Instructions to use splitner/single-seqtag-ontonotes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use splitner/single-seqtag-ontonotes with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("splitner/single-seqtag-ontonotes") model = AutoModel.from_pretrained("splitner/single-seqtag-ontonotes", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from splitner/single-seqtag-ontonotes: direct link, hf CLI and curl.
- Browser
- Download file 83.9 kB
-
https://huggingface.co/splitner/single-seqtag-ontonotes/resolve/refs%2Fpr%2F1/trainer_state.json
- Command line
-
hf download hf://splitner/single-seqtag-ontonotes@refs/pr/1/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/splitner/single-seqtag-ontonotes/resolve/refs%2Fpr%2F1/trainer_state.json
83.9 kB
{
"best_metric": 0.8688495092597597,
"best_model_checkpoint": "../out/onto_final/ner-roberta-bioe-char-pattern3-subtext-dim50/checkpoints/checkpoint-552000",
"epoch": 294.71436198611855,
"global_step": 552000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0678056593699947,
"learning_rate": 4.982203239010501e-05,
"loss": 0.1441604766845703,
"step": 2000
},
{
"epoch": 1.0678056593699947,
"eval_loss": 0.09690555930137634,
"eval_micro_f1": 0.8483981943974436,
"step": 2000
},
{
"epoch": 2.1356113187399894,
"learning_rate": 4.9644064780210006e-05,
"loss": 0.07054872894287109,
"step": 4000
},
{
"epoch": 2.1356113187399894,
"eval_loss": 0.10765556246042252,
"eval_micro_f1": 0.8489558032884322,
"step": 4000
},
{
"epoch": 3.203416978109984,
"learning_rate": 4.9466097170315004e-05,
"loss": 0.0522383918762207,
"step": 6000
},
{
"epoch": 3.203416978109984,
"eval_loss": 0.10142778605222702,
"eval_micro_f1": 0.858142664372088,
"step": 6000
},
{
"epoch": 4.271222637479979,
"learning_rate": 4.928812956042e-05,
"loss": 0.041123741149902346,
"step": 8000
},
{
"epoch": 4.271222637479979,
"eval_loss": 0.10864394158124924,
"eval_micro_f1": 0.8591757277856453,
"step": 8000
},
{
"epoch": 5.339028296849973,
"learning_rate": 4.911016195052501e-05,
"loss": 0.03384337615966797,
"step": 10000
},
{
"epoch": 5.339028296849973,
"eval_loss": 0.1240122839808464,
"eval_micro_f1": 0.8540363018122469,
"step": 10000
},
{
"epoch": 6.406833956219968,
"learning_rate": 4.8932194340630006e-05,
"loss": 0.027656402587890625,
"step": 12000
},
{
"epoch": 6.406833956219968,
"eval_loss": 0.12531153857707977,
"eval_micro_f1": 0.8595292326055319,
"step": 12000
},
{
"epoch": 7.474639615589963,
"learning_rate": 4.875422673073501e-05,
"loss": 0.023082820892333985,
"step": 14000
},
{
"epoch": 7.474639615589963,
"eval_loss": 0.1331861913204193,
"eval_micro_f1": 0.8607068602067829,
"step": 14000
},
{
"epoch": 8.542445274959958,
"learning_rate": 4.857625912084001e-05,
"loss": 0.019628978729248046,
"step": 16000
},
{
"epoch": 8.542445274959958,
"eval_loss": 0.14401184022426605,
"eval_micro_f1": 0.8595520651732423,
"step": 16000
},
{
"epoch": 9.610250934329953,
"learning_rate": 4.839829151094501e-05,
"loss": 0.017337644577026367,
"step": 18000
},
{
"epoch": 9.610250934329953,
"eval_loss": 0.14833271503448486,
"eval_micro_f1": 0.8617538223344821,
"step": 18000
},
{
"epoch": 10.678056593699946,
"learning_rate": 4.822032390105001e-05,
"loss": 0.014908449172973633,
"step": 20000
},
{
"epoch": 10.678056593699946,
"eval_loss": 0.1469031274318695,
"eval_micro_f1": 0.8583706351311212,
"step": 20000
},
{
"epoch": 11.74586225306994,
"learning_rate": 4.804235629115501e-05,
"loss": 0.0133180513381958,
"step": 22000
},
{
"epoch": 11.74586225306994,
"eval_loss": 0.1527302861213684,
"eval_micro_f1": 0.8600349347801151,
"step": 22000
},
{
"epoch": 12.813667912439936,
"learning_rate": 4.7864388681260017e-05,
"loss": 0.011943829536437989,
"step": 24000
},
{
"epoch": 12.813667912439936,
"eval_loss": 0.15925365686416626,
"eval_micro_f1": 0.862840422637449,
"step": 24000
},
{
"epoch": 13.88147357180993,
"learning_rate": 4.7686421071365015e-05,
"loss": 0.011462370872497558,
"step": 26000
},
{
"epoch": 13.88147357180993,
"eval_loss": 0.15267999470233917,
"eval_micro_f1": 0.861355613636976,
"step": 26000
},
{
"epoch": 14.949279231179926,
"learning_rate": 4.750845346147001e-05,
"loss": 0.010567516326904296,
"step": 28000
},
{
"epoch": 14.949279231179926,
"eval_loss": 0.1637338399887085,
"eval_micro_f1": 0.8584931131915317,
"step": 28000
},
{
"epoch": 16.01708489054992,
