{
  "best_global_step": 548,
  "best_metric": 0.9628349178910977,
  "best_model_checkpoint": "/tmp/finetune/l1/checkpoint-548",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 548,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.072992700729927,
      "grad_norm": Infinity,
      "learning_rate": 8.737864077669904e-07,
      "loss": 1.1059,
      "step": 10
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 44.42300796508789,
      "learning_rate": 1.8446601941747574e-06,
      "loss": 1.154,
      "step": 20
    },
    {
      "epoch": 0.21897810218978103,
      "grad_norm": 25.56485939025879,
      "learning_rate": 2.8155339805825245e-06,
      "loss": 1.2043,
      "step": 30
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 21.406190872192383,
      "learning_rate": 3.7864077669902915e-06,
      "loss": 1.0319,
      "step": 40
    },
    {
      "epoch": 0.36496350364963503,
      "grad_norm": 33.165164947509766,
      "learning_rate": 4.7572815533980585e-06,
      "loss": 0.8044,
      "step": 50
    },
    {
      "epoch": 0.43795620437956206,
      "grad_norm": 20.365318298339844,
      "learning_rate": 5.728155339805825e-06,
      "loss": 0.7708,
      "step": 60
    },
    {
      "epoch": 0.5109489051094891,
      "grad_norm": 22.465822219848633,
      "learning_rate": 6.6990291262135935e-06,
      "loss": 0.6323,
      "step": 70
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 16.91489601135254,
      "learning_rate": 7.66990291262136e-06,
      "loss": 0.4324,
      "step": 80
    },
    {
      "epoch": 0.656934306569343,
      "grad_norm": 21.687286376953125,
      "learning_rate": 8.640776699029127e-06,
      "loss": 0.4886,
      "step": 90
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 31.576948165893555,
      "learning_rate": 9.611650485436894e-06,
      "loss": 0.5687,
      "step": 100
    },
    {
      "epoch": 0.8029197080291971,
      "grad_norm": 1.9548248052597046,
      "learning_rate": 1.0582524271844662e-05,
      "loss": 0.2169,
      "step": 110
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 22.017236709594727,
      "learning_rate": 1.1553398058252427e-05,
      "loss": 0.2982,
      "step": 120
    },
    {
      "epoch": 0.948905109489051,
      "grad_norm": 13.639375686645508,
      "learning_rate": 1.2524271844660197e-05,
      "loss": 0.2452,
      "step": 130
    },
    {
      "epoch": 1.0,
      "eval_f1_macro": 0.904341174899243,
      "eval_f1_micro": 0.9032800672834315,
      "eval_f1_weighted": 0.9042588234821014,
      "eval_loss": 0.14684204757213593,
      "eval_runtime": 1.6696,
      "eval_samples_per_second": 327.624,
      "eval_steps_per_second": 20.963,
      "step": 137
    },
    {
      "epoch": 1.0218978102189782,
      "grad_norm": 4.722266674041748,
      "learning_rate": 1.3495145631067962e-05,
      "loss": 0.1568,
      "step": 140
    },
    {
      "epoch": 1.094890510948905,
      "grad_norm": 25.024124145507812,
      "learning_rate": 1.446601941747573e-05,
      "loss": 0.1066,
      "step": 150
    },
    {
      "epoch": 1.167883211678832,
      "grad_norm": 5.781569957733154,
      "learning_rate": 1.5436893203883496e-05,
      "loss": 0.1277,
      "step": 160
    },
    {
      "epoch": 1.2408759124087592,
      "grad_norm": 17.08236312866211,
      "learning_rate": 1.6407766990291263e-05,
      "loss": 0.0935,
      "step": 170
    },
    {
      "epoch": 1.313868613138686,
      "grad_norm": 10.940235137939453,
      "learning_rate": 1.737864077669903e-05,
      "loss": 0.1571,
      "step": 180
    },
    {
      "epoch": 1.3868613138686132,
      "grad_norm": 4.13682222366333,
