{
  "best_metric": 5.793323516845703,
  "best_model_checkpoint": "turkish-embedding-model/checkpoint-1564",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1564,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0319693094629156,
      "grad_norm": 70.72708129882812,
      "learning_rate": 1.1253196930946293e-06,
      "loss": 17.17,
      "step": 25
    },
    {
      "epoch": 0.0639386189258312,
      "grad_norm": 81.68770599365234,
      "learning_rate": 2.4040920716112534e-06,
      "loss": 16.4932,
      "step": 50
    },
    {
      "epoch": 0.0959079283887468,
      "grad_norm": 109.91338348388672,
      "learning_rate": 3.6828644501278778e-06,
      "loss": 16.5976,
      "step": 75
    },
    {
      "epoch": 0.1278772378516624,
      "grad_norm": 73.892578125,
      "learning_rate": 4.961636828644502e-06,
      "loss": 15.6991,
      "step": 100
    },
    {
      "epoch": 0.159846547314578,
      "grad_norm": 79.35150909423828,
      "learning_rate": 6.240409207161126e-06,
      "loss": 14.876,
      "step": 125
    },
    {
      "epoch": 0.1918158567774936,
      "grad_norm": 83.0904541015625,
      "learning_rate": 7.5191815856777495e-06,
      "loss": 14.4828,
      "step": 150
    },
    {
      "epoch": 0.2237851662404092,
      "grad_norm": 76.82855987548828,
      "learning_rate": 8.797953964194374e-06,
      "loss": 12.7061,
      "step": 175
    },
    {
      "epoch": 0.2557544757033248,
      "grad_norm": 51.30181121826172,
      "learning_rate": 1.0076726342710998e-05,
      "loss": 10.8687,
      "step": 200
    },
    {
      "epoch": 0.2877237851662404,
      "grad_norm": 18.70808219909668,
      "learning_rate": 1.1355498721227622e-05,
      "loss": 8.3797,
      "step": 225
    },
    {
      "epoch": 0.319693094629156,
      "grad_norm": 1.3039417266845703,
      "learning_rate": 1.2634271099744246e-05,
      "loss": 6.2029,
      "step": 250
    },
    {
      "epoch": 0.3516624040920716,
      "grad_norm": 0.2324853092432022,
      "learning_rate": 1.391304347826087e-05,
      "loss": 5.8228,
      "step": 275
    },
    {
      "epoch": 0.3836317135549872,
      "grad_norm": 0.1757364720106125,
      "learning_rate": 1.5191815856777494e-05,
      "loss": 5.811,
      "step": 300
    },
    {
      "epoch": 0.4156010230179028,
      "grad_norm": 0.1788654774427414,
      "learning_rate": 1.647058823529412e-05,
      "loss": 5.8079,
      "step": 325
    },
    {
      "epoch": 0.4475703324808184,
      "grad_norm": 0.12862567603588104,
      "learning_rate": 1.7749360613810744e-05,
      "loss": 5.8077,
      "step": 350
    },
    {
      "epoch": 0.479539641943734,
      "grad_norm": 0.14497514069080353,
      "learning_rate": 1.9028132992327367e-05,
      "loss": 5.8035,
      "step": 375
    },
    {
      "epoch": 0.5115089514066496,
      "grad_norm": 0.1350390762090683,
      "learning_rate": 1.996589940323956e-05,
      "loss": 5.8072,
      "step": 400
    },
    {
      "epoch": 0.5434782608695652,
      "grad_norm": 0.1435602754354477,
      "learning_rate": 1.9823813583404378e-05,
      "loss": 5.8033,
      "step": 425
    },
    {
      "epoch": 0.5754475703324808,
      "grad_norm": 0.11389254033565521,
      "learning_rate": 1.96817277635692e-05,
      "loss": 5.8086,
      "step": 450
    },
    {
      "epoch": 0.6074168797953964,
      "grad_norm": 0.15821650624275208,
      "learning_rate": 1.9539641943734017e-05,
      "loss": 5.81,
      "step": 475
    },
    {
      "epoch": 0.639386189258312,
      "grad_norm": 0.1179889366030693,
      "learning_rate": 1.9397556123898838e-05,
      "loss": 5.7949,
      "step": 500
    },
    {
      "epoch": 0.6713554987212276,
      "grad_norm": 0.10912967473268509,
      "learning_rate": 1.9255470304063656e-05,
      "loss": 5.8079,
      "step": 525
    },
    {
      "epoch": 0.7033248081841432,
      "grad_norm": 0.11702870577573776,
      "learning_rate": 1.9113384484228477e-05,
      "loss": 5.8057,
      "step": 550
    },
    {
      "epoch": 0.7352941176470589,
      "grad_norm": 0.13132448494434357,
      "learning_rate": 1.8971298664393295e-05,
      "loss": 5.8097,
      "step": 575
    },
    {
      "epoch": 0.7672634271099744,