"learning_rate": 4.733048585157502e-05,
"loss": 0.010466363906860352,
"step": 30000
},
{
"epoch": 16.01708489054992,
"eval_loss": 0.1614995300769806,
"eval_micro_f1": 0.8620005406742725,
"step": 30000
},
{
"epoch": 17.084890549919916,
"learning_rate": 4.715251824168002e-05,
"loss": 0.008756108283996582,
"step": 32000
},
{
"epoch": 17.084890549919916,
"eval_loss": 0.18236176669597626,
"eval_micro_f1": 0.8624787770891194,
"step": 32000
},
{
"epoch": 18.15269620928991,
"learning_rate": 4.697455063178502e-05,
"loss": 0.008643110275268555,
"step": 34000
},
{
"epoch": 18.15269620928991,
"eval_loss": 0.17678703367710114,
"eval_micro_f1": 0.8616735347087036,
"step": 34000
},
{
"epoch": 19.220501868659905,
"learning_rate": 4.679658302189002e-05,
"loss": 0.00804537296295166,
"step": 36000
},
{
"epoch": 19.220501868659905,
"eval_loss": 0.17433583736419678,
"eval_micro_f1": 0.8625264194306795,
"step": 36000
},
{
"epoch": 20.288307528029897,
"learning_rate": 4.661861541199502e-05,
"loss": 0.007841774463653564,
"step": 38000
},
{
"epoch": 20.288307528029897,
"eval_loss": 0.17555472254753113,
"eval_micro_f1": 0.860048166478867,
"step": 38000
},
{
"epoch": 21.35611318739989,
"learning_rate": 4.644064780210002e-05,
"loss": 0.007388807773590088,
"step": 40000
},
{
"epoch": 21.35611318739989,
"eval_loss": 0.18752311170101166,
"eval_micro_f1": 0.8576962921257212,
"step": 40000
},
{
"epoch": 22.423918846769887,
"learning_rate": 4.626268019220502e-05,
"loss": 0.007176242828369141,
"step": 42000
},
{
"epoch": 22.423918846769887,
"eval_loss": 0.18554599583148956,
"eval_micro_f1": 0.8686442574544394,
"step": 42000
},
{
"epoch": 23.49172450613988,
"learning_rate": 4.608471258231003e-05,
"loss": 0.007462764739990234,
"step": 44000
},
{
"epoch": 23.49172450613988,
"eval_loss": 0.18543270230293274,
"eval_micro_f1": 0.8580712120997698,
"step": 44000
},
{
"epoch": 24.559530165509877,
"learning_rate": 4.5906744972415025e-05,
"loss": 0.006708044528961182,
"step": 46000
},
{
"epoch": 24.559530165509877,
"eval_loss": 0.18160435557365417,
"eval_micro_f1": 0.8598358432809289,
"step": 46000
},
{
"epoch": 25.62733582487987,
"learning_rate": 4.5728777362520024e-05,
"loss": 0.006188345432281494,
"step": 48000
},
{
"epoch": 25.62733582487987,
"eval_loss": 0.1792888641357422,
"eval_micro_f1": 0.8601203840116637,
"step": 48000
},
{
"epoch": 26.695141484249866,
"learning_rate": 4.555080975262502e-05,
"loss": 0.006261987209320068,
"step": 50000
},
{
"epoch": 26.695141484249866,
"eval_loss": 0.18848691880702972,
"eval_micro_f1": 0.8622396641300746,
"step": 50000
},
{
"epoch": 27.76294714361986,
"learning_rate": 4.537284214273003e-05,
"loss": 0.005623719692230225,
"step": 52000
},
{
"epoch": 27.76294714361986,
"eval_loss": 0.18980298936367035,
"eval_micro_f1": 0.8576337080762596,
"step": 52000
},
{
"epoch": 28.830752802989856,
"learning_rate": 4.5194874532835026e-05,
"loss": 0.006225793838500976,
"step": 54000
},
{
"epoch": 28.830752802989856,
"eval_loss": 0.19089065492153168,
"eval_micro_f1": 0.8597888327140014,
"step": 54000
},
{
"epoch": 29.89855846235985,
"learning_rate": 4.501690692294003e-05,
"loss": 0.005721967220306396,
"step": 56000
},
{
"epoch": 29.89855846235985,
"eval_loss": 0.1912381500005722,
"eval_micro_f1": 0.8648769971655924,
"step": 56000
},
{
"epoch": 30.966364121729846,
"learning_rate": 4.483893931304502e-05,
"loss": 0.005537011623382568,
"step": 58000
},
{
"epoch": 30.966364121729846,
"eval_loss": 0.1839170902967453,
"eval_micro_f1": 0.861842996743109,
"step": 58000
},
{
"epoch": 32.03416978109984,
"learning_rate": 4.466097170315003e-05,
"loss": 0.0055362129211425784,
"step": 60000
},
{
"epoch": 32.03416978109984,
"eval_loss": 0.1916428804397583,
"eval_micro_f1": 0.8622797549835749,
"step": 60000
},
{
"epoch": 33.101975440469836,
"learning_rate": 4.448300409325503e-05,
"loss": 0.005321506977081299,
"step": 62000
},
{
"epoch": 33.101975440469836,
"eval_loss": 0.19113874435424805,
"eval_micro_f1": 0.8604869327141929,
"step": 62000
},
{
"epoch": 34.16978109983983,
"learning_rate": 4.430503648336003e-05,
"loss": 0.005131518840789795,
"step": 64000
},
{
"epoch": 34.16978109983983,
"eval_loss": 0.18931125104427338,
"eval_micro_f1": 0.862322742275031,
"step": 64000
},
{
"epoch": 35.237586759209826,
"learning_rate": 4.4127068873465036e-05,
"loss": 0.005316986083984375,
"step": 66000
},
{
"epoch": 35.237586759209826,