      "learning_rate": 1.8349514563106798e-05,
      "loss": 0.1316,
      "step": 190
    },
    {
      "epoch": 1.4598540145985401,
      "grad_norm": 3.4570860862731934,
      "learning_rate": 1.9320388349514565e-05,
      "loss": 0.1334,
      "step": 200
    },
    {
      "epoch": 1.5328467153284673,
      "grad_norm": 12.481249809265137,
      "learning_rate": 1.9967550027041647e-05,
      "loss": 0.1491,
      "step": 210
    },
    {
      "epoch": 1.6058394160583942,
      "grad_norm": 3.959305763244629,
      "learning_rate": 1.9859383450513794e-05,
      "loss": 0.1444,
      "step": 220
    },
    {
      "epoch": 1.6788321167883211,
      "grad_norm": 2.6921675205230713,
      "learning_rate": 1.9751216873985937e-05,
      "loss": 0.0971,
      "step": 230
    },
    {
      "epoch": 1.7518248175182483,
      "grad_norm": 3.2789011001586914,
      "learning_rate": 1.9643050297458088e-05,
      "loss": 0.0657,
      "step": 240
    },
    {
      "epoch": 1.8248175182481752,
      "grad_norm": 47.328712463378906,
      "learning_rate": 1.9534883720930235e-05,
      "loss": 0.1203,
      "step": 250
    },
    {
      "epoch": 1.897810218978102,
      "grad_norm": 3.395271062850952,
      "learning_rate": 1.942671714440238e-05,
      "loss": 0.1544,
      "step": 260
    },
    {
      "epoch": 1.9708029197080292,
      "grad_norm": 12.733712196350098,
      "learning_rate": 1.931855056787453e-05,
      "loss": 0.1459,
      "step": 270
    },
    {
      "epoch": 2.0,
      "eval_f1_macro": 0.9477708161509741,
      "eval_f1_micro": 0.9472789115646258,
      "eval_f1_weighted": 0.9480129474475043,
      "eval_loss": 0.12245870381593704,
      "eval_runtime": 1.7206,
      "eval_samples_per_second": 317.907,
      "eval_steps_per_second": 20.341,
      "step": 274
    },
    {
      "epoch": 2.0437956204379564,
      "grad_norm": 10.530322074890137,
      "learning_rate": 1.9210383991346675e-05,
      "loss": 0.1021,
      "step": 280
    },
    {
      "epoch": 2.116788321167883,
      "grad_norm": 2.0978612899780273,
      "learning_rate": 1.9102217414818822e-05,
      "loss": 0.0758,
      "step": 290
    },
    {
      "epoch": 2.18978102189781,
      "grad_norm": 9.21833610534668,
      "learning_rate": 1.899405083829097e-05,
      "loss": 0.0923,
      "step": 300
    },
    {
      "epoch": 2.2627737226277373,
      "grad_norm": 5.938577651977539,
      "learning_rate": 1.8885884261763116e-05,
      "loss": 0.0452,
      "step": 310
    },
    {
      "epoch": 2.335766423357664,
      "grad_norm": 3.3875350952148438,
      "learning_rate": 1.8777717685235263e-05,
      "loss": 0.0975,
      "step": 320
    },
    {
      "epoch": 2.408759124087591,
      "grad_norm": 14.354475021362305,
      "learning_rate": 1.866955110870741e-05,
      "loss": 0.0924,
      "step": 330
    },
    {
      "epoch": 2.4817518248175183,
      "grad_norm": 1.4160842895507812,
      "learning_rate": 1.8561384532179557e-05,
      "loss": 0.0611,
      "step": 340
    },
    {
      "epoch": 2.554744525547445,
      "grad_norm": 4.338066577911377,
      "learning_rate": 1.8453217955651707e-05,
      "loss": 0.0775,
      "step": 350
    },
    {
      "epoch": 2.627737226277372,
      "grad_norm": 2.572096347808838,
      "learning_rate": 1.8345051379123854e-05,
      "loss": 0.0453,
      "step": 360
    },
    {
      "epoch": 2.7007299270072993,
      "grad_norm": 1.1255489587783813,
      "learning_rate": 1.8236884802596e-05,
      "loss": 0.0324,
      "step": 370
    },
    {
      "epoch": 2.7737226277372264,
      "grad_norm": 15.42068099975586,
      "learning_rate": 1.8128718226068148e-05,
