Instructions to use splitner/spanclass-qa-crossentropy-wnut17 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use splitner/spanclass-qa-crossentropy-wnut17 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("splitner/spanclass-qa-crossentropy-wnut17") model = AutoModel.from_pretrained("splitner/spanclass-qa-crossentropy-wnut17", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from splitner/spanclass-qa-crossentropy-wnut17: direct link, hf CLI and curl.
- Browser
- Download file 63.3 kB
-
https://huggingface.co/splitner/spanclass-qa-crossentropy-wnut17/resolve/main/trainer_state.json
- Command line
-
hf download hf://splitner/spanclass-qa-crossentropy-wnut17/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/splitner/spanclass-qa-crossentropy-wnut17/resolve/main/trainer_state.json
63.3 kB
{
"best_metric": 0.8205741621784443,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/wnut/class/run-42/checkpoints/checkpoint-3000",
"epoch": 187.5,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.62,
"eval_loss": 1.6759881973266602,
"eval_micro_f1": 0.08851674591137737,
"eval_runtime": 1.3359,
"eval_samples_per_second": 625.794,
"step": 10
},
{
"epoch": 1.25,
"eval_loss": 1.5462044477462769,
"eval_micro_f1": 0.6052631573940128,
"eval_runtime": 1.2101,
"eval_samples_per_second": 690.875,
"step": 20
},
{
"epoch": 1.88,
"eval_loss": 1.3322491645812988,
"eval_micro_f1": 0.6244019133748512,
"eval_runtime": 0.8599,
"eval_samples_per_second": 972.239,
"step": 30
},
{
"epoch": 2.5,
"eval_loss": 1.1252518892288208,
"eval_micro_f1": 0.644736841604492,
"eval_runtime": 1.1837,
"eval_samples_per_second": 706.251,
"step": 40
},
{
"epoch": 3.12,
"eval_loss": 1.0135610103607178,
"eval_micro_f1": 0.6387559803604799,
"eval_runtime": 1.2916,
"eval_samples_per_second": 647.281,
"step": 50
},
{
"epoch": 3.75,
"eval_loss": 0.9341530203819275,
"eval_micro_f1": 0.6411483248580847,
"eval_runtime": 1.1548,
"eval_samples_per_second": 723.953,
"step": 60
},
{
"epoch": 4.38,
"eval_loss": 0.8877728581428528,
"eval_micro_f1": 0.644736841604492,
"eval_runtime": 1.2673,
"eval_samples_per_second": 659.646,
"step": 70
},
{
"epoch": 5.0,
"eval_loss": 0.8828455209732056,
"eval_micro_f1": 0.6459330138532943,
"eval_runtime": 0.8582,
"eval_samples_per_second": 974.142,
"step": 80
},
{
"epoch": 5.62,
"eval_loss": 0.887384295463562,
"eval_micro_f1": 0.6794258368197614,
"eval_runtime": 1.2161,
"eval_samples_per_second": 687.446,
"step": 90
},
{
"epoch": 6.25,
"eval_loss": 0.7980366945266724,
"eval_micro_f1": 0.7368421047622765,
"eval_runtime": 1.168,
"eval_samples_per_second": 715.781,
"step": 100
},
{
"epoch": 6.88,
"eval_loss": 0.7685986161231995,
"eval_micro_f1": 0.759569377489522,
"eval_runtime": 1.2908,
"eval_samples_per_second": 647.674,
"step": 110
},
{
"epoch": 7.5,
"eval_loss": 0.7412388324737549,
"eval_micro_f1": 0.7811004779679651,
"eval_runtime": 0.865,
"eval_samples_per_second": 966.496,
"step": 120
},
{
"epoch": 8.12,
"eval_loss": 0.736153781414032,
"eval_micro_f1": 0.777511961221558,
"eval_runtime": 0.8746,
"eval_samples_per_second": 955.819,
"step": 130
},
{
"epoch": 8.75,
"eval_loss": 0.741908848285675,
"eval_micro_f1": 0.7787081334703604,
"eval_runtime": 1.2436,
"eval_samples_per_second": 672.264,
"step": 140
},
{
"epoch": 9.38,
"eval_loss": 0.7110205888748169,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 4.1459,
"eval_samples_per_second": 201.643,
"step": 150
},
{
"epoch": 10.0,
"eval_loss": 0.743588387966156,
"eval_micro_f1": 0.7703349277287436,
"eval_runtime": 1.2283,
"eval_samples_per_second": 680.592,
"step": 160
},
{
"epoch": 10.62,
"eval_loss": 0.6968352198600769,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.1871,
"eval_samples_per_second": 704.248,
"step": 170
},
{
"epoch": 11.25,
"eval_loss": 0.7096373438835144,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 0.8786,
"eval_samples_per_second": 951.476,
"step": 180
},
{
"epoch": 11.88,
"eval_loss": 0.7048764228820801,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.3421,
"eval_samples_per_second": 622.892,
"step": 190
},
{
"epoch": 12.5,
"eval_loss": 0.7515257596969604,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.2546,
"eval_samples_per_second": 666.338,
"step": 200
},
{
"epoch": 13.12,
"eval_loss": 0.7905582785606384,
"eval_micro_f1": 0.7739234444751508,
"eval_runtime": 1.2206,
"eval_samples_per_second": 684.892,
"step": 210
},
{
"epoch": 13.75,
"eval_loss": 0.7019672393798828,
"eval_micro_f1": 0.8145933009344323,
"eval_runtime": 1.1469,
"eval_samples_per_second": 728.9,
"step": 220
},
{
"epoch": 14.38,
"eval_loss": 0.743220865726471,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 0.8806,
"eval_samples_per_second": 949.347,
"step": 230
},
{
"epoch": 15.0,
"eval_loss": 0.7914738059043884,
"eval_micro_f1": 0.7870813392119771,
"eval_runtime": 1.246,
"eval_samples_per_second": 670.957,
"step": 240
},
{
"epoch": 15.62,
"eval_loss": 0.8315173983573914,
"eval_micro_f1": 0.7799043057191627,
"eval_runtime": 1.621,
"eval_samples_per_second": 515.725,
"step": 250
},
{
"epoch": 16.25,
"eval_loss": 0.8176524043083191,
"eval_micro_f1": 0.7846889947143724,
"eval_runtime": 1.2095,
"eval_samples_per_second": 691.193,
"step": 260
},
{
"epoch": 16.88,
"eval_loss": 0.9075602889060974,
"eval_micro_f1": 0.771531099977546,
"eval_runtime": 1.2256,
"eval_samples_per_second": 682.12,
"step": 270
},
{
"epoch": 17.5,
"eval_loss": 0.8281694650650024,
"eval_micro_f1": 0.7954545449535938,
"eval_runtime": 0.8715,
"eval_samples_per_second": 959.275,
"step": 280
},
{
"epoch": 18.12,
"eval_loss": 0.8547766208648682,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 1.2407,
"eval_samples_per_second": 673.819,
"step": 290
},
{
"epoch": 18.75,
"eval_loss": 0.8972189426422119,
"eval_micro_f1": 0.7822966502167676,
"eval_runtime": 1.208,
"eval_samples_per_second": 692.055,
"step": 300
},
{
"epoch": 19.38,
"eval_loss": 0.9401060938835144,
"eval_micro_f1": 0.7787081334703604,
"eval_runtime": 1.1982,
"eval_samples_per_second": 697.732,
"step": 310
},
{
"epoch": 20.0,
"eval_loss": 0.9120603799819946,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2047,
"eval_samples_per_second": 693.932,
"step": 320
},
{
"epoch": 20.62,
"eval_loss": 0.920120358467102,
"eval_micro_f1": 0.7858851669631748,
"eval_runtime": 0.8725,
"eval_samples_per_second": 958.217,
"step": 330
},
{
"epoch": 21.25,
"eval_loss": 0.9525130987167358,
"eval_micro_f1": 0.771531099977546,
"eval_runtime": 1.1953,
"eval_samples_per_second": 699.415,
"step": 340
},
{
"epoch": 21.88,
"eval_loss": 0.9583889245986938,