      "grad_norm": 0.15833145380020142,
      "learning_rate": 1.8829212844558116e-05,
      "loss": 5.7986,
      "step": 600
    },
    {
      "epoch": 0.7992327365728901,
      "grad_norm": 0.11651863902807236,
      "learning_rate": 1.8687127024722937e-05,
      "loss": 5.8051,
      "step": 625
    },
    {
      "epoch": 0.8312020460358056,
      "grad_norm": 0.5393890142440796,
      "learning_rate": 1.854504120488775e-05,
      "loss": 5.8041,
      "step": 650
    },
    {
      "epoch": 0.8631713554987213,
      "grad_norm": 0.6457561254501343,
      "learning_rate": 1.8402955385052572e-05,
      "loss": 5.7907,
      "step": 675
    },
    {
      "epoch": 0.8951406649616368,
      "grad_norm": 0.5643135905265808,
      "learning_rate": 1.8260869565217393e-05,
      "loss": 5.7991,
      "step": 700
    },
    {
      "epoch": 0.9271099744245525,
      "grad_norm": 3.214787721633911,
      "learning_rate": 1.811878374538221e-05,
      "loss": 5.8035,
      "step": 725
    },
    {
      "epoch": 0.959079283887468,
      "grad_norm": 2.781162977218628,
      "learning_rate": 1.7976697925547032e-05,
      "loss": 5.7945,
      "step": 750
    },
    {
      "epoch": 0.9910485933503836,
      "grad_norm": 0.38559335470199585,
      "learning_rate": 1.783461210571185e-05,
      "loss": 5.8077,
      "step": 775
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.8023600578308105,
      "eval_runtime": 18.0632,
      "eval_samples_per_second": 276.805,
      "eval_steps_per_second": 4.374,
      "eval_tr_ling_pearson_cosine": 0.017751548525136808,
      "eval_tr_ling_pearson_dot": 0.025703597820631346,
      "eval_tr_ling_pearson_euclidean": 0.02195284877201089,
      "eval_tr_ling_pearson_manhattan": 0.02083376479528459,
      "eval_tr_ling_pearson_max": 0.025703597820631346,
      "eval_tr_ling_spearman_cosine": 0.027108099994157316,
      "eval_tr_ling_spearman_dot": 0.03304394653738539,
      "eval_tr_ling_spearman_euclidean": 0.025485959636772793,
      "eval_tr_ling_spearman_manhattan": 0.024466610177699702,
      "eval_tr_ling_spearman_max": 0.03304394653738539,
      "step": 782
    },
    {
      "epoch": 1.0230179028132993,
      "grad_norm": 0.3645063638687134,
      "learning_rate": 1.769252628587667e-05,
      "loss": 5.6703,
      "step": 800
    },
    {
      "epoch": 1.054987212276215,
      "grad_norm": 0.9638137817382812,
      "learning_rate": 1.7550440466041488e-05,
      "loss": 5.8052,
      "step": 825
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 2.114203691482544,
      "learning_rate": 1.740835464620631e-05,
      "loss": 5.7936,
      "step": 850
    },
    {
      "epoch": 1.118925831202046,
      "grad_norm": 1.8992066383361816,
      "learning_rate": 1.7266268826371127e-05,
      "loss": 5.7924,
      "step": 875
    },
    {
      "epoch": 1.1508951406649617,
      "grad_norm": 2.8299577236175537,
      "learning_rate": 1.7124183006535948e-05,
      "loss": 5.7806,
      "step": 900
    },
    {
      "epoch": 1.1828644501278773,
      "grad_norm": 1.956953525543213,
      "learning_rate": 1.698209718670077e-05,
      "loss": 5.7835,
      "step": 925
    },
    {
      "epoch": 1.2148337595907928,
      "grad_norm": 2.658413887023926,
      "learning_rate": 1.6840011366865587e-05,
      "loss": 5.7619,
      "step": 950
    },
    {
      "epoch": 1.2468030690537084,
      "grad_norm": 1.2760388851165771,
      "learning_rate": 1.6697925547030408e-05,
      "loss": 5.8038,
      "step": 975
    },
    {
      "epoch": 1.278772378516624,
      "grad_norm": 1.7434897422790527,
      "learning_rate": 1.6555839727195226e-05,
      "loss": 5.779,
      "step": 1000
    },
    {
      "epoch": 1.3107416879795397,
      "grad_norm": 1.3532071113586426,
      "learning_rate": 1.6413753907360047e-05,
      "loss": 5.7904,
      "step": 1025
    },
    {
      "epoch": 1.3427109974424551,
      "grad_norm": 3.7385997772216797,
      "learning_rate": 1.6271668087524864e-05,
      "loss": 5.7696,
      "step": 1050
    },
    {
      "epoch": 1.3746803069053708,
      "grad_norm": 0.9061102867126465,
      "learning_rate": 1.6129582267689685e-05,
      "loss": 5.7919,
      "step": 1075
    },
    {
      "epoch": 1.4066496163682864,
