{
  "best_metric": 0.840443960959029,
  "best_model_checkpoint": "/data/ephemeral/home/level2-nlp-datacentric-nlp-15/models/train_new_8564_7000fconcat+deepl_15000.csv_20241107_163124/checkpoint-600",
  "epoch": 2.0,
  "eval_steps": 100,
  "global_step": 692,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028901734104046242,
      "grad_norm": 5.670835018157959,
      "learning_rate": 1.971098265895954e-05,
      "loss": 1.8852,
      "step": 10
    },
    {
      "epoch": 0.057803468208092484,
      "grad_norm": 5.40836763381958,
      "learning_rate": 1.9421965317919077e-05,
      "loss": 1.6768,
      "step": 20
    },
    {
      "epoch": 0.08670520231213873,
      "grad_norm": 6.977480888366699,
      "learning_rate": 1.9132947976878615e-05,
      "loss": 1.4293,
      "step": 30
    },
    {
      "epoch": 0.11560693641618497,
      "grad_norm": 6.8324995040893555,
      "learning_rate": 1.8843930635838153e-05,
      "loss": 1.2372,
      "step": 40
    },
    {
      "epoch": 0.14450867052023122,
      "grad_norm": 4.969491481781006,
      "learning_rate": 1.855491329479769e-05,
      "loss": 1.0231,
      "step": 50
    },
    {
      "epoch": 0.17341040462427745,
      "grad_norm": 7.948673725128174,
      "learning_rate": 1.8265895953757225e-05,
      "loss": 0.9941,
      "step": 60
    },
    {
      "epoch": 0.2023121387283237,
      "grad_norm": 7.314361572265625,
      "learning_rate": 1.7976878612716763e-05,
      "loss": 0.8929,
      "step": 70
    },
    {
      "epoch": 0.23121387283236994,
      "grad_norm": 7.860761642456055,
      "learning_rate": 1.76878612716763e-05,
      "loss": 0.7236,
      "step": 80
    },
    {
      "epoch": 0.26011560693641617,
      "grad_norm": 8.400164604187012,
      "learning_rate": 1.739884393063584e-05,
      "loss": 0.7342,
      "step": 90
    },
    {
      "epoch": 0.28901734104046245,
      "grad_norm": 5.281578063964844,
      "learning_rate": 1.7109826589595377e-05,
      "loss": 0.7285,
      "step": 100
    },
    {
      "epoch": 0.28901734104046245,
      "eval_f1": 0.7855931775121717,
      "eval_loss": 0.6838143467903137,
      "eval_runtime": 43.4732,
      "eval_samples_per_second": 108.895,
      "eval_steps_per_second": 3.404,
      "step": 100
    },
    {
      "epoch": 0.3179190751445087,
      "grad_norm": 6.559142589569092,
      "learning_rate": 1.6820809248554915e-05,
      "loss": 0.767,
      "step": 110
    },
    {
      "epoch": 0.3468208092485549,
      "grad_norm": 6.961650371551514,
      "learning_rate": 1.6531791907514452e-05,
      "loss": 0.72,
      "step": 120
    },
    {
      "epoch": 0.37572254335260113,
      "grad_norm": 7.83851432800293,
      "learning_rate": 1.624277456647399e-05,
      "loss": 0.6204,
      "step": 130
    },
    {
      "epoch": 0.4046242774566474,
      "grad_norm": 5.967935562133789,
      "learning_rate": 1.5953757225433528e-05,
      "loss": 0.6811,
      "step": 140
    },
    {
      "epoch": 0.43352601156069365,
      "grad_norm": 7.195727348327637,
      "learning_rate": 1.5664739884393066e-05,
      "loss": 0.7254,
      "step": 150
    },
    {
      "epoch": 0.4624277456647399,
      "grad_norm": 6.0163750648498535,
      "learning_rate": 1.5375722543352604e-05,
      "loss": 0.5248,
      "step": 160
    },
    {
      "epoch": 0.4913294797687861,
      "grad_norm": 7.599509239196777,
      "learning_rate": 1.508670520231214e-05,
      "loss": 0.6095,
      "step": 170