"eval_micro_f1": 0.7858851669631748,
"eval_runtime": 1.2359,
"eval_samples_per_second": 676.414,
"step": 350
},
{
"epoch": 22.5,
"eval_loss": 1.0320873260498047,
"eval_micro_f1": 0.7739234444751508,
"eval_runtime": 1.1982,
"eval_samples_per_second": 697.705,
"step": 360
},
{
"epoch": 23.12,
"eval_loss": 0.9924129247665405,
"eval_micro_f1": 0.7751196167239531,
"eval_runtime": 1.2948,
"eval_samples_per_second": 645.665,
"step": 370
},
{
"epoch": 23.75,
"eval_loss": 0.919312059879303,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.2586,
"eval_samples_per_second": 664.256,
"step": 380
},
{
"epoch": 24.38,
"eval_loss": 1.0358171463012695,
"eval_micro_f1": 0.7751196167239531,
"eval_runtime": 1.2561,
"eval_samples_per_second": 665.549,
"step": 390
},
{
"epoch": 25.0,
"eval_loss": 1.0559030771255493,
"eval_micro_f1": 0.7787081334703604,
"eval_runtime": 1.2969,
"eval_samples_per_second": 644.633,
"step": 400
},
{
"epoch": 25.62,
"eval_loss": 0.9812420606613159,
"eval_micro_f1": 0.7870813392119771,
"eval_runtime": 1.2399,
"eval_samples_per_second": 674.266,
"step": 410
},
{
"epoch": 26.25,
"eval_loss": 1.0270429849624634,
"eval_micro_f1": 0.7799043057191627,
"eval_runtime": 1.332,
"eval_samples_per_second": 627.648,
"step": 420
},
{
"epoch": 26.88,
"eval_loss": 1.044345736503601,
"eval_micro_f1": 0.7894736837095819,
"eval_runtime": 1.2183,
"eval_samples_per_second": 686.179,
"step": 430
},
{
"epoch": 27.5,
"eval_loss": 1.0406349897384644,
"eval_micro_f1": 0.7846889947143724,
"eval_runtime": 0.8726,
"eval_samples_per_second": 958.035,
"step": 440
},
{
"epoch": 28.12,
"eval_loss": 0.9970749616622925,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.1767,
"eval_samples_per_second": 710.432,
"step": 450
},
{
"epoch": 28.75,
"eval_loss": 1.0192404985427856,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.1984,
"eval_samples_per_second": 697.599,
"step": 460
},
{
"epoch": 29.38,
"eval_loss": 1.1054484844207764,
"eval_micro_f1": 0.78349282246557,
"eval_runtime": 1.3117,
"eval_samples_per_second": 637.324,
"step": 470
},
{
"epoch": 30.0,
"eval_loss": 1.1029002666473389,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2415,
"eval_samples_per_second": 673.362,
"step": 480
},
{
"epoch": 30.62,
"eval_loss": 1.041625738143921,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.0809,
"eval_samples_per_second": 773.41,
"step": 490
},
{
"epoch": 31.25,
"learning_rate": 8.958333333333334e-06,
"loss": 0.3178,
"step": 500
},
{
"epoch": 31.25,
"eval_loss": 1.0797942876815796,
"eval_micro_f1": 0.7870813392119771,
"eval_runtime": 1.252,
"eval_samples_per_second": 667.722,
"step": 500
},
{
"epoch": 31.88,
"eval_loss": 1.1399964094161987,
"eval_micro_f1": 0.7846889947143724,
"eval_runtime": 1.1939,
"eval_samples_per_second": 700.251,
"step": 510
},
{
"epoch": 32.5,
"eval_loss": 1.1625529527664185,
"eval_micro_f1": 0.7739234444751508,
"eval_runtime": 1.2201,
"eval_samples_per_second": 685.212,
"step": 520
},
{
"epoch": 33.12,
"eval_loss": 1.104368805885315,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2001,
"eval_samples_per_second": 696.612,
"step": 530
},
{
"epoch": 33.75,
"eval_loss": 1.077760100364685,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 0.8761,
"eval_samples_per_second": 954.202,
"step": 540
},
{
"epoch": 34.38,
"eval_loss": 1.1734049320220947,
"eval_micro_f1": 0.7822966502167676,
"eval_runtime": 1.2138,
"eval_samples_per_second": 688.726,
"step": 550
},
{
"epoch": 35.0,
"eval_loss": 1.1793453693389893,
"eval_micro_f1": 0.78349282246557,
"eval_runtime": 1.5359,
"eval_samples_per_second": 544.292,
"step": 560
},
{
"epoch": 35.62,
"eval_loss": 1.1454592943191528,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2532,
"eval_samples_per_second": 667.093,
"step": 570
},
{
"epoch": 36.25,
"eval_loss": 1.1729267835617065,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2523,
"eval_samples_per_second": 667.549,
"step": 580
},
{
"epoch": 36.88,
"eval_loss": 1.1719892024993896,
"eval_micro_f1": 0.7906698559583843,
"eval_runtime": 3.7258,
"eval_samples_per_second": 224.381,
"step": 590
},
{
"epoch": 37.5,
"eval_loss": 1.1657602787017822,
"eval_micro_f1": 0.7930622004559891,
"eval_runtime": 1.2367,
"eval_samples_per_second": 675.991,
"step": 600
},
{
"epoch": 38.12,
"eval_loss": 1.1762133836746216,
"eval_micro_f1": 0.7858851669631748,
"eval_runtime": 1.223,
"eval_samples_per_second": 683.542,
"step": 610
},
{
"epoch": 38.75,
"eval_loss": 1.1761835813522339,
"eval_micro_f1": 0.7870813392119771,
"eval_runtime": 1.214,
"eval_samples_per_second": 688.657,
"step": 620
},
{
"epoch": 39.38,
"eval_loss": 1.1437163352966309,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.2096,
"eval_samples_per_second": 691.162,
"step": 630
},
{
"epoch": 40.0,
"eval_loss": 1.1287521123886108,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 0.8722,
"eval_samples_per_second": 958.491,
"step": 640
},
{
"epoch": 40.62,
"eval_loss": 1.1567052602767944,
"eval_micro_f1": 0.7906698559583843,
"eval_runtime": 1.1829,
"eval_samples_per_second": 706.74,
"step": 650
},
{
"epoch": 41.25,
"eval_loss": 1.1617976427078247,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 1.6636,
"eval_samples_per_second": 502.511,
"step": 660
},
{
"epoch": 41.88,
"eval_loss": 1.1672464609146118,
"eval_micro_f1": 0.7906698559583843,
"eval_runtime": 1.2985,
"eval_samples_per_second": 643.836,
"step": 670
},
{
"epoch": 42.5,
"eval_loss": 1.1712684631347656,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.1903,
"eval_samples_per_second": 702.367,
"step": 680
},
{
"epoch": 43.12,
"eval_loss": 1.1998251676559448,
"eval_micro_f1": 0.7930622004559891,
"eval_runtime": 0.8749,
"eval_samples_per_second": 955.576,
"step": 690
},
{
"epoch": 43.75,
"eval_loss": 1.1978861093521118,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 1.209,
"eval_samples_per_second": 691.482,
"step": 700
},
{
"epoch": 44.38,
"eval_loss": 1.2747777700424194,
"eval_micro_f1": 0.777511961221558,
"eval_runtime": 1.2446,
"eval_samples_per_second": 671.714,
"step": 710
},
{
"epoch": 45.0,
"eval_loss": 1.265109896659851,
"eval_micro_f1": 0.7727272722263484,
"eval_runtime": 1.3112,
"eval_samples_per_second": 637.588,
"step": 720
},
{
"epoch": 45.62,
"eval_loss": 1.2195650339126587,
"eval_micro_f1": 0.78349282246557,
"eval_runtime": 1.2682,
"eval_samples_per_second": 659.204,
"step": 730
},
{
"epoch": 46.25,
"eval_loss": 1.2457984685897827,
"eval_micro_f1": 0.7822966502167676,
"eval_runtime": 0.8903,
"eval_samples_per_second": 939.024,
"step": 740
},
{
"epoch": 46.88,
"eval_loss": 1.1744990348815918,
