{
  "best_metric": 0.113589346408844,
  "best_model_checkpoint": "./models/results_comb_453/checkpoint-425",
  "epoch": 0.9424809424809425,
  "global_step": 425,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6901,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6684,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.2e-05,
      "loss": 0.6534,
      "step": 24
    },
    {
      "epoch": 0.06,
      "eval_accuracy": 0.5841623557500994,
      "eval_f1": 0.7375031399145943,
      "eval_loss": 0.6666890978813171,
      "eval_precision": 0.5841623557500994,
      "eval_recall": 1.0,
      "eval_runtime": 38.749,
      "eval_samples_per_second": 194.56,
      "eval_steps_per_second": 24.336,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.64,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 0.6171,
      "step": 40
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.35e-05,
      "loss": 0.4811,
      "step": 48
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.8840695052394216,
      "eval_f1": 0.9018859452177818,
      "eval_loss": 0.38738805055618286,
      "eval_precision": 0.8918738898756661,
      "eval_recall": 0.912125340599455,
      "eval_runtime": 34.9973,
      "eval_samples_per_second": 215.416,
      "eval_steps_per_second": 26.945,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.3376,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.15e-05,
      "loss": 0.3194,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.55e-05,
      "loss": 0.256,
      "step": 72
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.913914312243003,
      "eval_f1": 0.9237636555855749,
      "eval_loss": 0.21917007863521576,
      "eval_precision": 0.9569238257483572,
      "eval_recall": 0.8928247048138056,
      "eval_runtime": 35.1296,
      "eval_samples_per_second": 214.606,
      "eval_steps_per_second": 26.843,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.243,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.35e-05,
      "loss": 0.2168,
      "step": 88
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.75e-05,
      "loss": 0.2272,
      "step": 96
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.9312906220984215,
      "eval_f1": 0.9422390722569135,
      "eval_loss": 0.18572893738746643,
      "eval_precision": 0.9257230499561788,
      "eval_recall": 0.959355131698456,
      "eval_runtime": 34.8101,
      "eval_samples_per_second": 216.575,
      "eval_steps_per_second": 27.09,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.957142857142857e-05,
      "loss": 0.1749,
      "step": 104
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.842857142857143e-05,
      "loss": 0.2275,
      "step": 112
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.728571428571429e-05,
      "loss": 0.218,
      "step": 120
    },
    {
      "epoch": 0.28,
      "eval_accuracy": 0.9393818808860591,
      "eval_f1": 0.949171393615838,
      "eval_loss": 0.15581709146499634,
      "eval_precision": 0.9302376280793547,
      "eval_recall": 0.9688919164396004,
      "eval_runtime": 35.2114,
      "eval_samples_per_second": 214.107,
      "eval_steps_per_second": 26.781,
      "step": 125
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.6142857142857145e-05,
      "loss": 0.2285,
      "step": 128
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.5e-05,
      "loss": 0.1953,
      "step": 136
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.385714285714286e-05,
      "loss": 0.201,
      "step": 144
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.940708316752885,
      "eval_f1": 0.9498260186328432,
      "eval_loss": 0.154759481549263,
      "eval_precision": 0.9391786903440622,
      "eval_recall": 0.9607175295186194,
      "eval_runtime": 34.6999,
      "eval_samples_per_second": 217.263,
      "eval_steps_per_second": 27.176,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.271428571428572e-05,
      "loss": 0.1915,
      "step": 152
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.1571428571428575e-05,
      "loss": 0.2163,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.042857142857143e-05,
      "loss": 0.1934,
      "step": 168
    },
    {
      "epoch": 0.39,
      "eval_accuracy": 0.9387186629526463,
      "eval_f1": 0.9471032745591939,
      "eval_loss": 0.1729520708322525,
      "eval_precision": 0.9551963048498845,
      "eval_recall": 0.9391462306993642,
      "eval_runtime": 34.0751,
      "eval_samples_per_second": 221.247,
      "eval_steps_per_second": 27.674,
      "step": 175
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.185,
      "step": 176
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.814285714285715e-05,
      "loss": 0.2181,
      "step": 184
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.7e-05,
      "loss": 0.1423,
      "step": 192
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.585714285714286e-05,
      "loss": 0.1737,
      "step": 200
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.9441570500066322,
      "eval_f1": 0.9513013302486986,
      "eval_loss": 0.1504576951265335,
      "eval_precision": 0.9695826456024522,
      "eval_recall": 0.9336966394187103,
      "eval_runtime": 34.4966,
      "eval_samples_per_second": 218.544,
      "eval_steps_per_second": 27.336,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.471428571428571e-05,
      "loss": 0.1664,
      "step": 208
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.357142857142857e-05,
      "loss": 0.1072,
      "step": 216
    },
    {
      "epoch": 0.5,
      "learning_rate": 3.242857142857143e-05,
      "loss": 0.1209,
      "step": 224
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.9538400318344608,
      "eval_f1": 0.9605710401087695,
      "eval_loss": 0.12554903328418732,
      "eval_precision": 0.9586160108548168,