    },
    {
      "epoch": 0.5202312138728323,
      "grad_norm": 11.452792167663574,
      "learning_rate": 1.4797687861271676e-05,
      "loss": 0.6339,
      "step": 180
    },
    {
      "epoch": 0.5491329479768786,
      "grad_norm": 9.863639831542969,
      "learning_rate": 1.4508670520231216e-05,
      "loss": 0.5901,
      "step": 190
    },
    {
      "epoch": 0.5780346820809249,
      "grad_norm": 6.931671619415283,
      "learning_rate": 1.4219653179190754e-05,
      "loss": 0.5106,
      "step": 200
    },
    {
      "epoch": 0.5780346820809249,
      "eval_f1": 0.8163391427279263,
      "eval_loss": 0.604805588722229,
      "eval_runtime": 43.5017,
      "eval_samples_per_second": 108.823,
      "eval_steps_per_second": 3.402,
      "step": 200
    },
    {
      "epoch": 0.6069364161849711,
      "grad_norm": 7.751237869262695,
      "learning_rate": 1.393063583815029e-05,
      "loss": 0.6615,
      "step": 210
    },
    {
      "epoch": 0.6358381502890174,
      "grad_norm": 7.981545925140381,
      "learning_rate": 1.3641618497109828e-05,
      "loss": 0.6194,
      "step": 220
    },
    {
      "epoch": 0.6647398843930635,
      "grad_norm": 8.75810432434082,
      "learning_rate": 1.3352601156069365e-05,
      "loss": 0.6756,
      "step": 230
    },
    {
      "epoch": 0.6936416184971098,
      "grad_norm": 7.4759521484375,
      "learning_rate": 1.3063583815028902e-05,
      "loss": 0.6079,
      "step": 240
    },
    {
      "epoch": 0.7225433526011561,
      "grad_norm": 9.445594787597656,
      "learning_rate": 1.2774566473988441e-05,
      "loss": 0.5329,
      "step": 250
    },
    {
      "epoch": 0.7514450867052023,
      "grad_norm": 7.227514266967773,
      "learning_rate": 1.2485549132947979e-05,
      "loss": 0.5342,
      "step": 260
    },
    {
      "epoch": 0.7803468208092486,
      "grad_norm": 6.781445503234863,
      "learning_rate": 1.2196531791907515e-05,
      "loss": 0.5455,
      "step": 270
    },
    {
      "epoch": 0.8092485549132948,
      "grad_norm": 7.4944353103637695,
      "learning_rate": 1.1907514450867053e-05,
      "loss": 0.5171,
      "step": 280
    },
    {
      "epoch": 0.838150289017341,
      "grad_norm": 12.261595726013184,
      "learning_rate": 1.161849710982659e-05,
      "loss": 0.5793,
      "step": 290
    },
    {
      "epoch": 0.8670520231213873,
      "grad_norm": 7.033445835113525,
      "learning_rate": 1.1329479768786129e-05,
      "loss": 0.6664,
      "step": 300
    },
    {
      "epoch": 0.8670520231213873,
      "eval_f1": 0.8202014204332396,
      "eval_loss": 0.5958309769630432,
      "eval_runtime": 43.4645,
      "eval_samples_per_second": 108.916,
      "eval_steps_per_second": 3.405,
      "step": 300
    },
    {
      "epoch": 0.8959537572254336,
      "grad_norm": 16.04691505432129,
      "learning_rate": 1.1040462427745667e-05,
      "loss": 0.5736,
      "step": 310
    },
    {
      "epoch": 0.9248554913294798,
      "grad_norm": 6.906232833862305,
      "learning_rate": 1.0751445086705203e-05,
      "loss": 0.5677,
      "step": 320
    },
    {
      "epoch": 0.953757225433526,
      "grad_norm": 7.995438098907471,
      "learning_rate": 1.046242774566474e-05,
      "loss": 0.5872,
      "step": 330
    },
    {
      "epoch": 0.9826589595375722,
      "grad_norm": 7.967160701751709,
      "learning_rate": 1.0173410404624278e-05,
      "loss": 0.5363,
      "step": 340
    },
    {