"eval_micro_f1": 0.7930622004559891,
"eval_runtime": 1.3358,
"eval_samples_per_second": 625.839,
"step": 750
},
{
"epoch": 47.5,
"eval_loss": 1.203239917755127,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 1.6763,
"eval_samples_per_second": 498.716,
"step": 760
},
{
"epoch": 48.12,
"eval_loss": 1.2865585088729858,
"eval_micro_f1": 0.78349282246557,
"eval_runtime": 1.2521,
"eval_samples_per_second": 667.703,
"step": 770
},
{
"epoch": 48.75,
"eval_loss": 1.279433012008667,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2416,
"eval_samples_per_second": 673.34,
"step": 780
},
{
"epoch": 49.38,
"eval_loss": 1.1663239002227783,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 0.8824,
"eval_samples_per_second": 947.447,
"step": 790
},
{
"epoch": 50.0,
"eval_loss": 1.2201182842254639,
"eval_micro_f1": 0.7858851669631748,
"eval_runtime": 1.209,
"eval_samples_per_second": 691.487,
"step": 800
},
{
"epoch": 50.62,
"eval_loss": 1.2731646299362183,
"eval_micro_f1": 0.7799043057191627,
"eval_runtime": 1.1798,
"eval_samples_per_second": 708.603,
"step": 810
},
{
"epoch": 51.25,
"eval_loss": 1.281266689300537,
"eval_micro_f1": 0.7870813392119771,
"eval_runtime": 1.2611,
"eval_samples_per_second": 662.933,
"step": 820
},
{
"epoch": 51.88,
"eval_loss": 1.2305707931518555,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.2303,
"eval_samples_per_second": 679.521,
"step": 830
},
{
"epoch": 52.5,
"eval_loss": 1.2005953788757324,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.8744,
"eval_samples_per_second": 956.054,
"step": 840
},
{
"epoch": 53.12,
"eval_loss": 1.1868442296981812,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2462,
"eval_samples_per_second": 670.838,
"step": 850
},
{
"epoch": 53.75,
"eval_loss": 1.1953299045562744,
"eval_micro_f1": 0.8122009564368274,
"eval_runtime": 1.2115,
"eval_samples_per_second": 690.074,
"step": 860
},
{
"epoch": 54.38,
"eval_loss": 1.2319210767745972,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.293,
"eval_samples_per_second": 646.538,
"step": 870
},
{
"epoch": 55.0,
"eval_loss": 1.2394708395004272,
"eval_micro_f1": 0.7894736837095819,
"eval_runtime": 1.2712,
"eval_samples_per_second": 657.649,
"step": 880
},
{
"epoch": 55.62,
"eval_loss": 1.2563230991363525,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 0.9917,
"eval_samples_per_second": 842.982,
"step": 890
},
{
"epoch": 56.25,
"eval_loss": 1.228058934211731,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2046,
"eval_samples_per_second": 693.995,
"step": 900
},
{
"epoch": 56.88,
"eval_loss": 1.1921310424804688,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.248,
"eval_samples_per_second": 669.888,
"step": 910
},
{
"epoch": 57.5,
"eval_loss": 1.2339122295379639,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.2206,
"eval_samples_per_second": 684.9,
"step": 920
},
{
"epoch": 58.12,
"eval_loss": 1.2367137670516968,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2785,
"eval_samples_per_second": 653.869,
"step": 930
},
{
"epoch": 58.75,
"eval_loss": 1.2339813709259033,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.0677,
"eval_samples_per_second": 782.976,
"step": 940
},
{
"epoch": 59.38,
"eval_loss": 1.211556077003479,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.2224,
"eval_samples_per_second": 683.888,
"step": 950
},
{
"epoch": 60.0,
"eval_loss": 1.232566475868225,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2448,
"eval_samples_per_second": 671.612,
"step": 960
},
{
"epoch": 60.62,
"eval_loss": 1.3279404640197754,
"eval_micro_f1": 0.7822966502167676,
"eval_runtime": 1.3157,
"eval_samples_per_second": 635.425,
"step": 970
},
{
"epoch": 61.25,
"eval_loss": 1.3272722959518433,
"eval_micro_f1": 0.7846889947143724,
"eval_runtime": 1.1899,
"eval_samples_per_second": 702.602,
"step": 980
},
{
"epoch": 61.88,
"eval_loss": 1.2583824396133423,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 0.879,
"eval_samples_per_second": 951.032,
"step": 990
},
{
"epoch": 62.5,
"learning_rate": 7.916666666666667e-06,
"loss": 0.0078,
"step": 1000
},
{
"epoch": 62.5,
"eval_loss": 1.1969189643859863,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.3096,
"eval_samples_per_second": 638.368,
"step": 1000
},
{
"epoch": 63.12,
"eval_loss": 1.1956655979156494,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.0962,
"eval_samples_per_second": 762.667,
"step": 1010
},
{
"epoch": 63.75,
"eval_loss": 1.2163807153701782,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.3787,
"eval_samples_per_second": 606.388,
"step": 1020
},
{
"epoch": 64.38,
"eval_loss": 1.210200309753418,
"eval_micro_f1": 0.8110047841880251,
"eval_runtime": 1.2665,
"eval_samples_per_second": 660.086,
"step": 1030
},
{
"epoch": 65.0,
"eval_loss": 1.2128517627716064,
"eval_micro_f1": 0.8110047841880251,
"eval_runtime": 1.2021,
"eval_samples_per_second": 695.431,
"step": 1040
},
{
"epoch": 65.62,
"eval_loss": 1.2162755727767944,
"eval_micro_f1": 0.8133971286856299,
"eval_runtime": 1.2565,
"eval_samples_per_second": 665.323,
"step": 1050
},
{
"epoch": 66.25,
"eval_loss": 1.2298272848129272,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.6232,
"eval_samples_per_second": 515.022,
"step": 1060
},
{
"epoch": 66.88,
"eval_loss": 1.2755159139633179,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2261,
"eval_samples_per_second": 681.813,
"step": 1070
},
{
"epoch": 67.5,
"eval_loss": 1.2912817001342773,
"eval_micro_f1": 0.7954545449535938,
"eval_runtime": 1.1591,
"eval_samples_per_second": 721.241,
"step": 1080
},
{
"epoch": 68.12,
"eval_loss": 1.3157159090042114,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.2387,
"eval_samples_per_second": 674.901,
"step": 1090
},
{
"epoch": 68.75,
"eval_loss": 1.3245816230773926,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.1908,
"eval_samples_per_second": 702.038,
"step": 1100
},
{
"epoch": 69.38,
"eval_loss": 1.3124953508377075,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.1483,
"eval_samples_per_second": 728.05,
"step": 1110
},
{
"epoch": 70.0,
"eval_loss": 1.3136175870895386,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2297,
"eval_samples_per_second": 679.856,
"step": 1120
},
{
"epoch": 70.62,
"eval_loss": 1.317233681678772,
"eval_micro_f1": 0.7954545449535938,
"eval_runtime": 1.2422,
"eval_samples_per_second": 673.009,
"step": 1130
},
{
"epoch": 71.25,
"eval_loss": 1.342434048652649,
"eval_micro_f1": 0.7930622004559891,
"eval_runtime": 1.2164,
"eval_samples_per_second": 687.252,
"step": 1140
},
{
"epoch": 71.88,