"eval_loss": 0.18068699538707733,
"eval_micro_f1": 0.8563334677314197,
"step": 66000
},
{
"epoch": 36.30539241857982,
"learning_rate": 4.394910126357003e-05,
"loss": 0.004507422924041748,
"step": 68000
},
{
"epoch": 36.30539241857982,
"eval_loss": 0.19036008417606354,
"eval_micro_f1": 0.8623407028817446,
"step": 68000
},
{
"epoch": 37.373198077949816,
"learning_rate": 4.377113365367503e-05,
"loss": 0.004602288246154785,
"step": 70000
},
{
"epoch": 37.373198077949816,
"eval_loss": 0.19767245650291443,
"eval_micro_f1": 0.8620937973215159,
"step": 70000
},
{
"epoch": 38.44100373731981,
"learning_rate": 4.359316604378003e-05,
"loss": 0.004596829414367676,
"step": 72000
},
{
"epoch": 38.44100373731981,
"eval_loss": 0.1985686868429184,
"eval_micro_f1": 0.8606730461818811,
"step": 72000
},
{
"epoch": 39.508809396689806,
"learning_rate": 4.3415198433885036e-05,
"loss": 0.00506240177154541,
"step": 74000
},
{
"epoch": 39.508809396689806,
"eval_loss": 0.19221682846546173,
"eval_micro_f1": 0.8625967940254106,
"step": 74000
},
{
"epoch": 40.576615056059794,
"learning_rate": 4.323723082399004e-05,
"loss": 0.0043592162132263185,
"step": 76000
},
{
"epoch": 40.576615056059794,
"eval_loss": 0.19294172525405884,
"eval_micro_f1": 0.862280269661444,
"step": 76000
},
{
"epoch": 41.64442071542979,
"learning_rate": 4.305926321409503e-05,
"loss": 0.004392739772796631,
"step": 78000
},
{
"epoch": 41.64442071542979,
"eval_loss": 0.18995815515518188,
"eval_micro_f1": 0.8615938761320762,
"step": 78000
},
{
"epoch": 42.71222637479978,
"learning_rate": 4.288129560420004e-05,
"loss": 0.004247452259063721,
"step": 80000
},
{
"epoch": 42.71222637479978,
"eval_loss": 0.19998286664485931,
"eval_micro_f1": 0.8580193994548074,
"step": 80000
},
{
"epoch": 43.78003203416978,
"learning_rate": 4.2703327994305036e-05,
"loss": 0.004592265129089355,
"step": 82000
},
{
"epoch": 43.78003203416978,
"eval_loss": 0.18968616425991058,
"eval_micro_f1": 0.8599764509083115,
"step": 82000
},
{
"epoch": 44.84783769353977,
"learning_rate": 4.252536038441004e-05,
"loss": 0.004490021705627441,
"step": 84000
},
{
"epoch": 44.84783769353977,
"eval_loss": 0.19186130166053772,
"eval_micro_f1": 0.8586519790945234,
"step": 84000
},
{
"epoch": 45.91564335290977,
"learning_rate": 4.234739277451504e-05,
"loss": 0.004225976943969726,
"step": 86000
},
{
"epoch": 45.91564335290977,
"eval_loss": 0.19815164804458618,
"eval_micro_f1": 0.8588319593709755,
"step": 86000
},
{
"epoch": 46.98344901227976,
"learning_rate": 4.216942516462004e-05,
"loss": 0.004158265590667724,
"step": 88000
},
{
"epoch": 46.98344901227976,
"eval_loss": 0.19364391267299652,
"eval_micro_f1": 0.8586883024072952,
"step": 88000
},
{
"epoch": 48.05125467164976,
"learning_rate": 4.1991457554725043e-05,
"loss": 0.0037199242115020753,
"step": 90000
},
{
"epoch": 48.05125467164976,
"eval_loss": 0.19885197281837463,
"eval_micro_f1": 0.8625276157134597,
"step": 90000
},
{
"epoch": 49.11906033101975,
"learning_rate": 4.181348994483004e-05,
"loss": 0.003676062107086182,
"step": 92000
},
{
"epoch": 49.11906033101975,
"eval_loss": 0.19308163225650787,
"eval_micro_f1": 0.8576289393280451,
"step": 92000
},
{
"epoch": 50.18686599038975,
"learning_rate": 4.163552233493505e-05,
"loss": 0.0038728065490722654,
"step": 94000
},
{
"epoch": 50.18686599038975,
"eval_loss": 0.19670134782791138,
"eval_micro_f1": 0.8620643125199465,
"step": 94000
},
{
"epoch": 51.25467164975974,
"learning_rate": 4.1457554725040045e-05,
"loss": 0.0035796360969543458,
"step": 96000
},
{
"epoch": 51.25467164975974,
"eval_loss": 0.20435616374015808,
"eval_micro_f1": 0.8613368042761704,
"step": 96000
},
{
"epoch": 52.32247730912974,
"learning_rate": 4.1279587115145044e-05,
"loss": 0.003631280183792114,
"step": 98000
},
{
"epoch": 52.32247730912974,
"eval_loss": 0.20271043479442596,
"eval_micro_f1": 0.8630284529601373,
"step": 98000
},
{
"epoch": 53.39028296849973,
"learning_rate": 4.110161950525004e-05,
"loss": 0.003397218704223633,
"step": 100000
},
{
"epoch": 53.39028296849973,
"eval_loss": 0.19718486070632935,
"eval_micro_f1": 0.8587784534102251,
"step": 100000
},
{
"epoch": 54.45808862786973,
"learning_rate": 4.092365189535505e-05,
"loss": 0.0034236457347869872,
"step": 102000
},
{
"epoch": 54.45808862786973,
"eval_loss": 0.22809669375419617,
"eval_micro_f1": 0.8566551362862476,
"step": 102000
},