      "loss": 0.0729,
      "step": 380
    },
    {
      "epoch": 2.846715328467153,
      "grad_norm": 1.9290357828140259,
      "learning_rate": 1.8020551649540295e-05,
      "loss": 0.1018,
      "step": 390
    },
    {
      "epoch": 2.9197080291970803,
      "grad_norm": 1.0439828634262085,
      "learning_rate": 1.791238507301244e-05,
      "loss": 0.0856,
      "step": 400
    },
    {
      "epoch": 2.9927007299270074,
      "grad_norm": 10.982110977172852,
      "learning_rate": 1.7804218496484588e-05,
      "loss": 0.077,
      "step": 410
    },
    {
      "epoch": 3.0,
      "eval_f1_macro": 0.9476025336319455,
      "eval_f1_micro": 0.9478260869565217,
      "eval_f1_weighted": 0.947698687741686,
      "eval_loss": 0.14635968208312988,
      "eval_runtime": 1.6325,
      "eval_samples_per_second": 335.077,
      "eval_steps_per_second": 21.44,
      "step": 411
    },
    {
      "epoch": 3.065693430656934,
      "grad_norm": 1.0763516426086426,
      "learning_rate": 1.7696051919956735e-05,
      "loss": 0.0499,
      "step": 420
    },
    {
      "epoch": 3.1386861313868613,
      "grad_norm": 4.268288612365723,
      "learning_rate": 1.7587885343428882e-05,
      "loss": 0.0415,
      "step": 430
    },
    {
      "epoch": 3.2116788321167884,
      "grad_norm": 1.0834965705871582,
      "learning_rate": 1.747971876690103e-05,
      "loss": 0.0505,
      "step": 440
    },
    {
      "epoch": 3.2846715328467155,
      "grad_norm": 1.1049467325210571,
      "learning_rate": 1.7371552190373176e-05,
      "loss": 0.0495,
      "step": 450
    },
    {
      "epoch": 3.3576642335766422,
      "grad_norm": 4.047983646392822,
      "learning_rate": 1.7263385613845323e-05,
      "loss": 0.0615,
      "step": 460
    },
    {
      "epoch": 3.4306569343065694,
      "grad_norm": 2.435213327407837,
      "learning_rate": 1.715521903731747e-05,
      "loss": 0.043,
      "step": 470
    },
    {
      "epoch": 3.5036496350364965,
      "grad_norm": 2.0357930660247803,
      "learning_rate": 1.7047052460789617e-05,
      "loss": 0.1102,
      "step": 480
    },
    {
      "epoch": 3.576642335766423,
      "grad_norm": 30.20710563659668,
      "learning_rate": 1.6938885884261763e-05,
      "loss": 0.0407,
      "step": 490
    },
    {
      "epoch": 3.6496350364963503,
      "grad_norm": 1.8748276233673096,
      "learning_rate": 1.683071930773391e-05,
      "loss": 0.0748,
      "step": 500
    },
    {
      "epoch": 3.7226277372262775,
      "grad_norm": 2.229926347732544,
      "learning_rate": 1.6722552731206057e-05,
      "loss": 0.0328,
      "step": 510
    },
    {
      "epoch": 3.795620437956204,
      "grad_norm": 0.9702017903327942,
      "learning_rate": 1.6614386154678208e-05,
      "loss": 0.0491,
      "step": 520
    },
    {
      "epoch": 3.8686131386861313,
      "grad_norm": 0.7791664600372314,
      "learning_rate": 1.6506219578150354e-05,
      "loss": 0.0218,
      "step": 530
    },
    {
      "epoch": 3.9416058394160585,
      "grad_norm": 1.9696235656738281,
      "learning_rate": 1.63980530016225e-05,
      "loss": 0.0641,
      "step": 540
    },
    {
      "epoch": 4.0,
      "eval_f1_macro": 0.9628456567083955,
      "eval_f1_micro": 0.9628349178910977,
      "eval_f1_weighted": 0.9628281230678446,
      "eval_loss": 0.12824897468090057,
      "eval_runtime": 1.8072,
      "eval_samples_per_second": 302.683,
      "eval_steps_per_second": 19.367,
      "step": 548
    }
  ],
  "logging_steps": 10,
  "max_steps": 2055,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 115136787138912.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}