"eval_loss": 1.3436208963394165,
"eval_micro_f1": 0.7930622004559891,
"eval_runtime": 1.2786,
"eval_samples_per_second": 653.846,
"step": 1150
},
{
"epoch": 72.5,
"eval_loss": 1.338441252708435,
"eval_micro_f1": 0.7954545449535938,
"eval_runtime": 1.2159,
"eval_samples_per_second": 687.582,
"step": 1160
},
{
"epoch": 73.12,
"eval_loss": 1.3312480449676514,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.2921,
"eval_samples_per_second": 647.025,
"step": 1170
},
{
"epoch": 73.75,
"eval_loss": 1.3264278173446655,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 3.9896,
"eval_samples_per_second": 209.544,
"step": 1180
},
{
"epoch": 74.38,
"eval_loss": 1.3332304954528809,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.2124,
"eval_samples_per_second": 689.539,
"step": 1190
},
{
"epoch": 75.0,
"eval_loss": 1.2966439723968506,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 0.8752,
"eval_samples_per_second": 955.179,
"step": 1200
},
{
"epoch": 75.62,
"eval_loss": 1.2809137105941772,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.2334,
"eval_samples_per_second": 677.811,
"step": 1210
},
{
"epoch": 76.25,
"eval_loss": 1.2974853515625,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.233,
"eval_samples_per_second": 678.032,
"step": 1220
},
{
"epoch": 76.88,
"eval_loss": 1.310535192489624,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.2405,
"eval_samples_per_second": 673.936,
"step": 1230
},
{
"epoch": 77.5,
"eval_loss": 1.3318800926208496,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.2634,
"eval_samples_per_second": 661.702,
"step": 1240
},
{
"epoch": 78.12,
"eval_loss": 1.3147168159484863,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 0.8772,
"eval_samples_per_second": 953.073,
"step": 1250
},
{
"epoch": 78.75,
"eval_loss": 1.2976956367492676,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.264,
"eval_samples_per_second": 661.391,
"step": 1260
},
{
"epoch": 79.38,
"eval_loss": 1.3273509740829468,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2445,
"eval_samples_per_second": 671.777,
"step": 1270
},
{
"epoch": 80.0,
"eval_loss": 1.3371427059173584,
"eval_micro_f1": 0.7954545449535938,
"eval_runtime": 1.2894,
"eval_samples_per_second": 648.368,
"step": 1280
},
{
"epoch": 80.62,
"eval_loss": 1.327476143836975,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2422,
"eval_samples_per_second": 673.01,
"step": 1290
},
{
"epoch": 81.25,
"eval_loss": 1.3186708688735962,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 0.8785,
"eval_samples_per_second": 951.656,
"step": 1300
},
{
"epoch": 81.88,
"eval_loss": 1.332135796546936,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2523,
"eval_samples_per_second": 667.587,
"step": 1310
},
{
"epoch": 82.5,
"eval_loss": 1.318489909172058,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.2698,
"eval_samples_per_second": 658.368,
"step": 1320
},
{
"epoch": 83.12,
"eval_loss": 1.2983919382095337,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2359,
"eval_samples_per_second": 676.443,
"step": 1330
},
{
"epoch": 83.75,
"eval_loss": 1.291175365447998,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.1857,
"eval_samples_per_second": 705.057,
"step": 1340
},
{
"epoch": 84.38,
"eval_loss": 1.2960314750671387,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 0.8815,
"eval_samples_per_second": 948.384,
"step": 1350
},
{
"epoch": 85.0,
"eval_loss": 1.3666927814483643,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.2997,
"eval_samples_per_second": 643.203,
"step": 1360
},
{
"epoch": 85.62,
"eval_loss": 1.4970866441726685,
"eval_micro_f1": 0.7667464109823364,
"eval_runtime": 1.2654,
"eval_samples_per_second": 660.663,
"step": 1370
},
{
"epoch": 86.25,
"eval_loss": 1.5397878885269165,
"eval_micro_f1": 0.7643540664847316,
"eval_runtime": 1.1787,
"eval_samples_per_second": 709.241,
"step": 1380
},
{
"epoch": 86.88,
"eval_loss": 1.39130437374115,
"eval_micro_f1": 0.7906698559583843,
"eval_runtime": 1.2669,
"eval_samples_per_second": 659.895,
"step": 1390
},
{
"epoch": 87.5,
"eval_loss": 1.2624567747116089,
"eval_micro_f1": 0.8122009564368274,
"eval_runtime": 0.8738,
"eval_samples_per_second": 956.757,
"step": 1400
},
{
"epoch": 88.12,
"eval_loss": 1.2743109464645386,
"eval_micro_f1": 0.8110047841880251,
"eval_runtime": 1.284,
"eval_samples_per_second": 651.102,
"step": 1410
},
{
"epoch": 88.75,
"eval_loss": 1.2854809761047363,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2065,
"eval_samples_per_second": 692.911,
"step": 1420
},
{
"epoch": 89.38,
"eval_loss": 1.327154278755188,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.1934,
"eval_samples_per_second": 700.519,
"step": 1430
},
{
"epoch": 90.0,
"eval_loss": 1.3507665395736694,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2239,
"eval_samples_per_second": 683.074,
"step": 1440
},
{
"epoch": 90.62,
"eval_loss": 1.2883785963058472,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 0.8728,
"eval_samples_per_second": 957.881,
"step": 1450
},
{
"epoch": 91.25,
"eval_loss": 1.2497007846832275,
"eval_micro_f1": 0.8122009564368274,
"eval_runtime": 1.3123,
"eval_samples_per_second": 637.046,
"step": 1460
},
{
"epoch": 91.88,
"eval_loss": 1.2521108388900757,
"eval_micro_f1": 0.8145933009344323,
"eval_runtime": 1.1754,
"eval_samples_per_second": 711.23,
"step": 1470
},
{
"epoch": 92.5,
"eval_loss": 1.2865349054336548,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.2551,
"eval_samples_per_second": 666.106,
"step": 1480
},
{
"epoch": 93.12,
"eval_loss": 1.3087444305419922,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.1018,
"eval_samples_per_second": 758.737,
"step": 1490
},
{
"epoch": 93.75,
"learning_rate": 6.875e-06,
"loss": 0.0051,
"step": 1500
},
{
"epoch": 93.75,
"eval_loss": 1.3142979145050049,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 0.8803,
"eval_samples_per_second": 949.724,
"step": 1500
},
{
"epoch": 94.38,
"eval_loss": 1.2547414302825928,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.2904,
"eval_samples_per_second": 647.886,
"step": 1510
},
{
"epoch": 95.0,
"eval_loss": 1.2591632604599,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2169,
"eval_samples_per_second": 687.019,
"step": 1520
},
{
"epoch": 95.62,
"eval_loss": 1.2607752084732056,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2989,
"eval_samples_per_second": 643.606,
"step": 1530
},
{
"epoch": 96.25,
"eval_loss": 1.292096734046936,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.2125,
"eval_samples_per_second": 689.47,
"step": 1540
},
{
"epoch": 96.88,
