{
  "best_metric": 0.6951560974121094,
  "best_model_checkpoint": "output/morgenshtern/checkpoint-294",
  "epoch": 3.0,
  "global_step": 294,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 4.8622670741210196e-05,
      "loss": 0.9101,
      "step": 5
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.902924774844624e-05,
      "loss": 0.8731,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 6.96668542977361e-05,
      "loss": 0.9581,
      "step": 15
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.027870792255626e-05,
      "loss": 0.8474,
      "step": 20
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.060864780933411e-05,
      "loss": 0.9838,
      "step": 25
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010040731829419309,
      "loss": 1.012,
      "step": 30
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00010943818808937948,
      "loss": 0.8702,
      "step": 35
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00011748325994051893,
      "loss": 0.9656,
      "step": 40
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012434833288861775,
      "loss": 0.9745,
      "step": 45
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001298676901104138,
      "loss": 0.8875,
      "step": 50
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00013390809917674526,
      "loss": 0.9281,
      "step": 55
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00013637202816621594,
      "loss": 0.932,
      "step": 60
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001372,
      "loss": 1.071,
      "step": 65
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000136372028166216,
      "loss": 0.8787,
      "step": 70
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00013390809917674537,
      "loss": 0.9074,
      "step": 75
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00012986769011041397,
      "loss": 1.0496,
      "step": 80
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012434833288861794,
      "loss": 0.9943,
      "step": 85
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00011748325994051916,
      "loss": 1.0026,
      "step": 90
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00010943818808937974,
      "loss": 1.0201,
      "step": 95
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00010040731829419337,
      "loss": 0.9215,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8902494311332703,
      "eval_runtime": 5.4222,
      "eval_samples_per_second": 22.684,
      "eval_steps_per_second": 2.951,
      "step": 101
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.060864780933398e-05,
      "loss": 0.9922,
      "step": 105
    },
    {
      "epoch": 1.09,
      "learning_rate": 8.027870792255707e-05,
      "loss": 0.8911,
      "step": 110
    },
    {
      "epoch": 1.14,
      "learning_rate": 6.966685429773643e-05,
      "loss": 0.9184,
      "step": 115
    },
    {
      "epoch": 1.19,
      "learning_rate": 5.902924774844707e-05,
      "loss": 0.8339,
      "step": 120
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.862267074121052e-05,
      "loss": 0.791,
      "step": 125
    },
    {
      "epoch": 1.29,
      "learning_rate": 3.869832889258939e-05,
      "loss": 0.8984,
      "step": 130
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.9495787086535028e-05,
      "loss": 0.7645,
      "step": 135
    },
    {
      "epoch": 1.39,
      "learning_rate": 2.1237186588777798e-05,
      "loss": 0.8448,
      "step": 140
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.4121882752050083e-05,
      "loss": 0.8783,
      "step": 145
    },
    {
      "epoch": 1.49,
      "learning_rate": 8.321632753190209e-06,
      "loss": 0.8214,
      "step": 150
    },
    {
      "epoch": 1.53,
      "learning_rate": 3.976449525958718e-06,
      "loss": 0.7646,
      "step": 155
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.1912219719526667e-06,
      "loss": 0.8915,
      "step": 160
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.318303476960258e-08,
      "loss": 0.7759,
      "step": 165
    },
    {
      "epoch": 1.68,
      "learning_rate": 5.302867558791814e-07,
      "loss": 0.9129,
      "step": 170
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.670533488647443e-06,
      "loss": 0.8839,
      "step": 175
    },
    {
      "epoch": 1.78,
      "learning_rate": 6.402259559252401e-06,
      "loss": 0.9542,
      "step": 180
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.1635384382334973e-05,
      "loss": 0.891,
      "step": 185
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.824358492710126e-05,
      "loss": 0.7246,
      "step": 190
    },
    {
      "epoch": 1.93,
      "learning_rate": 2.6067345044190458e-05,
      "loss": 0.7276,
      "step": 195
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.491780604522984e-05,
      "loss": 0.8327,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8691701889038086,
      "eval_runtime": 5.4146,
      "eval_samples_per_second": 22.717,
      "eval_steps_per_second": 2.955,
      "step": 202
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00013663679494827462,
      "loss": 0.8056,
      "step": 205
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00013436461471831498,
      "loss": 0.8153,
      "step": 210
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00013040646433810593,
      "loss": 0.8439,
      "step": 215
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00012486381666535154,
      "loss": 0.8468,
      "step": 220
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00011787876541670438,
      "loss": 0.9434,
      "step": 225
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00010963038239169752,
      "loss": 0.9117,
      "step": 230
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001003301267105212,
      "loss": 0.9685,
      "step": 235
    },
    {
      "epoch": 2.45,
      "learning_rate": 9.021642375642094e-05,
      "loss": 0.8183,
      "step": 240
    },
    {
      "epoch": 2.5,
      "learning_rate": 7.954855279929014e-05,
      "loss": 0.8455,
      "step": 245
    },
    {
      "epoch": 2.55,
      "learning_rate": 6.860000000000005e-05,
      "loss": 0.8961,
      "step": 250
    },
    {
      "epoch": 2.6,
      "learning_rate": 5.765144720071096e-05,
      "loss": 0.9542,
      "step": 255
    },
    {
      "epoch": 2.65,
      "learning_rate": 4.698357624357919e-05,
      "loss": 0.9393,
      "step": 260
    },
    {
      "epoch": 2.7,
      "learning_rate": 3.686987328947893e-05,
      "loss": 0.9105,
      "step": 265
    },
    {
      "epoch": 2.76,
      "learning_rate": 2.7569617608302584e-05,
      "loss": 0.9638,
      "step": 270
    },
    {
      "epoch": 2.81,
      "learning_rate": 1.932123458329638e-05,
      "loss": 0.8269,
      "step": 275
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.233618333464853e-05,
      "loss": 0.9693,
      "step": 280
    },
    {
      "epoch": 2.91,
      "learning_rate": 6.7935356618941304e-06,
      "loss": 0.8474,
      "step": 285
    },
    {
      "epoch": 2.96,
      "learning_rate": 2.8353852816850615e-06,
      "loss": 0.8138,
      "step": 290
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6951560974121094,
      "eval_runtime": 6.9159,
      "eval_samples_per_second": 20.677,
      "eval_steps_per_second": 2.603,
      "step": 294
    }
  ],
  "max_steps": 294,
  "num_train_epochs": 3,
  "total_flos": 305711677440000.0,
  "trial_name": null,
  "trial_params": null
}