
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.06292294710874557,
      "eval_runtime": 1.5056,
      "eval_samples_per_second": 88.334,
      "eval_steps_per_second": 11.291,
      "step": 520
    },
    {
      "epoch": 4.076923076923077,
      "grad_norm": 6.251921653747559,
      "learning_rate": 3.692307692307693e-06,
      "loss": 0.0994,
      "step": 530
    },
    {
      "epoch": 4.153846153846154,
      "grad_norm": 1.505910038948059,
      "learning_rate": 3.384615384615385e-06,
      "loss": 0.1646,
      "step": 540
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 0.3793761432170868,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.1533,
      "step": 550
    },
    {
      "epoch": 4.3076923076923075,
      "grad_norm": 1.360785961151123,
      "learning_rate": 2.7692307692307697e-06,
      "loss": 0.0502,
      "step": 560
    },
    {
      "epoch": 4.384615384615385,
      "grad_norm": 0.3551625907421112,
      "learning_rate": 2.461538461538462e-06,
      "loss": 0.1334,
      "step": 570
    },
    {
      "epoch": 4.461538461538462,
      "grad_norm": 0.2675708830356598,
      "learning_rate": 2.153846153846154e-06,
      "loss": 0.0877,
      "step": 580
    },
    {
      "epoch": 4.538461538461538,
      "grad_norm": 8.761523246765137,
      "learning_rate": 1.8461538461538465e-06,
      "loss": 0.074,
      "step": 590
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 2.3534207344055176,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.0924,
      "step": 600
    },
    {
      "epoch": 4.6923076923076925,
      "grad_norm": 5.307082653045654,
      "learning_rate": 1.230769230769231e-06,
      "loss": 0.087,
      "step": 610
    },
    {
      "epoch": 4.769230769230769,
      "grad_norm": 0.25473231077194214,
      "learning_rate": 9.230769230769232e-07,
      "loss": 0.0816,
      "step": 620
    },
    {
      "epoch": 4.846153846153846,
      "grad_norm": 0.21327146887779236,
      "learning_rate": 6.153846153846155e-07,
      "loss": 0.0687,
      "step": 630
    },
    {
      "epoch": 4.923076923076923,
      "grad_norm": 0.22991123795509338,
      "learning_rate": 3.0769230769230774e-07,
      "loss": 0.0781,
      "step": 640
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6434995532035828,
      "learning_rate": 0.0,
      "loss": 0.1153,
      "step": 650
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.07998156547546387,
      "eval_runtime": 1.5355,
      "eval_samples_per_second": 86.614,
      "eval_steps_per_second": 11.071,
      "step": 650
    },
    {
      "epoch": 5.0,
      "step": 650,
      "total_flos": 4.006371770595533e+17,
      "train_loss": 0.21930334192055922,
      "train_runtime": 166.3355,
      "train_samples_per_second": 31.082,
      "train_steps_per_second": 3.908
    }
  ],
  "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
}