{
"epoch": 55.52589428723972,
"learning_rate": 4.074568428546005e-05,
"loss": 0.0033523378372192383,
"step": 104000
},
{
"epoch": 55.52589428723972,
"eval_loss": 0.21574394404888153,
"eval_micro_f1": 0.863969929695065,
"step": 104000
},
{
"epoch": 56.59369994660972,
"learning_rate": 4.056771667556505e-05,
"loss": 0.0035488724708557127,
"step": 106000
},
{
"epoch": 56.59369994660972,
"eval_loss": 0.20770174264907837,
"eval_micro_f1": 0.8612994472122136,
"step": 106000
},
{
"epoch": 57.66150560597971,
"learning_rate": 4.038974906567005e-05,
"loss": 0.0029777846336364747,
"step": 108000
},
{
"epoch": 57.66150560597971,
"eval_loss": 0.21020378172397614,
"eval_micro_f1": 0.8597837299257557,
"step": 108000
},
{
"epoch": 58.72931126534971,
"learning_rate": 4.021178145577505e-05,
"loss": 0.0034167163372039793,
"step": 110000
},
{
"epoch": 58.72931126534971,
"eval_loss": 0.20460911095142365,
"eval_micro_f1": 0.8603658257549366,
"step": 110000
},
{
"epoch": 59.7971169247197,
"learning_rate": 4.003381384588005e-05,
"loss": 0.003229135036468506,
"step": 112000
},
{
"epoch": 59.7971169247197,
"eval_loss": 0.21315120160579681,
"eval_micro_f1": 0.8584778501603754,
"step": 112000
},
{
"epoch": 60.8649225840897,
"learning_rate": 3.985584623598505e-05,
"loss": 0.0032584888935089113,
"step": 114000
},
{
"epoch": 60.8649225840897,
"eval_loss": 0.21643145382404327,
"eval_micro_f1": 0.8587167557197265,
"step": 114000
},
{
"epoch": 61.93272824345969,
"learning_rate": 3.9677878626090056e-05,
"loss": 0.003184603214263916,
"step": 116000
},
{
"epoch": 61.93272824345969,
"eval_loss": 0.2074163407087326,
"eval_micro_f1": 0.8609580135699486,
"step": 116000
},
{
"epoch": 63.00053390282969,
"learning_rate": 3.9499911016195054e-05,
"loss": 0.003010392665863037,
"step": 118000
},
{
"epoch": 63.00053390282969,
"eval_loss": 0.21201346814632416,
"eval_micro_f1": 0.8555570470806484,
"step": 118000
},
{
"epoch": 64.06833956219968,
"learning_rate": 3.932194340630005e-05,
"loss": 0.002922715425491333,
"step": 120000
},
{
"epoch": 64.06833956219968,
"eval_loss": 0.19645464420318604,
"eval_micro_f1": 0.858481217408224,
"step": 120000
},
{
"epoch": 65.13614522156968,
"learning_rate": 3.914397579640506e-05,
"loss": 0.0029303188323974608,
"step": 122000
},
{
"epoch": 65.13614522156968,
"eval_loss": 0.2092672884464264,
"eval_micro_f1": 0.8634586866545411,
"step": 122000
},
{
"epoch": 66.20395088093967,
"learning_rate": 3.8966008186510056e-05,
"loss": 0.0025819108486175536,
"step": 124000
},
{
"epoch": 66.20395088093967,
"eval_loss": 0.21263988316059113,
"eval_micro_f1": 0.8620487624004618,
"step": 124000
},
{
"epoch": 67.27175654030967,
"learning_rate": 3.878804057661506e-05,
"loss": 0.0030023691654205323,
"step": 126000
},
{
"epoch": 67.27175654030967,
"eval_loss": 0.20814797282218933,
"eval_micro_f1": 0.8615356945188166,
"step": 126000
},
{
"epoch": 68.33956219967966,
"learning_rate": 3.861007296672006e-05,
"loss": 0.002790276050567627,
"step": 128000
},
{
"epoch": 68.33956219967966,
"eval_loss": 0.21176110208034515,
"eval_micro_f1": 0.862110796103254,
"step": 128000
},
{
"epoch": 69.40736785904966,
"learning_rate": 3.843210535682506e-05,
"loss": 0.002653460741043091,
"step": 130000
},
{
"epoch": 69.40736785904966,
"eval_loss": 0.20997311174869537,
"eval_micro_f1": 0.8591124122054908,
"step": 130000
},
{
"epoch": 70.47517351841965,
"learning_rate": 3.825413774693006e-05,
"loss": 0.0029963724613189698,
"step": 132000
},
{
"epoch": 70.47517351841965,
"eval_loss": 0.21968315541744232,
"eval_micro_f1": 0.859869186848763,
"step": 132000
},
{
"epoch": 71.54297917778965,
"learning_rate": 3.807617013703506e-05,
"loss": 0.002651949405670166,
"step": 134000
},
{
"epoch": 71.54297917778965,
"eval_loss": 0.20945623517036438,
"eval_micro_f1": 0.8570528678913827,
"step": 134000
},
{
"epoch": 72.61078483715964,
"learning_rate": 3.7898202527140067e-05,
"loss": 0.0028313062191009522,
"step": 136000
},
{
"epoch": 72.61078483715964,
"eval_loss": 0.21140611171722412,
"eval_micro_f1": 0.861396349439416,
"step": 136000
},
{
"epoch": 73.67859049652964,
"learning_rate": 3.7720234917245065e-05,
"loss": 0.0024838025569915772,
"step": 138000
},
{
"epoch": 73.67859049652964,
"eval_loss": 0.22475212812423706,
"eval_micro_f1": 0.8568738224754701,
"step": 138000
},
{
"epoch": 74.74639615589963,
"learning_rate": 3.754226730735006e-05,