"eval_loss": 1.3454042673110962,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.4007,
"eval_samples_per_second": 596.855,
"step": 1550
},
{
"epoch": 97.5,
"eval_loss": 1.3864357471466064,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.2241,
"eval_samples_per_second": 682.938,
"step": 1560
},
{
"epoch": 98.12,
"eval_loss": 1.3908559083938599,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.3369,
"eval_samples_per_second": 625.31,
"step": 1570
},
{
"epoch": 98.75,
"eval_loss": 1.4005109071731567,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.2554,
"eval_samples_per_second": 665.924,
"step": 1580
},
{
"epoch": 99.38,
"eval_loss": 1.391554832458496,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2244,
"eval_samples_per_second": 682.765,
"step": 1590
},
{
"epoch": 100.0,
"eval_loss": 1.3920481204986572,
"eval_micro_f1": 0.7954545449535938,
"eval_runtime": 0.8815,
"eval_samples_per_second": 948.377,
"step": 1600
},
{
"epoch": 100.62,
"eval_loss": 1.3875278234481812,
"eval_micro_f1": 0.7930622004559891,
"eval_runtime": 1.2232,
"eval_samples_per_second": 683.451,
"step": 1610
},
{
"epoch": 101.25,
"eval_loss": 1.4043912887573242,
"eval_micro_f1": 0.7894736837095819,
"eval_runtime": 1.1326,
"eval_samples_per_second": 738.143,
"step": 1620
},
{
"epoch": 101.88,
"eval_loss": 1.4151456356048584,
"eval_micro_f1": 0.7894736837095819,
"eval_runtime": 1.3225,
"eval_samples_per_second": 632.123,
"step": 1630
},
{
"epoch": 102.5,
"eval_loss": 1.4104795455932617,
"eval_micro_f1": 0.7906698559583843,
"eval_runtime": 1.2042,
"eval_samples_per_second": 694.229,
"step": 1640
},
{
"epoch": 103.12,
"eval_loss": 1.375184178352356,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.1911,
"eval_samples_per_second": 701.874,
"step": 1650
},
{
"epoch": 103.75,
"eval_loss": 1.3621584177017212,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2147,
"eval_samples_per_second": 688.226,
"step": 1660
},
{
"epoch": 104.38,
"eval_loss": 1.3727388381958008,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.209,
"eval_samples_per_second": 691.473,
"step": 1670
},
{
"epoch": 105.0,
"eval_loss": 1.380932331085205,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.2641,
"eval_samples_per_second": 661.316,
"step": 1680
},
{
"epoch": 105.62,
"eval_loss": 1.3932331800460815,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2238,
"eval_samples_per_second": 683.116,
"step": 1690
},
{
"epoch": 106.25,
"eval_loss": 1.3928004503250122,
"eval_micro_f1": 0.7966507172023963,
"eval_runtime": 1.1965,
"eval_samples_per_second": 698.711,
"step": 1700
},
{
"epoch": 106.88,
"eval_loss": 1.3964753150939941,
"eval_micro_f1": 0.7954545449535938,
"eval_runtime": 0.8771,
"eval_samples_per_second": 953.152,
"step": 1710
},
{
"epoch": 107.5,
"eval_loss": 1.386148452758789,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.2205,
"eval_samples_per_second": 684.952,
"step": 1720
},
{
"epoch": 108.12,
"eval_loss": 1.3845064640045166,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.2444,
"eval_samples_per_second": 671.803,
"step": 1730
},
{
"epoch": 108.75,
"eval_loss": 1.3763731718063354,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.3141,
"eval_samples_per_second": 636.162,
"step": 1740
},
{
"epoch": 109.38,
"eval_loss": 1.377465844154358,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.2303,
"eval_samples_per_second": 679.51,
"step": 1750
},
{
"epoch": 110.0,
"eval_loss": 1.3758480548858643,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 0.8807,
"eval_samples_per_second": 949.229,
"step": 1760
},
{
"epoch": 110.62,
"eval_loss": 1.3523021936416626,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.5753,
"eval_samples_per_second": 530.681,
"step": 1770
},
{
"epoch": 111.25,
"eval_loss": 1.3379099369049072,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2925,
"eval_samples_per_second": 646.831,
"step": 1780
},
{
"epoch": 111.88,
"eval_loss": 1.3364219665527344,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.2079,
"eval_samples_per_second": 692.136,
"step": 1790
},
{
"epoch": 112.5,
"eval_loss": 1.3755286931991577,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.242,
"eval_samples_per_second": 673.103,
"step": 1800
},
{
"epoch": 113.12,
"eval_loss": 1.3941314220428467,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 0.8774,
"eval_samples_per_second": 952.794,
"step": 1810
},
{
"epoch": 113.75,
"eval_loss": 1.3608207702636719,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.225,
"eval_samples_per_second": 682.462,
"step": 1820
},
{
"epoch": 114.38,
"eval_loss": 1.363614797592163,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.2034,
"eval_samples_per_second": 694.715,
"step": 1830
},
{
"epoch": 115.0,
"eval_loss": 1.3695135116577148,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2559,
"eval_samples_per_second": 665.647,
"step": 1840
},
{
"epoch": 115.62,
"eval_loss": 1.3885483741760254,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.2092,
"eval_samples_per_second": 691.391,
"step": 1850
},
{
"epoch": 116.25,
"eval_loss": 1.3952767848968506,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.8801,
"eval_samples_per_second": 949.859,
"step": 1860
},
{
"epoch": 116.88,
"eval_loss": 1.4006528854370117,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2331,
"eval_samples_per_second": 677.969,
"step": 1870
},
{
"epoch": 117.5,
"eval_loss": 1.4018462896347046,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.214,
"eval_samples_per_second": 688.636,
"step": 1880
},
{
"epoch": 118.12,
"eval_loss": 1.3956125974655151,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2698,
"eval_samples_per_second": 658.395,
"step": 1890
},
{
"epoch": 118.75,
"eval_loss": 1.399295449256897,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.1873,
"eval_samples_per_second": 704.098,
"step": 1900
},
{
"epoch": 119.38,
"eval_loss": 1.3782769441604614,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 0.8736,
"eval_samples_per_second": 957.009,
"step": 1910
},
{
"epoch": 120.0,
"eval_loss": 1.3840773105621338,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.3233,
"eval_samples_per_second": 631.744,
"step": 1920
},
{
"epoch": 120.62,
"eval_loss": 1.3932669162750244,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.1049,
"eval_samples_per_second": 756.626,
"step": 1930
},
{
"epoch": 121.25,
"eval_loss": 1.4053575992584229,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2271,
"eval_samples_per_second": 681.275,
"step": 1940
},
{
"epoch": 121.88,