      "epoch": 1.0115606936416186,
      "grad_norm": 7.901902198791504,
      "learning_rate": 9.884393063583816e-06,
      "loss": 0.4558,
      "step": 350
    },
    {
      "epoch": 1.0404624277456647,
      "grad_norm": 3.8353588581085205,
      "learning_rate": 9.595375722543352e-06,
      "loss": 0.563,
      "step": 360
    },
    {
      "epoch": 1.069364161849711,
      "grad_norm": 10.367301940917969,
      "learning_rate": 9.306358381502892e-06,
      "loss": 0.4669,
      "step": 370
    },
    {
      "epoch": 1.0982658959537572,
      "grad_norm": 3.960563898086548,
      "learning_rate": 9.017341040462428e-06,
      "loss": 0.4186,
      "step": 380
    },
    {
      "epoch": 1.1271676300578035,
      "grad_norm": 5.368332862854004,
      "learning_rate": 8.728323699421966e-06,
      "loss": 0.4852,
      "step": 390
    },
    {
      "epoch": 1.1560693641618498,
      "grad_norm": 4.498876094818115,
      "learning_rate": 8.439306358381504e-06,
      "loss": 0.5515,
      "step": 400
    },
    {
      "epoch": 1.1560693641618498,
      "eval_f1": 0.832606512739663,
      "eval_loss": 0.5639938116073608,
      "eval_runtime": 43.4855,
      "eval_samples_per_second": 108.864,
      "eval_steps_per_second": 3.403,
      "step": 400
    },
    {
      "epoch": 1.1849710982658959,
      "grad_norm": 6.101068496704102,
      "learning_rate": 8.150289017341042e-06,
      "loss": 0.5084,
      "step": 410
    },
    {
      "epoch": 1.2138728323699421,
      "grad_norm": 8.67908000946045,
      "learning_rate": 7.86127167630058e-06,
      "loss": 0.4328,
      "step": 420
    },
    {
      "epoch": 1.2427745664739884,
      "grad_norm": 6.932382106781006,
      "learning_rate": 7.5722543352601166e-06,
      "loss": 0.3798,
      "step": 430
    },
    {
      "epoch": 1.2716763005780347,
      "grad_norm": 6.64376163482666,
      "learning_rate": 7.283236994219654e-06,
      "loss": 0.4763,
      "step": 440
    },
    {
      "epoch": 1.300578034682081,
      "grad_norm": 5.648944854736328,
      "learning_rate": 6.9942196531791914e-06,
      "loss": 0.4008,
      "step": 450
    },
    {
      "epoch": 1.3294797687861273,
      "grad_norm": 8.3818998336792,
      "learning_rate": 6.7052023121387284e-06,
      "loss": 0.4959,
      "step": 460
    },
    {
      "epoch": 1.3583815028901733,
      "grad_norm": 6.271963119506836,
      "learning_rate": 6.416184971098266e-06,
      "loss": 0.4123,
      "step": 470
    },
    {
      "epoch": 1.3872832369942196,
      "grad_norm": 10.868525505065918,
      "learning_rate": 6.127167630057804e-06,
      "loss": 0.4478,
      "step": 480
    },
    {
      "epoch": 1.416184971098266,
      "grad_norm": 4.8018012046813965,
      "learning_rate": 5.838150289017341e-06,
      "loss": 0.3475,
      "step": 490
    },
    {
      "epoch": 1.4450867052023122,
      "grad_norm": 7.195227146148682,
      "learning_rate": 5.549132947976878e-06,
      "loss": 0.5246,
      "step": 500
    },
    {
      "epoch": 1.4450867052023122,
      "eval_f1": 0.8394367921843663,
      "eval_loss": 0.5455829501152039,
      "eval_runtime": 43.4865,
      "eval_samples_per_second": 108.861,
      "eval_steps_per_second": 3.403,
      "step": 500
    },
    {
      "epoch": 1.4739884393063583,
      "grad_norm": 7.47812557220459,
      "learning_rate": 5.260115606936417e-06,
      "loss": 0.4008,
      "step": 510
    },
    {
      "epoch": 1.5028901734104045,