"loss": 0.0025286438465118408,
"step": 140000
},
{
"epoch": 74.74639615589963,
"eval_loss": 0.20995303988456726,
"eval_micro_f1": 0.8634954852835268,
"step": 140000
},
{
"epoch": 75.81420181526963,
"learning_rate": 3.736429969745506e-05,
"loss": 0.0024675247669219973,
"step": 142000
},
{
"epoch": 75.81420181526963,
"eval_loss": 0.22036942839622498,
"eval_micro_f1": 0.86106361868467,
"step": 142000
},
{
"epoch": 76.88200747463962,
"learning_rate": 3.718633208756007e-05,
"loss": 0.0026259043216705323,
"step": 144000
},
{
"epoch": 76.88200747463962,
"eval_loss": 0.21488071978092194,
"eval_micro_f1": 0.8588420810498253,
"step": 144000
},
{
"epoch": 77.94981313400962,
"learning_rate": 3.7008364477665065e-05,
"loss": 0.002294412851333618,
"step": 146000
},
{
"epoch": 77.94981313400962,
"eval_loss": 0.20914296805858612,
"eval_micro_f1": 0.8610022958662664,
"step": 146000
},
{
"epoch": 79.01761879337961,
"learning_rate": 3.683039686777007e-05,
"loss": 0.002372340202331543,
"step": 148000
},
{
"epoch": 79.01761879337961,
"eval_loss": 0.22916126251220703,
"eval_micro_f1": 0.8579384679481777,
"step": 148000
},
{
"epoch": 80.0854244527496,
"learning_rate": 3.665242925787507e-05,
"loss": 0.002520388126373291,
"step": 150000
},
{
"epoch": 80.0854244527496,
"eval_loss": 0.22416692972183228,
"eval_micro_f1": 0.8581293152563864,
"step": 150000
},
{
"epoch": 81.15323011211959,
"learning_rate": 3.647446164798007e-05,
"loss": 0.00264005184173584,
"step": 152000
},
{
"epoch": 81.15323011211959,
"eval_loss": 0.21678157150745392,
"eval_micro_f1": 0.8623077609892762,
"step": 152000
},
{
"epoch": 82.22103577148958,
"learning_rate": 3.629649403808507e-05,
"loss": 0.0023589327335357666,
"step": 154000
},
{
"epoch": 82.22103577148958,
"eval_loss": 0.21393051743507385,
"eval_micro_f1": 0.8614408694591464,
"step": 154000
},
{
"epoch": 83.28884143085958,
"learning_rate": 3.611852642819007e-05,
"loss": 0.002270070791244507,
"step": 156000
},
{
"epoch": 83.28884143085958,
"eval_loss": 0.22115078568458557,
"eval_micro_f1": 0.8597130386759324,
"step": 156000
},
{
"epoch": 84.35664709022957,
"learning_rate": 3.5940558818295076e-05,
"loss": 0.0024425249099731443,
"step": 158000
},
{
"epoch": 84.35664709022957,
"eval_loss": 0.21257692575454712,
"eval_micro_f1": 0.8641908615300888,
"step": 158000
},
{
"epoch": 85.42445274959957,
"learning_rate": 3.576259120840007e-05,
"loss": 0.0023241539001464845,
"step": 160000
},
{
"epoch": 85.42445274959957,
"eval_loss": 0.23051173985004425,
"eval_micro_f1": 0.8566816138497273,
"step": 160000
},
{
"epoch": 86.49225840896956,
"learning_rate": 3.558462359850507e-05,
"loss": 0.00196639621257782,
"step": 162000
},
{
"epoch": 86.49225840896956,
"eval_loss": 0.23142772912979126,
"eval_micro_f1": 0.8593616729748285,
"step": 162000
},
{
"epoch": 87.56006406833956,
"learning_rate": 3.540665598861008e-05,
"loss": 0.0023800725936889647,
"step": 164000
},
{
"epoch": 87.56006406833956,
"eval_loss": 0.21721826493740082,
"eval_micro_f1": 0.8591713844195028,
"step": 164000
},
{
"epoch": 88.62786972770955,
"learning_rate": 3.5228688378715076e-05,
"loss": 0.002247375965118408,
"step": 166000
},
{
"epoch": 88.62786972770955,
"eval_loss": 0.21846149861812592,
"eval_micro_f1": 0.859530119440643,
"step": 166000
},
{
"epoch": 89.69567538707955,
"learning_rate": 3.505072076882008e-05,
"loss": 0.0022114086151123046,
"step": 168000
},
{
"epoch": 89.69567538707955,
"eval_loss": 0.22235164046287537,
"eval_micro_f1": 0.8583310726397834,
"step": 168000
},
{
"epoch": 90.76348104644954,
"learning_rate": 3.487275315892507e-05,
"loss": 0.002251800537109375,
"step": 170000
},
{
"epoch": 90.76348104644954,
"eval_loss": 0.21426522731781006,
"eval_micro_f1": 0.8597179031545608,
"step": 170000
},
{
"epoch": 91.83128670581954,
"learning_rate": 3.469478554903008e-05,
"loss": 0.0022111124992370604,
"step": 172000
},
{
"epoch": 91.83128670581954,
"eval_loss": 0.22568802535533905,
"eval_micro_f1": 0.8610724072485993,
"step": 172000
},
{
"epoch": 92.89909236518953,
"learning_rate": 3.4516817939135076e-05,
"loss": 0.0021670064926147463,
"step": 174000
},
{
"epoch": 92.89909236518953,
"eval_loss": 0.21815767884254456,
"eval_micro_f1": 0.8625854028753356,
"step": 174000
},
{
"epoch": 93.96689802455953,
"learning_rate": 3.433885032924008e-05,
"loss": 0.001791886329650879,
"step": 176000
},
{
"epoch": 93.96689802455953,