"eval_loss": 1.4166978597640991,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 1.2483,
"eval_samples_per_second": 669.695,
"step": 1950
},
{
"epoch": 122.5,
"eval_loss": 1.4135366678237915,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 0.8725,
"eval_samples_per_second": 958.127,
"step": 1960
},
{
"epoch": 123.12,
"eval_loss": 1.4139994382858276,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.2175,
"eval_samples_per_second": 686.667,
"step": 1970
},
{
"epoch": 123.75,
"eval_loss": 1.4165161848068237,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.3362,
"eval_samples_per_second": 625.641,
"step": 1980
},
{
"epoch": 124.38,
"eval_loss": 1.40915846824646,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2142,
"eval_samples_per_second": 688.537,
"step": 1990
},
{
"epoch": 125.0,
"learning_rate": 5.833333333333334e-06,
"loss": 0.0044,
"step": 2000
},
{
"epoch": 125.0,
"eval_loss": 1.4081146717071533,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2318,
"eval_samples_per_second": 678.656,
"step": 2000
},
{
"epoch": 125.62,
"eval_loss": 1.4219191074371338,
"eval_micro_f1": 0.7990430617000013,
"eval_runtime": 0.8813,
"eval_samples_per_second": 948.645,
"step": 2010
},
{
"epoch": 126.25,
"eval_loss": 1.3743187189102173,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2439,
"eval_samples_per_second": 672.106,
"step": 2020
},
{
"epoch": 126.88,
"eval_loss": 1.362810492515564,
"eval_micro_f1": 0.8145933009344323,
"eval_runtime": 1.1987,
"eval_samples_per_second": 697.407,
"step": 2030
},
{
"epoch": 127.5,
"eval_loss": 1.3660919666290283,
"eval_micro_f1": 0.8110047841880251,
"eval_runtime": 1.2816,
"eval_samples_per_second": 652.291,
"step": 2040
},
{
"epoch": 128.12,
"eval_loss": 1.3641290664672852,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.225,
"eval_samples_per_second": 682.466,
"step": 2050
},
{
"epoch": 128.75,
"eval_loss": 1.3647525310516357,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.2187,
"eval_samples_per_second": 685.983,
"step": 2060
},
{
"epoch": 129.38,
"eval_loss": 1.360830307006836,
"eval_micro_f1": 0.8133971286856299,
"eval_runtime": 1.2278,
"eval_samples_per_second": 680.892,
"step": 2070
},
{
"epoch": 130.0,
"eval_loss": 1.3614624738693237,
"eval_micro_f1": 0.8122009564368274,
"eval_runtime": 1.2841,
"eval_samples_per_second": 651.062,
"step": 2080
},
{
"epoch": 130.62,
"eval_loss": 1.3574117422103882,
"eval_micro_f1": 0.8122009564368274,
"eval_runtime": 1.7015,
"eval_samples_per_second": 491.32,
"step": 2090
},
{
"epoch": 131.25,
"eval_loss": 1.374392032623291,
"eval_micro_f1": 0.8122009564368274,
"eval_runtime": 1.2828,
"eval_samples_per_second": 651.707,
"step": 2100
},
{
"epoch": 131.88,
"eval_loss": 1.382655143737793,
"eval_micro_f1": 0.8122009564368274,
"eval_runtime": 1.1275,
"eval_samples_per_second": 741.461,
"step": 2110
},
{
"epoch": 132.5,
"eval_loss": 1.3805127143859863,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 0.8758,
"eval_samples_per_second": 954.57,
"step": 2120
},
{
"epoch": 133.12,
"eval_loss": 1.375221848487854,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2774,
"eval_samples_per_second": 654.464,
"step": 2130
},
{
"epoch": 133.75,
"eval_loss": 1.402666449546814,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2807,
"eval_samples_per_second": 652.791,
"step": 2140
},
{
"epoch": 134.38,
"eval_loss": 1.459406852722168,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 1.2372,
"eval_samples_per_second": 675.744,
"step": 2150
},
{
"epoch": 135.0,
"eval_loss": 1.4087191820144653,
"eval_micro_f1": 0.7978468894511987,
"eval_runtime": 1.1993,
"eval_samples_per_second": 697.101,
"step": 2160
},
{
"epoch": 135.62,
"eval_loss": 1.3900821208953857,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.879,
"eval_samples_per_second": 951.107,
"step": 2170
},
{
"epoch": 136.25,
"eval_loss": 1.3888801336288452,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2747,
"eval_samples_per_second": 655.835,
"step": 2180
},
{
"epoch": 136.88,
"eval_loss": 1.3903478384017944,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.6856,
"eval_samples_per_second": 495.974,
"step": 2190
},
{
"epoch": 137.5,
"eval_loss": 1.416823387145996,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2675,
"eval_samples_per_second": 659.555,
"step": 2200
},
{
"epoch": 138.12,
"eval_loss": 1.4222781658172607,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.22,
"eval_samples_per_second": 685.227,
"step": 2210
},
{
"epoch": 138.75,
"eval_loss": 1.4133540391921997,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 0.8706,
"eval_samples_per_second": 960.266,
"step": 2220
},
{
"epoch": 139.38,
"eval_loss": 1.426302194595337,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.1725,
"eval_samples_per_second": 713.02,
"step": 2230
},
{
"epoch": 140.0,
"eval_loss": 1.486598014831543,
"eval_micro_f1": 0.7942583727047915,
"eval_runtime": 1.1361,
"eval_samples_per_second": 735.872,
"step": 2240
},
{
"epoch": 140.62,
"eval_loss": 1.4972662925720215,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 1.2368,
"eval_samples_per_second": 675.944,
"step": 2250
},
{
"epoch": 141.25,
"eval_loss": 1.5124529600143433,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.324,
"eval_samples_per_second": 631.433,
"step": 2260
},
{
"epoch": 141.88,
"eval_loss": 1.5166574716567993,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 0.9232,
"eval_samples_per_second": 905.575,
"step": 2270
},
{
"epoch": 142.5,
"eval_loss": 1.5198700428009033,
"eval_micro_f1": 0.7882775114607795,
"eval_runtime": 1.2257,
"eval_samples_per_second": 682.035,
"step": 2280
},
{
"epoch": 143.12,
"eval_loss": 1.506667137145996,
"eval_micro_f1": 0.7894736837095819,
"eval_runtime": 1.2551,
"eval_samples_per_second": 666.058,
"step": 2290
},
{
"epoch": 143.75,
"eval_loss": 1.353083610534668,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2243,
"eval_samples_per_second": 682.853,
"step": 2300
},
{
"epoch": 144.38,
"eval_loss": 1.3727068901062012,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.1611,
"eval_samples_per_second": 720.002,
"step": 2310
},
{
"epoch": 145.0,
"eval_loss": 1.3860739469528198,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.3389,
"eval_samples_per_second": 624.39,
"step": 2320
},
{
"epoch": 145.62,
"eval_loss": 1.3961546421051025,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.2503,
"eval_samples_per_second": 668.664,
"step": 2330
},
{
"epoch": 146.25,
"eval_loss": 1.398186206817627,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2663,
"eval_samples_per_second": 660.17,
"step": 2340
