{
  "best_metric": 0.45652173913043476,
  "best_model_checkpoint": "SW2-DMAE\\checkpoint-49",
  "epoch": 34.285714285714285,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 7.9393720626831055,
      "eval_runtime": 0.2251,
      "eval_samples_per_second": 204.399,
      "eval_steps_per_second": 13.33,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 7.897927761077881,
      "eval_runtime": 0.2391,
      "eval_samples_per_second": 192.425,
      "eval_steps_per_second": 12.549,
      "step": 7
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.166666666666667e-05,
      "loss": 7.935,
      "step": 10
    },
    {
      "epoch": 2.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 7.767155647277832,
      "eval_runtime": 0.2321,
      "eval_samples_per_second": 198.231,
      "eval_steps_per_second": 12.928,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 7.219719886779785,
      "eval_runtime": 0.2351,
      "eval_samples_per_second": 195.7,
      "eval_steps_per_second": 12.763,
      "step": 14
    },
    {
      "epoch": 4.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 6.566103935241699,
      "eval_runtime": 0.2292,
      "eval_samples_per_second": 200.702,
      "eval_steps_per_second": 13.089,
      "step": 17
    },
    {
      "epoch": 5.71,
      "learning_rate": 4.62962962962963e-05,
      "loss": 7.0143,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 5.730363368988037,
      "eval_runtime": 0.2911,
      "eval_samples_per_second": 158.04,
      "eval_steps_per_second": 10.307,
      "step": 21
    },
    {
      "epoch": 6.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 5.118360996246338,
      "eval_runtime": 0.2291,
      "eval_samples_per_second": 200.828,
      "eval_steps_per_second": 13.097,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 4.352573394775391,
      "eval_runtime": 0.2536,
      "eval_samples_per_second": 181.411,
      "eval_steps_per_second": 11.831,
      "step": 28
    },
    {
      "epoch": 8.57,
      "learning_rate": 4.166666666666667e-05,
      "loss": 4.9972,
      "step": 30
    },
    {
      "epoch": 8.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 3.8116581439971924,
      "eval_runtime": 0.2421,
      "eval_samples_per_second": 190.04,
      "eval_steps_per_second": 12.394,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 3.151806354522705,
      "eval_runtime": 0.2396,
      "eval_samples_per_second": 192.018,
      "eval_steps_per_second": 12.523,
      "step": 35
    },
    {
      "epoch": 10.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 2.7124626636505127,
      "eval_runtime": 0.2381,
      "eval_samples_per_second": 193.229,
      "eval_steps_per_second": 12.602,
      "step": 38
    },
    {
      "epoch": 11.43,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 3.3803,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 2.2254273891448975,
      "eval_runtime": 0.2416,
      "eval_samples_per_second": 190.423,
      "eval_steps_per_second": 12.419,
      "step": 42
    },
    {
      "epoch": 12.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 1.9449864625930786,
      "eval_runtime": 0.2426,
      "eval_samples_per_second": 189.639,
      "eval_steps_per_second": 12.368,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.6738574504852295,
      "eval_runtime": 0.2396,
      "eval_samples_per_second": 192.014,
      "eval_steps_per_second": 12.523,
      "step": 49
    },
    {
      "epoch": 14.29,
      "learning_rate": 3.240740740740741e-05,
      "loss": 2.0759,
      "step": 50
    },
    {
      "epoch": 14.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.5299274921417236,
      "eval_runtime": 0.2221,
      "eval_samples_per_second": 207.16,
      "eval_steps_per_second": 13.51,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.3876434564590454,
      "eval_runtime": 0.2486,
      "eval_samples_per_second": 185.061,
      "eval_steps_per_second": 12.069,
      "step": 56
    },
    {
      "epoch": 16.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.305933952331543,
      "eval_runtime": 0.2481,
      "eval_samples_per_second": 185.442,
      "eval_steps_per_second": 12.094,
      "step": 59
    },
    {
      "epoch": 17.14,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.4466,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2341125011444092,
      "eval_runtime": 0.2951,
      "eval_samples_per_second": 155.897,
      "eval_steps_per_second": 10.167,
      "step": 63
    },
    {
      "epoch": 18.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2120041847229004,