      "grad_norm": 2.7104809284210205,
      "learning_rate": 1.5987496447854503e-05,
      "loss": 5.7785,
      "step": 1100
    },
    {
      "epoch": 1.438618925831202,
      "grad_norm": 1.7147830724716187,
      "learning_rate": 1.5845410628019324e-05,
      "loss": 5.7862,
      "step": 1125
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 2.525214672088623,
      "learning_rate": 1.5703324808184145e-05,
      "loss": 5.7703,
      "step": 1150
    },
    {
      "epoch": 1.5025575447570332,
      "grad_norm": 1.7794997692108154,
      "learning_rate": 1.5561238988348963e-05,
      "loss": 5.773,
      "step": 1175
    },
    {
      "epoch": 1.5345268542199488,
      "grad_norm": 4.901644229888916,
      "learning_rate": 1.5419153168513784e-05,
      "loss": 5.7627,
      "step": 1200
    },
    {
      "epoch": 1.5664961636828645,
      "grad_norm": 3.360812187194824,
      "learning_rate": 1.52770673486786e-05,
      "loss": 5.7596,
      "step": 1225
    },
    {
      "epoch": 1.59846547314578,
      "grad_norm": 1.2768888473510742,
      "learning_rate": 1.5134981528843423e-05,
      "loss": 5.7882,
      "step": 1250
    },
    {
      "epoch": 1.6304347826086958,
      "grad_norm": 2.206226348876953,
      "learning_rate": 1.4992895709008242e-05,
      "loss": 5.7828,
      "step": 1275
    },
    {
      "epoch": 1.6624040920716112,
      "grad_norm": 1.4602406024932861,
      "learning_rate": 1.4850809889173061e-05,
      "loss": 5.771,
      "step": 1300
    },
    {
      "epoch": 1.6943734015345269,
      "grad_norm": 1.1597537994384766,
      "learning_rate": 1.4708724069337881e-05,
      "loss": 5.788,
      "step": 1325
    },
    {
      "epoch": 1.7263427109974425,
      "grad_norm": 3.7494003772735596,
      "learning_rate": 1.45666382495027e-05,
      "loss": 5.7719,
      "step": 1350
    },
    {
      "epoch": 1.758312020460358,
      "grad_norm": 1.6271498203277588,
      "learning_rate": 1.442455242966752e-05,
      "loss": 5.7846,
      "step": 1375
    },
    {
      "epoch": 1.7902813299232738,
      "grad_norm": 2.0469117164611816,
      "learning_rate": 1.4282466609832339e-05,
      "loss": 5.7838,
      "step": 1400
    },
    {
      "epoch": 1.8222506393861893,
      "grad_norm": 2.533921003341675,
      "learning_rate": 1.4140380789997158e-05,
      "loss": 5.7912,
      "step": 1425
    },
    {
      "epoch": 1.854219948849105,
      "grad_norm": 3.291757583618164,
      "learning_rate": 1.3998294970161978e-05,
      "loss": 5.7686,
      "step": 1450
    },
    {
      "epoch": 1.8861892583120206,
      "grad_norm": 3.0181350708007812,
      "learning_rate": 1.3856209150326799e-05,
      "loss": 5.7938,
      "step": 1475
    },
    {
      "epoch": 1.918158567774936,
      "grad_norm": 2.553502321243286,
      "learning_rate": 1.3714123330491618e-05,
      "loss": 5.7847,
      "step": 1500
    },
    {
      "epoch": 1.9501278772378516,
      "grad_norm": 1.8034719228744507,
      "learning_rate": 1.3572037510656438e-05,
      "loss": 5.7952,
      "step": 1525
    },
    {
      "epoch": 1.9820971867007673,
      "grad_norm": 3.7138864994049072,
      "learning_rate": 1.3429951690821257e-05,
      "loss": 5.7528,
      "step": 1550
    },
    {
      "epoch": 2.0,
      "eval_loss": 5.793323516845703,
      "eval_runtime": 18.2796,
      "eval_samples_per_second": 273.528,
      "eval_steps_per_second": 4.322,
      "eval_tr_ling_pearson_cosine": 0.037604255015168134,
      "eval_tr_ling_pearson_dot": 0.0673696846368413,
      "eval_tr_ling_pearson_euclidean": 0.03698411306484619,
      "eval_tr_ling_pearson_manhattan": 0.034740275152181296,
      "eval_tr_ling_pearson_max": 0.0673696846368413,
      "eval_tr_ling_spearman_cosine": 0.04804112988506346,
      "eval_tr_ling_spearman_dot": 0.06818119362900125,
      "eval_tr_ling_spearman_euclidean": 0.03903062430281842,
      "eval_tr_ling_spearman_manhattan": 0.03769766156967754,
      "eval_tr_ling_spearman_max": 0.06818119362900125,
      "step": 1564
    }
  ],
  "logging_steps": 25,
  "max_steps": 3910,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "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": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}