},
{
"epoch": 146.88,
"eval_loss": 1.3962750434875488,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.2418,
"eval_samples_per_second": 673.193,
"step": 2350
},
{
"epoch": 147.5,
"eval_loss": 1.4075311422348022,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2555,
"eval_samples_per_second": 665.849,
"step": 2360
},
{
"epoch": 148.12,
"eval_loss": 1.4148565530776978,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.1998,
"eval_samples_per_second": 696.769,
"step": 2370
},
{
"epoch": 148.75,
"eval_loss": 1.424800157546997,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.8731,
"eval_samples_per_second": 957.508,
"step": 2380
},
{
"epoch": 149.38,
"eval_loss": 1.417323112487793,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.2438,
"eval_samples_per_second": 672.156,
"step": 2390
},
{
"epoch": 150.0,
"eval_loss": 1.4144436120986938,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.2261,
"eval_samples_per_second": 681.846,
"step": 2400
},
{
"epoch": 150.62,
"eval_loss": 1.4174091815948486,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.2274,
"eval_samples_per_second": 681.14,
"step": 2410
},
{
"epoch": 151.25,
"eval_loss": 1.413324236869812,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.2046,
"eval_samples_per_second": 694.0,
"step": 2420
},
{
"epoch": 151.88,
"eval_loss": 1.4170891046524048,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 0.872,
"eval_samples_per_second": 958.689,
"step": 2430
},
{
"epoch": 152.5,
"eval_loss": 1.4190303087234497,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2273,
"eval_samples_per_second": 681.156,
"step": 2440
},
{
"epoch": 153.12,
"eval_loss": 1.4272630214691162,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2724,
"eval_samples_per_second": 657.001,
"step": 2450
},
{
"epoch": 153.75,
"eval_loss": 1.429481029510498,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.264,
"eval_samples_per_second": 661.394,
"step": 2460
},
{
"epoch": 154.38,
"eval_loss": 1.4257972240447998,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.1744,
"eval_samples_per_second": 711.853,
"step": 2470
},
{
"epoch": 155.0,
"eval_loss": 1.4273958206176758,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.8805,
"eval_samples_per_second": 949.424,
"step": 2480
},
{
"epoch": 155.62,
"eval_loss": 1.4307893514633179,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2578,
"eval_samples_per_second": 664.629,
"step": 2490
},
{
"epoch": 156.25,
"learning_rate": 4.791666666666668e-06,
"loss": 0.0042,
"step": 2500
},
{
"epoch": 156.25,
"eval_loss": 1.4220995903015137,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2821,
"eval_samples_per_second": 652.047,
"step": 2500
},
{
"epoch": 156.88,
"eval_loss": 1.4195088148117065,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2563,
"eval_samples_per_second": 665.428,
"step": 2510
},
{
"epoch": 157.5,
"eval_loss": 1.4252077341079712,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.3978,
"eval_samples_per_second": 598.091,
"step": 2520
},
{
"epoch": 158.12,
"eval_loss": 1.428691029548645,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.8787,
"eval_samples_per_second": 951.381,
"step": 2530
},
{
"epoch": 158.75,
"eval_loss": 1.4256610870361328,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2302,
"eval_samples_per_second": 679.563,
"step": 2540
},
{
"epoch": 159.38,
"eval_loss": 1.4328128099441528,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2704,
"eval_samples_per_second": 658.068,
"step": 2550
},
{
"epoch": 160.0,
"eval_loss": 1.4293843507766724,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.2275,
"eval_samples_per_second": 681.075,
"step": 2560
},
{
"epoch": 160.62,
"eval_loss": 1.4297587871551514,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.8781,
"eval_samples_per_second": 952.051,
"step": 2570
},
{
"epoch": 161.25,
"eval_loss": 1.4381576776504517,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 0.8794,
"eval_samples_per_second": 950.628,
"step": 2580
},
{
"epoch": 161.88,
"eval_loss": 1.439926266670227,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.3552,
"eval_samples_per_second": 616.906,
"step": 2590
},
{
"epoch": 162.5,
"eval_loss": 1.4571921825408936,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.2667,
"eval_samples_per_second": 660.002,
"step": 2600
},
{
"epoch": 163.12,
"eval_loss": 1.4617875814437866,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.24,
"eval_samples_per_second": 674.215,
"step": 2610
},
{
"epoch": 163.75,
"eval_loss": 1.4595539569854736,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.1716,
"eval_samples_per_second": 713.53,
"step": 2620
},
{
"epoch": 164.38,
"eval_loss": 1.4529329538345337,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.0252,
"eval_samples_per_second": 815.48,
"step": 2630
},
{
"epoch": 165.0,
"eval_loss": 1.4418772459030151,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.1928,
"eval_samples_per_second": 700.888,
"step": 2640
},
{
"epoch": 165.62,
"eval_loss": 1.4406232833862305,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2626,
"eval_samples_per_second": 662.129,
"step": 2650
},
{
"epoch": 166.25,
"eval_loss": 1.4389880895614624,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2098,
"eval_samples_per_second": 691.045,
"step": 2660
},
{
"epoch": 166.88,
"eval_loss": 1.4397320747375488,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2381,
"eval_samples_per_second": 675.232,
"step": 2670
},
{
"epoch": 167.5,
"eval_loss": 1.4551808834075928,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2946,
"eval_samples_per_second": 645.758,
"step": 2680
},
{
"epoch": 168.12,
"eval_loss": 1.4501805305480957,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.2067,
"eval_samples_per_second": 692.798,
"step": 2690
},
{
"epoch": 168.75,
"eval_loss": 1.4495714902877808,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2244,
"eval_samples_per_second": 682.775,
"step": 2700
},
{
"epoch": 169.38,
"eval_loss": 1.4503188133239746,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 1.3433,
"eval_samples_per_second": 622.326,
"step": 2710
},
{
"epoch": 170.0,
"eval_loss": 1.4485152959823608,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.2481,
"eval_samples_per_second": 669.796,
"step": 2720
},
{
"epoch": 170.62,
"eval_loss": 1.4404151439666748,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.1977,
"eval_samples_per_second": 698.008,
"step": 2730
},
{
"epoch": 171.25,
"eval_loss": 1.4550838470458984,
"eval_micro_f1": 0.8026315784464082,
"eval_runtime": 1.264,