      "eval_runtime": 0.2371,
      "eval_samples_per_second": 194.049,
      "eval_steps_per_second": 12.655,
      "step": 66
    },
    {
      "epoch": 20.0,
      "learning_rate": 2.314814814814815e-05,
      "loss": 1.2349,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2095657587051392,
      "eval_runtime": 0.2456,
      "eval_samples_per_second": 187.325,
      "eval_steps_per_second": 12.217,
      "step": 70
    },
    {
      "epoch": 20.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2118462324142456,
      "eval_runtime": 0.2391,
      "eval_samples_per_second": 192.425,
      "eval_steps_per_second": 12.549,
      "step": 73
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2113664150238037,
      "eval_runtime": 0.2471,
      "eval_samples_per_second": 186.183,
      "eval_steps_per_second": 12.142,
      "step": 77
    },
    {
      "epoch": 22.86,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.1854,
      "step": 80
    },
    {
      "epoch": 22.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2140562534332275,
      "eval_runtime": 0.2411,
      "eval_samples_per_second": 190.828,
      "eval_steps_per_second": 12.445,
      "step": 80
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.211725115776062,
      "eval_runtime": 0.2571,
      "eval_samples_per_second": 178.948,
      "eval_steps_per_second": 11.671,
      "step": 84
    },
    {
      "epoch": 24.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2102160453796387,
      "eval_runtime": 0.2521,
      "eval_samples_per_second": 182.498,
      "eval_steps_per_second": 11.902,
      "step": 87
    },
    {
      "epoch": 25.71,
      "learning_rate": 1.388888888888889e-05,
      "loss": 1.1878,
      "step": 90
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2075891494750977,
      "eval_runtime": 0.2521,
      "eval_samples_per_second": 182.498,
      "eval_steps_per_second": 11.902,
      "step": 91
    },
    {
      "epoch": 26.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2082799673080444,
      "eval_runtime": 0.2431,
      "eval_samples_per_second": 189.258,
      "eval_steps_per_second": 12.343,
      "step": 94
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2129710912704468,
      "eval_runtime": 0.2271,
      "eval_samples_per_second": 202.585,
      "eval_steps_per_second": 13.212,
      "step": 98
    },
    {
      "epoch": 28.57,
      "learning_rate": 9.259259259259259e-06,
      "loss": 1.1986,
      "step": 100
    },
    {
      "epoch": 28.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2068954706192017,
      "eval_runtime": 0.2281,
      "eval_samples_per_second": 201.708,
      "eval_steps_per_second": 13.155,
      "step": 101
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2058416604995728,
      "eval_runtime": 0.2551,
      "eval_samples_per_second": 180.351,
      "eval_steps_per_second": 11.762,
      "step": 105
    },
    {
      "epoch": 30.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2070415019989014,
      "eval_runtime": 0.2396,
      "eval_samples_per_second": 192.016,
      "eval_steps_per_second": 12.523,
      "step": 108
    },
    {
      "epoch": 31.43,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 1.182,
      "step": 110
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2074666023254395,
      "eval_runtime": 0.2631,
      "eval_samples_per_second": 174.865,
      "eval_steps_per_second": 11.404,
      "step": 112
    },
    {
      "epoch": 32.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.2073932886123657,
      "eval_runtime": 0.2401,
      "eval_samples_per_second": 191.624,
      "eval_steps_per_second": 12.497,
      "step": 115
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.207228422164917,
      "eval_runtime": 0.2461,
      "eval_samples_per_second": 186.949,
      "eval_steps_per_second": 12.192,
      "step": 119
    },
    {
      "epoch": 34.29,
      "learning_rate": 0.0,
      "loss": 1.2064,
      "step": 120
    },
    {
      "epoch": 34.29,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 1.207200050354004,
      "eval_runtime": 0.2516,
      "eval_samples_per_second": 182.854,
      "eval_steps_per_second": 11.925,
      "step": 120
    },
    {
      "epoch": 34.29,
      "step": 120,
      "total_flos": 2.3770905934823424e+17,
      "train_loss": 2.837039653460185,
      "train_runtime": 179.4861,
      "train_samples_per_second": 47.469,
      "train_steps_per_second": 0.669
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 500,
  "total_flos": 2.3770905934823424e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}