{
  "best_metric": 1.0323867797851562,
  "best_model_checkpoint": "./beans_outputs/checkpoint-650",
  "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": 2.1331980228424072,
      "learning_rate": 1.9692307692307696e-05,
      "loss": 1.1239,
      "step": 10
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 1.7910937070846558,
      "learning_rate": 1.9384615384615386e-05,
      "loss": 1.1221,
      "step": 20
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 2.01678729057312,
      "learning_rate": 1.907692307692308e-05,
      "loss": 1.1164,
      "step": 30
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.4709253311157227,
      "learning_rate": 1.876923076923077e-05,
      "loss": 1.1046,
      "step": 40
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 1.6879830360412598,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 1.1084,
      "step": 50
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 1.4891974925994873,
      "learning_rate": 1.8153846153846155e-05,
      "loss": 1.1047,
      "step": 60
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 2.6175765991210938,
      "learning_rate": 1.784615384615385e-05,
      "loss": 1.1033,
      "step": 70
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 2.685450792312622,
      "learning_rate": 1.753846153846154e-05,
      "loss": 1.0914,
      "step": 80
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 2.0266225337982178,
      "learning_rate": 1.7230769230769234e-05,
      "loss": 1.095,
      "step": 90
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 2.4788904190063477,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 1.0926,
      "step": 100
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 1.8994899988174438,
      "learning_rate": 1.6615384615384618e-05,
      "loss": 1.0953,
      "step": 110
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 2.286781072616577,
      "learning_rate": 1.630769230769231e-05,
      "loss": 1.1013,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.015382766723633,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0884,
      "step": 130
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.40601503759398494,
      "eval_loss": 1.090308427810669,
      "eval_runtime": 1.5658,
      "eval_samples_per_second": 84.941,
      "eval_steps_per_second": 10.857,
      "step": 130
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 2.888793468475342,
      "learning_rate": 1.5692307692307693e-05,
      "loss": 1.0808,
      "step": 140
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 2.544851303100586,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.0753,
      "step": 150
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.5049091577529907,
      "learning_rate": 1.5076923076923078e-05,
      "loss": 1.0799,
      "step": 160
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 2.3966455459594727,
      "learning_rate": 1.4769230769230772e-05,
      "loss": 1.0957,
      "step": 170
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 2.1688547134399414,
      "learning_rate": 1.4461538461538462e-05,
      "loss": 1.0837,
      "step": 180
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 2.218165159225464,
      "learning_rate": 1.4153846153846156e-05,
      "loss": 1.0834,
      "step": 190
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.7778892517089844,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 1.0815,
      "step": 200
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 1.6511861085891724,
      "learning_rate": 1.353846153846154e-05,
      "loss": 1.0721,
      "step": 210
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 3.5080718994140625,
      "learning_rate": 1.3230769230769231e-05,
      "loss": 1.075,
      "step": 220
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 1.9993922710418701,
      "learning_rate": 1.2923076923076925e-05,
      "loss": 1.077,
      "step": 230
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 2.002586841583252,
      "learning_rate": 1.2615384615384616e-05,
      "loss": 1.0924,
      "step": 240
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 1.9362667798995972,
      "learning_rate": 1.230769230769231e-05,
      "loss": 1.0756,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.8682315349578857,
      "learning_rate": 1.2e-05,
      "loss": 1.0721,
      "step": 260
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.518796992481203,
      "eval_loss": 1.068122386932373,
      "eval_runtime": 1.1118,
      "eval_samples_per_second": 119.625,
      "eval_steps_per_second": 15.29,
      "step": 260
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 1.8234657049179077,
      "learning_rate": 1.1692307692307694e-05,
      "loss": 1.0784,
      "step": 270
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 2.394803047180176,
      "learning_rate": 1.1384615384615385e-05,
      "loss": 1.0671,
      "step": 280
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 2.4006338119506836,
      "learning_rate": 1.1076923076923079e-05,
      "loss": 1.0674,
      "step": 290
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 2.40977144241333,
      "learning_rate": 1.076923076923077e-05,
      "loss": 1.0545,
      "step": 300
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 1.989514946937561,
      "learning_rate": 1.0461538461538463e-05,
      "loss": 1.0702,
      "step": 310
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 1.9289751052856445,
      "learning_rate": 1.0153846153846154e-05,
      "loss": 1.0594,
      "step": 320
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 1.4276608228683472,
      "learning_rate": 9.846153846153848e-06,
      "loss": 1.0461,
      "step": 330
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 2.1731224060058594,
      "learning_rate": 9.53846153846154e-06,
      "loss": 1.0621,
      "step": 340
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 1.9502283334732056,
      "learning_rate": 9.230769230769232e-06,