      "eval_recall": 0.9625340599455041,
      "eval_runtime": 34.0808,
      "eval_samples_per_second": 221.21,
      "eval_steps_per_second": 27.67,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.1285714285714285e-05,
      "loss": 0.1808,
      "step": 232
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.0142857142857146e-05,
      "loss": 0.1619,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.9e-05,
      "loss": 0.1808,
      "step": 248
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.9460140602201883,
      "eval_f1": 0.9544691799977626,
      "eval_loss": 0.14133918285369873,
      "eval_precision": 0.940683572216097,
      "eval_recall": 0.9686648501362398,
      "eval_runtime": 34.4019,
      "eval_samples_per_second": 219.145,
      "eval_steps_per_second": 27.411,
      "step": 250
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.785714285714286e-05,
      "loss": 0.1802,
      "step": 256
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.6714285714285715e-05,
      "loss": 0.1555,
      "step": 264
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.5571428571428572e-05,
      "loss": 0.1274,
      "step": 272
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.9559623292213821,
      "eval_f1": 0.9620137299771168,
      "eval_loss": 0.1330484300851822,
      "eval_precision": 0.9695571955719557,
      "eval_recall": 0.9545867393278837,
      "eval_runtime": 34.8961,
      "eval_samples_per_second": 216.041,
      "eval_steps_per_second": 27.023,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.442857142857143e-05,
      "loss": 0.1112,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.3285714285714287e-05,
      "loss": 0.1567,
      "step": 288
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.214285714285714e-05,
      "loss": 0.1408,
      "step": 296
    },
    {
      "epoch": 0.67,
      "eval_accuracy": 0.9571561215015254,
      "eval_f1": 0.9634325823615986,
      "eval_loss": 0.12022460252046585,
      "eval_precision": 0.9607134793407089,
      "eval_recall": 0.9661671207992734,
      "eval_runtime": 35.3597,
      "eval_samples_per_second": 213.209,
      "eval_steps_per_second": 26.669,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.1e-05,
      "loss": 0.1256,
      "step": 304
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.9857142857142856e-05,
      "loss": 0.1378,
      "step": 312
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8714285714285714e-05,
      "loss": 0.0942,
      "step": 320
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.9551664677012867,
      "eval_f1": 0.9612563044475011,
      "eval_loss": 0.1314559429883957,
      "eval_precision": 0.9706018518518519,
      "eval_recall": 0.9520890099909174,
      "eval_runtime": 35.9898,
      "eval_samples_per_second": 209.476,
      "eval_steps_per_second": 26.202,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.757142857142857e-05,
      "loss": 0.1238,
      "step": 328
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.642857142857143e-05,
      "loss": 0.1262,
      "step": 336
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.5285714285714286e-05,
      "loss": 0.1627,
      "step": 344
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.9473404960870142,
      "eval_f1": 0.9539603386292473,
      "eval_loss": 0.14597517251968384,
      "eval_precision": 0.9748755629296042,
      "eval_recall": 0.9339237057220708,
      "eval_runtime": 39.0107,
      "eval_samples_per_second": 193.255,
      "eval_steps_per_second": 24.173,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.4142857142857143e-05,
      "loss": 0.1338,
      "step": 352
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.1022,
      "step": 360
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.1857142857142858e-05,
      "loss": 0.095,
      "step": 368
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.9562276163947473,
      "eval_f1": 0.9622425629290619,
      "eval_loss": 0.13147765398025513,
      "eval_precision": 0.9697878228782287,
      "eval_recall": 0.9548138056312443,
      "eval_runtime": 37.6951,
      "eval_samples_per_second": 199.999,
      "eval_steps_per_second": 25.016,
      "step": 375
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 0.0907,
      "step": 376
    },
    {
      "epoch": 0.85,
      "learning_rate": 9.571428571428572e-06,
      "loss": 0.1099,
      "step": 384
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.428571428571429e-06,
      "loss": 0.1498,
      "step": 392
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.285714285714286e-06,
      "loss": 0.1221,
      "step": 400
    },
    {
      "epoch": 0.89,
      "eval_accuracy": 0.9549011805279215,
      "eval_f1": 0.961080586080586,
      "eval_loss": 0.11751025170087814,
      "eval_precision": 0.969067405355494,
      "eval_recall": 0.9532243415077203,
      "eval_runtime": 38.9296,
      "eval_samples_per_second": 193.657,
      "eval_steps_per_second": 24.223,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.142857142857143e-06,
      "loss": 0.1109,
      "step": 408
    },
    {
      "epoch": 0.92,
      "learning_rate": 5e-06,
      "loss": 0.1069,
      "step": 416
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.857142857142857e-06,
      "loss": 0.0952,
      "step": 424
    },
    {
      "epoch": 0.94,
      "eval_accuracy": 0.9602069239952248,
      "eval_f1": 0.9661552346570397,
      "eval_loss": 0.113589346408844,
      "eval_precision": 0.9600896860986547,
      "eval_recall": 0.9722979109900091,
      "eval_runtime": 39.1055,
      "eval_samples_per_second": 192.786,
      "eval_steps_per_second": 24.114,
      "step": 425
    }
  ],
  "max_steps": 450,
  "num_train_epochs": 1,
  "total_flos": 4626643464096000.0,
  "trial_name": null,
  "trial_params": null
}