"eval_loss": 0.22718997299671173,
"eval_micro_f1": 0.8608233487477429,
"step": 176000
},
{
"epoch": 95.03470368392952,
"learning_rate": 3.4160882719345086e-05,
"loss": 0.0022712950706481935,
"step": 178000
},
{
"epoch": 95.03470368392952,
"eval_loss": 0.22081848978996277,
"eval_micro_f1": 0.8590260958141839,
"step": 178000
},
{
"epoch": 96.10250934329952,
"learning_rate": 3.398291510945008e-05,
"loss": 0.001983537435531616,
"step": 180000
},
{
"epoch": 96.10250934329952,
"eval_loss": 0.2304282784461975,
"eval_micro_f1": 0.8596436100749256,
"step": 180000
},
{
"epoch": 97.17031500266951,
"learning_rate": 3.380494749955508e-05,
"loss": 0.0017843385934829712,
"step": 182000
},
{
"epoch": 97.17031500266951,
"eval_loss": 0.24379734694957733,
"eval_micro_f1": 0.8581439218788814,
"step": 182000
},
{
"epoch": 98.2381206620395,
"learning_rate": 3.362697988966008e-05,
"loss": 0.002217904567718506,
"step": 184000
},
{
"epoch": 98.2381206620395,
"eval_loss": 0.23734766244888306,
"eval_micro_f1": 0.8577715897455963,
"step": 184000
},
{
"epoch": 99.3059263214095,
"learning_rate": 3.3449012279765086e-05,
"loss": 0.0019373159408569336,
"step": 186000
},
{
"epoch": 99.3059263214095,
"eval_loss": 0.2344348132610321,
"eval_micro_f1": 0.8588688020773816,
"step": 186000
},
{
"epoch": 100.3737319807795,
"learning_rate": 3.3271044669870085e-05,
"loss": 0.0017083662748336793,
"step": 188000
},
{
"epoch": 100.3737319807795,
"eval_loss": 0.23221217095851898,
"eval_micro_f1": 0.8592718942793128,
"step": 188000
},
{
"epoch": 101.44153764014949,
"learning_rate": 3.309307705997508e-05,
"loss": 0.001737923264503479,
"step": 190000
},
{
"epoch": 101.44153764014949,
"eval_loss": 0.23596663773059845,
"eval_micro_f1": 0.8628424420688624,
"step": 190000
},
{
"epoch": 102.50934329951949,
"learning_rate": 3.291510945008009e-05,
"loss": 0.001814214587211609,
"step": 192000
},
{
"epoch": 102.50934329951949,
"eval_loss": 0.23174215853214264,
"eval_micro_f1": 0.8612758305870909,
"step": 192000
},
{
"epoch": 103.57714895888948,
"learning_rate": 3.2737141840185087e-05,
"loss": 0.0018568933010101318,
"step": 194000
},
{
"epoch": 103.57714895888948,
"eval_loss": 0.2273360937833786,
"eval_micro_f1": 0.8596365584472413,
"step": 194000
},
{
"epoch": 104.64495461825948,
"learning_rate": 3.255917423029009e-05,
"loss": 0.001986026406288147,
"step": 196000
},
{
"epoch": 104.64495461825948,
"eval_loss": 0.23130175471305847,
"eval_micro_f1": 0.8625647955332808,
"step": 196000
},
{
"epoch": 105.71276027762947,
"learning_rate": 3.238120662039509e-05,
"loss": 0.001677799105644226,
"step": 198000
},
{
"epoch": 105.71276027762947,
"eval_loss": 0.2318616509437561,
"eval_micro_f1": 0.863030957023329,
"step": 198000
},
{
"epoch": 106.78056593699947,
"learning_rate": 3.220323901050009e-05,
"loss": 0.0017691035270690919,
"step": 200000
},
{
"epoch": 106.78056593699947,
"eval_loss": 0.23336781561374664,
"eval_micro_f1": 0.8628669182825687,
"step": 200000
},
{
"epoch": 107.84837159636946,
"learning_rate": 3.202527140060509e-05,
"loss": 0.00182578706741333,
"step": 202000
},
{
"epoch": 107.84837159636946,
"eval_loss": 0.22371776401996613,
"eval_micro_f1": 0.860121320551387,
"step": 202000
},
{
"epoch": 108.91617725573946,
"learning_rate": 3.184730379071009e-05,
"loss": 0.0015997549295425416,
"step": 204000
},
{
"epoch": 108.91617725573946,
"eval_loss": 0.23864321410655975,
"eval_micro_f1": 0.8618834075716998,
"step": 204000
},
{
"epoch": 109.98398291510945,
"learning_rate": 3.16693361808151e-05,
"loss": 0.0018162869215011597,
"step": 206000
},
{
"epoch": 109.98398291510945,
"eval_loss": 0.2285407930612564,
"eval_micro_f1": 0.85963499681613,
"step": 206000
},
{
"epoch": 111.05178857447945,
"learning_rate": 3.1491368570920095e-05,
"loss": 0.0016109637022018433,
"step": 208000
},
{
"epoch": 111.05178857447945,
"eval_loss": 0.2389502227306366,
"eval_micro_f1": 0.8583694861232052,
"step": 208000
},
{
"epoch": 112.11959423384944,
"learning_rate": 3.1313400961025094e-05,
"loss": 0.0017224030494689942,
"step": 210000
},
{
"epoch": 112.11959423384944,
"eval_loss": 0.2187904715538025,
"eval_micro_f1": 0.860368229576562,
"step": 210000
},
{
"epoch": 113.18739989321944,
"learning_rate": 3.113543335113009e-05,
"loss": 0.0014214364290237426,
"step": 212000
},
{
"epoch": 113.18739989321944,
"eval_loss": 0.24186697602272034,