      "loss": 1.0639,
      "step": 350
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 1.8020390272140503,
      "learning_rate": 8.923076923076925e-06,
      "loss": 1.0589,
      "step": 360
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 1.9864907264709473,
      "learning_rate": 8.615384615384617e-06,
      "loss": 1.0536,
      "step": 370
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 1.8596194982528687,
      "learning_rate": 8.307692307692309e-06,
      "loss": 1.0449,
      "step": 380
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.991027355194092,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0623,
      "step": 390
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6390977443609023,
      "eval_loss": 1.0459624528884888,
      "eval_runtime": 1.1732,
      "eval_samples_per_second": 113.364,
      "eval_steps_per_second": 14.49,
      "step": 390
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 2.3061418533325195,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.0617,
      "step": 400
    },
    {
      "epoch": 3.1538461538461537,
      "grad_norm": 1.7080086469650269,
      "learning_rate": 7.384615384615386e-06,
      "loss": 1.0502,
      "step": 410
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 2.0486979484558105,
      "learning_rate": 7.076923076923078e-06,
      "loss": 1.062,
      "step": 420
    },
    {
      "epoch": 3.3076923076923075,
      "grad_norm": 2.1800215244293213,
      "learning_rate": 6.76923076923077e-06,
      "loss": 1.0468,
      "step": 430
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 2.1321449279785156,
      "learning_rate": 6.461538461538463e-06,
      "loss": 1.0492,
      "step": 440
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 1.7226018905639648,
      "learning_rate": 6.153846153846155e-06,
      "loss": 1.0571,
      "step": 450
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 2.405348539352417,
      "learning_rate": 5.846153846153847e-06,
      "loss": 1.0583,
      "step": 460
    },
    {
      "epoch": 3.6153846153846154,
      "grad_norm": 1.523526906967163,
      "learning_rate": 5.538461538461539e-06,
      "loss": 1.036,
      "step": 470
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 2.7491352558135986,
      "learning_rate": 5.230769230769232e-06,
      "loss": 1.0416,
      "step": 480
    },
    {
      "epoch": 3.769230769230769,
      "grad_norm": 1.5548614263534546,
      "learning_rate": 4.923076923076924e-06,
      "loss": 1.0353,
      "step": 490
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 1.448201060295105,
      "learning_rate": 4.615384615384616e-06,
      "loss": 1.0562,
      "step": 500
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 1.9137156009674072,
      "learning_rate": 4.307692307692308e-06,
      "loss": 1.0363,
      "step": 510
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.4221014976501465,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.052,
      "step": 520
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6165413533834586,
      "eval_loss": 1.040980339050293,
      "eval_runtime": 1.088,
      "eval_samples_per_second": 122.247,
      "eval_steps_per_second": 15.626,
      "step": 520
    },
    {
      "epoch": 4.076923076923077,
      "grad_norm": 2.5872342586517334,
      "learning_rate": 3.692307692307693e-06,
      "loss": 1.052,
      "step": 530
    },
    {
      "epoch": 4.153846153846154,
      "grad_norm": 1.7396414279937744,
      "learning_rate": 3.384615384615385e-06,
      "loss": 1.0499,
      "step": 540
    },
    {
      "epoch": 4.230769230769231,
      "grad_norm": 2.633549928665161,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 1.0563,
      "step": 550
    },
    {
      "epoch": 4.3076923076923075,
      "grad_norm": 2.2198593616485596,
      "learning_rate": 2.7692307692307697e-06,
      "loss": 1.0623,
      "step": 560
    },
    {
      "epoch": 4.384615384615385,
      "grad_norm": 1.9397387504577637,
      "learning_rate": 2.461538461538462e-06,
      "loss": 1.0341,
      "step": 570
    },
    {
      "epoch": 4.461538461538462,
      "grad_norm": 2.3226265907287598,
      "learning_rate": 2.153846153846154e-06,
      "loss": 1.0402,
      "step": 580
    },
    {
      "epoch": 4.538461538461538,
      "grad_norm": 2.3199572563171387,
      "learning_rate": 1.8461538461538465e-06,
      "loss": 1.0364,
      "step": 590
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 1.7650482654571533,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 1.0353,
      "step": 600
    },
    {
      "epoch": 4.6923076923076925,
      "grad_norm": 3.022646427154541,
      "learning_rate": 1.230769230769231e-06,
      "loss": 1.0518,
      "step": 610
    },
    {
      "epoch": 4.769230769230769,
      "grad_norm": 3.9652676582336426,
      "learning_rate": 9.230769230769232e-07,
      "loss": 1.0519,
      "step": 620
    },
    {
      "epoch": 4.846153846153846,
      "grad_norm": 1.8114593029022217,
      "learning_rate": 6.153846153846155e-07,
      "loss": 1.0386,
      "step": 630
    },
    {
      "epoch": 4.923076923076923,
      "grad_norm": 2.25443434715271,
      "learning_rate": 3.0769230769230774e-07,
      "loss": 1.038,
      "step": 640
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.6620893478393555,
      "learning_rate": 0.0,
      "loss": 1.0519,
      "step": 650
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6917293233082706,
      "eval_loss": 1.0323867797851562,
      "eval_runtime": 1.1019,
      "eval_samples_per_second": 120.702,
      "eval_steps_per_second": 15.428,
      "step": 650
    },
    {
      "epoch": 5.0,
      "step": 650,
      "total_flos": 5.219455168198656e+16,
      "train_loss": 1.068038198030912,
      "train_runtime": 89.4433,
      "train_samples_per_second": 57.802,
      "train_steps_per_second": 7.267
    }
  ],
  "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": 5.219455168198656e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}