{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015009324542872259,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 9.8e-05,
      "loss": 1.7437,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.6e-05,
      "loss": 1.7193,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.4e-05,
      "loss": 1.7594,
      "step": 60
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.6967,
      "step": 80
    },
    {
      "epoch": 0.0,
      "learning_rate": 9e-05,
      "loss": 1.6901,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.6982,
      "step": 120
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.6e-05,
      "loss": 1.7172,
      "step": 140
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.4e-05,
      "loss": 1.7211,
      "step": 160
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.2e-05,
      "loss": 1.7745,
      "step": 180
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 1.7274,
      "step": 200
    },
    {
      "epoch": 0.0,
      "eval_accuracy": 0.621273737842038,
      "eval_loss": 1.8277987241744995,
      "eval_runtime": 1953.3722,
      "eval_samples_per_second": 83.488,
      "eval_steps_per_second": 1.305,
      "step": 200
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.7197,
      "step": 220
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.6e-05,
      "loss": 1.7018,
      "step": 240
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.4e-05,
      "loss": 1.7197,
      "step": 260
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.2e-05,
      "loss": 1.7273,
      "step": 280
    },
    {
      "epoch": 0.0,
      "learning_rate": 7e-05,
      "loss": 1.7183,
      "step": 300
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.6984,
      "step": 320
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.6e-05,
      "loss": 1.7386,
      "step": 340
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.7249,
      "step": 360
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.2e-05,
      "loss": 1.7773,
      "step": 380
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 1.6666,
      "step": 400
    },
    {
      "epoch": 0.01,
      "eval_accuracy": 0.6223302329977166,
      "eval_loss": 1.8232501745224,
      "eval_runtime": 1951.452,
      "eval_samples_per_second": 83.571,
      "eval_steps_per_second": 1.306,
      "step": 400
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.8e-05,
      "loss": 1.7198,
      "step": 420
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.7502,
      "step": 440
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.7609,
      "step": 460
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.6984,
      "step": 480
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.7254,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.8e-05,
      "loss": 1.7266,
      "step": 520
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.6992,
      "step": 540
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.6693,
      "step": 560
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2e-05,
      "loss": 1.7121,
      "step": 580
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.7053,
      "step": 600
    },
    {
      "epoch": 0.01,
      "eval_accuracy": 0.6236126691293421,
      "eval_loss": 1.8155388832092285,
      "eval_runtime": 1969.8681,
      "eval_samples_per_second": 82.789,
      "eval_steps_per_second": 1.294,
      "step": 600
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.8e-05,
      "loss": 1.711,
      "step": 620
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.6e-05,
      "loss": 1.6866,
      "step": 640
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.7273,
      "step": 660
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.64,
      "step": 680
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 1.67,
      "step": 700
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.6873,
      "step": 720
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.7368,
      "step": 740
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 1.7325,
      "step": 760
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.6948,
      "step": 780
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 1.7117,
      "step": 800
    },
    {
      "epoch": 0.01,
      "eval_accuracy": 0.6249809385925811,
      "eval_loss": 1.808415412902832,
      "eval_runtime": 1947.0907,
      "eval_samples_per_second": 83.758,
      "eval_steps_per_second": 1.309,
      "step": 800
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-05,
      "loss": 1.7079,
      "step": 820
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.6933,
      "step": 840
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.6583,
      "step": 860
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 1.6468,
      "step": 880
    },
    {
      "epoch": 0.01,
      "learning_rate": 1e-05,
      "loss": 1.6779,
      "step": 900
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.717,
      "step": 920
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-06,
      "loss": 1.6988,
      "step": 940
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.7096,
      "step": 960
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.7079,
      "step": 980
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 1.678,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "eval_accuracy": 0.6257492027087862,
      "eval_loss": 1.8040720224380493,
      "eval_runtime": 1943.062,
      "eval_samples_per_second": 83.931,
      "eval_steps_per_second": 1.312,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "step": 1000,
      "total_flos": 1.7866929733632e+17,
      "train_loss": 1.710025089263916,
      "train_runtime": 11151.3123,
      "train_samples_per_second": 5.739,
      "train_steps_per_second": 0.09
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 1,
  "total_flos": 1.7866929733632e+17,
  "trial_name": null,
  "trial_params": null
}