"eval_samples_per_second": 661.391,
"step": 2740
},
{
"epoch": 171.88,
"eval_loss": 1.4467554092407227,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.216,
"eval_samples_per_second": 687.528,
"step": 2750
},
{
"epoch": 172.5,
"eval_loss": 1.4552243947982788,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.2435,
"eval_samples_per_second": 672.314,
"step": 2760
},
{
"epoch": 173.12,
"eval_loss": 1.456278920173645,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.2556,
"eval_samples_per_second": 665.823,
"step": 2770
},
{
"epoch": 173.75,
"eval_loss": 1.4586423635482788,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.1702,
"eval_samples_per_second": 714.398,
"step": 2780
},
{
"epoch": 174.38,
"eval_loss": 1.4615603685379028,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.2023,
"eval_samples_per_second": 695.339,
"step": 2790
},
{
"epoch": 175.0,
"eval_loss": 1.4521640539169312,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.1678,
"eval_samples_per_second": 715.881,
"step": 2800
},
{
"epoch": 175.62,
"eval_loss": 1.459039330482483,
"eval_micro_f1": 0.8110047841880251,
"eval_runtime": 1.3223,
"eval_samples_per_second": 632.225,
"step": 2810
},
{
"epoch": 176.25,
"eval_loss": 1.4770715236663818,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.5915,
"eval_samples_per_second": 525.283,
"step": 2820
},
{
"epoch": 176.88,
"eval_loss": 1.4787960052490234,
"eval_micro_f1": 0.8038277506952107,
"eval_runtime": 0.9666,
"eval_samples_per_second": 864.913,
"step": 2830
},
{
"epoch": 177.5,
"eval_loss": 1.4933847188949585,
"eval_micro_f1": 0.8002392339488035,
"eval_runtime": 1.1953,
"eval_samples_per_second": 699.427,
"step": 2840
},
{
"epoch": 178.12,
"eval_loss": 1.4820541143417358,
"eval_micro_f1": 0.801435406197606,
"eval_runtime": 1.2387,
"eval_samples_per_second": 674.92,
"step": 2850
},
{
"epoch": 178.75,
"eval_loss": 1.4721782207489014,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2678,
"eval_samples_per_second": 659.39,
"step": 2860
},
{
"epoch": 179.38,
"eval_loss": 1.4754302501678467,
"eval_micro_f1": 0.805023922944013,
"eval_runtime": 1.2891,
"eval_samples_per_second": 648.51,
"step": 2870
},
{
"epoch": 180.0,
"eval_loss": 1.4293739795684814,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.2496,
"eval_samples_per_second": 668.995,
"step": 2880
},
{
"epoch": 180.62,
"eval_loss": 1.4377115964889526,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.2049,
"eval_samples_per_second": 693.81,
"step": 2890
},
{
"epoch": 181.25,
"eval_loss": 1.4376572370529175,
"eval_micro_f1": 0.8098086119392227,
"eval_runtime": 1.2023,
"eval_samples_per_second": 695.357,
"step": 2900
},
{
"epoch": 181.88,
"eval_loss": 1.4372467994689941,
"eval_micro_f1": 0.8074162674416179,
"eval_runtime": 1.2237,
"eval_samples_per_second": 683.176,
"step": 2910
},
{
"epoch": 182.5,
"eval_loss": 1.442883014678955,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.6226,
"eval_samples_per_second": 515.219,
"step": 2920
},
{
"epoch": 183.12,
"eval_loss": 1.531345248222351,
"eval_micro_f1": 0.7918660282071867,
"eval_runtime": 1.2097,
"eval_samples_per_second": 691.06,
"step": 2930
},
{
"epoch": 183.75,
"eval_loss": 1.5837615728378296,
"eval_micro_f1": 0.7858851669631748,
"eval_runtime": 0.8758,
"eval_samples_per_second": 954.581,
"step": 2940
},
{
"epoch": 184.38,
"eval_loss": 1.5461186170578003,
"eval_micro_f1": 0.7906698559583843,
"eval_runtime": 0.9708,
"eval_samples_per_second": 861.124,
"step": 2950
},
{
"epoch": 185.0,
"eval_loss": 1.4445397853851318,
"eval_micro_f1": 0.8086124396904203,
"eval_runtime": 1.1505,
"eval_samples_per_second": 726.643,
"step": 2960
},
{
"epoch": 185.62,
"eval_loss": 1.4366849660873413,
"eval_micro_f1": 0.8062200951928155,
"eval_runtime": 1.2172,
"eval_samples_per_second": 686.81,
"step": 2970
},
{
"epoch": 186.25,
"eval_loss": 1.4100123643875122,
"eval_micro_f1": 0.8169856454320371,
"eval_runtime": 1.3528,
"eval_samples_per_second": 617.955,
"step": 2980
},
{
"epoch": 186.88,
"eval_loss": 1.415737271308899,
"eval_micro_f1": 0.8110047841880251,
"eval_runtime": 1.3206,
"eval_samples_per_second": 633.03,
"step": 2990
},
{
"epoch": 187.5,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0037,
"step": 3000
},
{
"epoch": 187.5,
"eval_loss": 1.4148428440093994,
"eval_micro_f1": 0.8205741621784443,
"eval_runtime": 1.3405,
"eval_samples_per_second": 623.635,
"step": 3000
}
],
"max_steps": 4800,
"num_train_epochs": 300,
"total_flos": 17832540398972616,
"trial_name": null,
"trial_params": null
}
{
"best_metric": 0.8205741621784443,
"best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/wnut/class/run-42/checkpoints/checkpoint-3000",
"epoch": 187.5,
"global_step": 3000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.62,
"eval_loss": 1.6759881973266602,
"eval_micro_f1": 0.08851674591137737,
"eval_runtime": 1.3359,
"eval_samples_per_second": 625.794,
"step": 10
},
{
"epoch": 1.25,
"eval_loss": 1.5462044477462769,
"eval_micro_f1": 0.6052631573940128,
"eval_runtime": 1.2101,
"eval_samples_per_second": 690.875,
"step": 20
},
{
"epoch": 1.88,
"eval_loss": 1.3322491645812988,
"eval_micro_f1": 0.6244019133748512,
"eval_runtime": 0.8599,
"eval_samples_per_second": 972.239,
"step": 30
},
{
"epoch": 2.5,
"eval_loss": 1.1252518892288208,
"eval_micro_f1": 0.644736841604492,
"eval_runtime": 1.1837,
"eval_samples_per_second": 706.251,
"step": 40
},
{
"epoch": 3.12,
"eval_loss": 1.0135610103607178,
"eval_micro_f1": 0.6387559803604799,
"eval_runtime": 1.2916,
"eval_samples_per_second": 647.281,
"step": 50
},
{
"epoch": 3.75,
"eval_loss": 0.9341530203819275,
"eval_micro_f1": 0.6411483248580847,
"eval_runtime": 1.1548,
"eval_samples_per_second": 723.953,
"step": 60
},
{
"epoch": 4.38,
"eval_loss": 0.8877728581428528,
"eval_micro_f1": 0.644736841604492,
"eval_runtime": 1.2673,
"eval_samples_per_second": 659.646,
"step": 70
},
{
"epoch": 5.0,
"eval_loss": 0.8828455209732056,
"eval_micro_f1": 0.6459330138532943,
"eval_runtime": 0.8582,
"eval_samples_per_second": 974.142,
"step": 80
},
{
"epoch": 5.62,
"eval_loss": 0.887384295463562,
"eval_micro_f1": 0.6794258368197614,
"eval_runtime": 1.2161,
"eval_samples_per_second": 687.446,
"step": 90
},
{
"epoch": 6.25,
"eval_loss": 0.7980366945266724,
"eval_micro_f1": 0.7368421047622765,
"eval_runtime": 1.168,
"eval_samples_per_second": 715.781,
"step": 100
},
{
"epoch": 6.88,
"eval_loss": 0.7685986161231995,
"eval_micro_f1": 0.759569377489522,
"eval_runtime": 1.2908,
"eval_samples_per_second": 647.674,
"step": 110
},
{
"epoch": 7.5,
"eval_loss": 0.7412388324737549,