      "grad_norm": 3.8493812084198,
      "learning_rate": 4.971098265895954e-06,
      "loss": 0.4166,
      "step": 520
    },
    {
      "epoch": 1.5317919075144508,
      "grad_norm": 6.382811069488525,
      "learning_rate": 4.682080924855492e-06,
      "loss": 0.4287,
      "step": 530
    },
    {
      "epoch": 1.560693641618497,
      "grad_norm": 4.259267330169678,
      "learning_rate": 4.3930635838150296e-06,
      "loss": 0.4493,
      "step": 540
    },
    {
      "epoch": 1.5895953757225434,
      "grad_norm": 5.338929653167725,
      "learning_rate": 4.1040462427745666e-06,
      "loss": 0.4488,
      "step": 550
    },
    {
      "epoch": 1.6184971098265897,
      "grad_norm": 4.65845251083374,
      "learning_rate": 3.815028901734104e-06,
      "loss": 0.4649,
      "step": 560
    },
    {
      "epoch": 1.647398843930636,
      "grad_norm": 8.946381568908691,
      "learning_rate": 3.526011560693642e-06,
      "loss": 0.4826,
      "step": 570
    },
    {
      "epoch": 1.6763005780346822,
      "grad_norm": 10.277519226074219,
      "learning_rate": 3.2369942196531797e-06,
      "loss": 0.4061,
      "step": 580
    },
    {
      "epoch": 1.7052023121387283,
      "grad_norm": 9.004323959350586,
      "learning_rate": 2.947976878612717e-06,
      "loss": 0.463,
      "step": 590
    },
    {
      "epoch": 1.7341040462427746,
      "grad_norm": 9.768237113952637,
      "learning_rate": 2.658959537572254e-06,
      "loss": 0.407,
      "step": 600
    },
    {
      "epoch": 1.7341040462427746,
      "eval_f1": 0.840443960959029,
      "eval_loss": 0.5418282151222229,
      "eval_runtime": 43.4552,
      "eval_samples_per_second": 108.94,
      "eval_steps_per_second": 3.406,
      "step": 600
    },
    {
      "epoch": 1.7630057803468207,
      "grad_norm": 3.791731119155884,
      "learning_rate": 2.369942196531792e-06,
      "loss": 0.4195,
      "step": 610
    },
    {
      "epoch": 1.791907514450867,
      "grad_norm": 9.772268295288086,
      "learning_rate": 2.08092485549133e-06,
      "loss": 0.4644,
      "step": 620
    },
    {
      "epoch": 1.8208092485549132,
      "grad_norm": 5.360107421875,
      "learning_rate": 1.791907514450867e-06,
      "loss": 0.4315,
      "step": 630
    },
    {
      "epoch": 1.8497109826589595,
      "grad_norm": 9.654316902160645,
      "learning_rate": 1.502890173410405e-06,
      "loss": 0.435,
      "step": 640
    },
    {
      "epoch": 1.8786127167630058,
      "grad_norm": 6.9839768409729,
      "learning_rate": 1.2138728323699423e-06,
      "loss": 0.387,
      "step": 650
    },
    {
      "epoch": 1.907514450867052,
      "grad_norm": 8.008018493652344,
      "learning_rate": 9.248554913294798e-07,
      "loss": 0.4039,
      "step": 660
    },
    {
      "epoch": 1.9364161849710984,
      "grad_norm": 7.851306438446045,
      "learning_rate": 6.358381502890174e-07,
      "loss": 0.4879,
      "step": 670
    },
    {
      "epoch": 1.9653179190751446,
      "grad_norm": 10.8189115524292,
      "learning_rate": 3.468208092485549e-07,
      "loss": 0.3706,
      "step": 680
    },
    {
      "epoch": 1.9942196531791907,
      "grad_norm": 8.877676963806152,
      "learning_rate": 5.7803468208092485e-08,
      "loss": 0.3861,
      "step": 690
    }
  ],
  "logging_steps": 10,
  "max_steps": 692,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5812910382182400.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}