"eval_micro_f1": 0.8593447198568593,
"step": 212000
},
{
"epoch": 114.25520555258943,
"learning_rate": 3.09574657412351e-05,
"loss": 0.0018300899267196654,
"step": 214000
},
{
"epoch": 114.25520555258943,
"eval_loss": 0.2178592085838318,
"eval_micro_f1": 0.8589206000680298,
"step": 214000
},
{
"epoch": 115.32301121195943,
"learning_rate": 3.0779498131340096e-05,
"loss": 0.0017930263280868531,
"step": 216000
},
{
"epoch": 115.32301121195943,
"eval_loss": 0.22575804591178894,
"eval_micro_f1": 0.8613447262820334,
"step": 216000
},
{
"epoch": 116.39081687132942,
"learning_rate": 3.06015305214451e-05,
"loss": 0.0014410455226898193,
"step": 218000
},
{
"epoch": 116.39081687132942,
"eval_loss": 0.23413068056106567,
"eval_micro_f1": 0.8610412921390829,
"step": 218000
},
{
"epoch": 117.45862253069942,
"learning_rate": 3.0423562911550102e-05,
"loss": 0.0013108035326004027,
"step": 220000
},
{
"epoch": 117.45862253069942,
"eval_loss": 0.24708405137062073,
"eval_micro_f1": 0.8579767405533302,
"step": 220000
},
{
"epoch": 118.52642819006941,
"learning_rate": 3.02455953016551e-05,
"loss": 0.0016451451778411864,
"step": 222000
},
{
"epoch": 118.52642819006941,
"eval_loss": 0.231824591755867,
"eval_micro_f1": 0.8595644916328312,
"step": 222000
},
{
"epoch": 119.5942338494394,
"learning_rate": 3.0067627691760102e-05,
"loss": 0.0015194268226623535,
"step": 224000
},
{
"epoch": 119.5942338494394,
"eval_loss": 0.24116140604019165,
"eval_micro_f1": 0.8573861594139032,
"step": 224000
},
{
"epoch": 120.6620395088094,
"learning_rate": 2.98896600818651e-05,
"loss": 0.00149759578704834,
"step": 226000
},
{
"epoch": 120.6620395088094,
"eval_loss": 0.23434299230575562,
"eval_micro_f1": 0.8589945537102908,
"step": 226000
},
{
"epoch": 121.7298451681794,
"learning_rate": 2.9711692471970103e-05,
"loss": 0.0013095945119857787,
"step": 228000
},
{
"epoch": 121.7298451681794,
"eval_loss": 0.2434019297361374,
"eval_micro_f1": 0.8609092135308919,
"step": 228000
},
{
"epoch": 122.79765082754939,
"learning_rate": 2.95337248620751e-05,
"loss": 0.0013460679054260254,
"step": 230000
},
{
"epoch": 122.79765082754939,
"eval_loss": 0.24153538048267365,
"eval_micro_f1": 0.8547370312002169,
"step": 230000
},
{
"epoch": 123.86545648691938,
"learning_rate": 2.9355757252180106e-05,
"loss": 0.001442591428756714,
"step": 232000
},
{
"epoch": 123.86545648691938,
"eval_loss": 0.24694040417671204,
"eval_micro_f1": 0.8586532856430528,
"step": 232000
},
{
"epoch": 124.93326214628938,
"learning_rate": 2.9177789642285108e-05,
"loss": 0.001434849262237549,
"step": 234000
},
{
"epoch": 124.93326214628938,
"eval_loss": 0.24347247183322906,
"eval_micro_f1": 0.8557356491820632,
"step": 234000
},
{
"epoch": 126.00106780565937,
"learning_rate": 2.8999822032390106e-05,
"loss": 0.0012582790851593017,
"step": 236000
},
{
"epoch": 126.00106780565937,
"eval_loss": 0.24746358394622803,
"eval_micro_f1": 0.8563128486619935,
"step": 236000
},
{
"epoch": 127.06887346502937,
"learning_rate": 2.8821854422495108e-05,
"loss": 0.001532185912132263,
"step": 238000
},
{
"epoch": 127.06887346502937,
"eval_loss": 0.23931099474430084,
"eval_micro_f1": 0.8568087780572282,
"step": 238000
},
{
"epoch": 128.13667912439936,
"learning_rate": 2.8643886812600106e-05,
"loss": 0.0013591699600219726,
"step": 240000
},
{
"epoch": 128.13667912439936,
"eval_loss": 0.23480115830898285,
"eval_micro_f1": 0.8617813251793834,
"step": 240000
},
{
"epoch": 129.20448478376935,
"learning_rate": 2.846591920270511e-05,
"loss": 0.0013070305585861205,
"step": 242000
},
{
"epoch": 129.20448478376935,
"eval_loss": 0.23284810781478882,
"eval_micro_f1": 0.8660858626219096,
"step": 242000
},
{
"epoch": 130.27229044313935,
"learning_rate": 2.8287951592810106e-05,
"loss": 0.0015051685571670533,
"step": 244000
},
{
"epoch": 130.27229044313935,
"eval_loss": 0.24077753722667694,
"eval_micro_f1": 0.8593350378631183,
"step": 244000
},
{
"epoch": 131.34009610250934,
"learning_rate": 2.810998398291511e-05,
"loss": 0.0013471574783325195,
"step": 246000
},
{
"epoch": 131.34009610250934,
"eval_loss": 0.2404518574476242,
"eval_micro_f1": 0.8568621316066403,
"step": 246000
},
{
"epoch": 132.40790176187934,
"learning_rate": 2.793201637302011e-05,
"loss": 0.0011686781644821168,
"step": 248000
},
{
"epoch": 132.40790176187934,
"eval_loss": 0.24784733355045319,
"eval_micro_f1": 0.8595978221640196,
"step": 248000
},
{
"epoch": 133.47570742124933,
"learning_rate": 2.775404876312511e-05,
"loss": 0.0011055631637573243,
"step": 250000
},
{
"epoch": 133.47570742124933,
"eval_loss": 0.24275857210159302,
"eval_micro_f1": 0.8586321555168336,
"step": 250000
},
{
"epoch": 134.54351308061933,
"learning_rate": 2.7576081153230117e-05,
"loss": 0.00125644052028656,
"step": 252000
},
{
"epoch": 134.54351308061933,
"eval_loss": 0.2398672103881836,
"eval_micro_f1": 0.8606060601060038,
"step": 252000
},
{
"epoch": 135.61131873998931,
"learning_rate": 2.739811354333511e-05,
"loss": 0.0011021168231964112,
"step": 254000
},
{
"epoch": 135.61131873998931,
"eval_loss": 0.25806522369384766,
"eval_micro_f1": 0.8606880482367453,
"step": 254000
},
{
"epoch": 136.67912439935932,
"learning_rate": 2.7220145933440117e-05,
"loss": 0.0014515784978866577,
"step": 256000
},
{
"epoch": 136.67912439935932,
"eval_loss": 0.2490159422159195,
"eval_micro_f1": 0.8637303365785879,
"step": 256000
},
{
"epoch": 137.7469300587293,
"learning_rate": 2.7042178323545115e-05,
"loss": 0.0011552497148513794,
"step": 258000
},
{
"epoch": 137.7469300587293,
"eval_loss": 0.2444666475057602,
"eval_micro_f1": 0.8648745836948468,
"step": 258000
},
{
"epoch": 138.8147357180993,
"learning_rate": 2.6864210713650117e-05,
"loss": 0.001279594898223877,
"step": 260000
},
{
"epoch": 138.8147357180993,
"eval_loss": 0.24462324380874634,
"eval_micro_f1": 0.8603759969752416,
"step": 260000
},
{
"epoch": 139.8825413774693,
"learning_rate": 2.6686243103755115e-05,
"loss": 0.001271600842475891,
"step": 262000
},
{
"epoch": 139.8825413774693,
"eval_loss": 0.24830742180347443,
"eval_micro_f1": 0.8615439883623831,
"step": 262000
},
{
"epoch": 140.9503470368393,
"learning_rate": 2.6508275493860117e-05,
"loss": 0.0012245097160339356,
"step": 264000
},
{
"epoch": 140.9503470368393,
"eval_loss": 0.23577940464019775,
"eval_micro_f1": 0.8606933808596765,
"step": 264000
},
{
"epoch": 142.01815269620928,
"learning_rate": 2.6330307883965122e-05,
"loss": 0.0014426486492156983,
"step": 266000
},
{
"epoch": 142.01815269620928,
"eval_loss": 0.24613334238529205,
"eval_micro_f1": 0.8600205912901087,
"step": 266000
},
{
"epoch": 143.0859583555793,
"learning_rate": 2.615234027407012e-05,
"loss": 0.0014088290929794311,
"step": 268000
},
{
"epoch": 143.0859583555793,
"eval_loss": 0.24390412867069244,
"eval_micro_f1": 0.8562751223226786,
"step": 268000
},
{
"epoch": 144.15376401494927,
"learning_rate": 2.5974372664175122e-05,
"loss": 0.0010638545751571655,
"step": 270000
},
{
"epoch": 144.15376401494927,
"eval_loss": 0.2476940006017685,
"eval_micro_f1": 0.8595955051179142,
"step": 270000
},
{
"epoch": 145.22156967431928,
"learning_rate": 2.579640505428012e-05,
"loss": 0.001026271939277649,
"step": 272000
},
{
"epoch": 145.22156967431928,
"eval_loss": 0.24218125641345978,
"eval_micro_f1": 0.862013277806067,
"step": 272000
},
{
"epoch": 146.28937533368926,
"learning_rate": 2.5618437444385122e-05,
"loss": 0.001083476185798645,
"step": 274000
},
{
"epoch": 146.28937533368926,
"eval_loss": 0.24849438667297363,
"eval_micro_f1": 0.8579542888205761,
"step": 274000
},
{
"epoch": 147.35718099305927,
"learning_rate": 2.544046983449012e-05,
"loss": 0.0010218629837036133,
"step": 276000
},
{
"epoch": 147.35718099305927,
"eval_loss": 0.25935453176498413,
"eval_micro_f1": 0.8597280988967061,
"step": 276000
},
{
"epoch": 148.42498665242925,
"learning_rate": 2.5262502224595126e-05,
"loss": 0.0010705002546310424,
"step": 278000
},
{
"epoch": 148.42498665242925,
"eval_loss": 0.2479417473077774,
"eval_micro_f1": 0.8580569569620748,
"step": 278000
},
{
"epoch": 149.49279231179926,
"learning_rate": 2.5084534614700127e-05,
"loss": 0.0010823713541030884,
"step": 280000
},
{
"epoch": 149.49279231179926,
"eval_loss": 0.23807799816131592,
"eval_micro_f1": 0.8599864890293131,
"step": 280000
},
{
"epoch": 150.56059797116924,
"learning_rate": 2.4906567004805126e-05,
"loss": 0.0011554213762283326,
"step": 282000
},
{
"epoch": 150.56059797116924,
"eval_loss": 0.25400295853614807,
"eval_micro_f1": 0.8587049065131764,
"step": 282000
},
{
"epoch": 151.62840363053925,
"learning_rate": 2.4728599394910128e-05,
"loss": 0.0009153247475624085,
"step": 284000
},
{
"epoch": 151.62840363053925,
"eval_loss": 0.24164018034934998,
"eval_micro_f1": 0.8617791157852775,
"step": 284000
},
{
"epoch": 152.69620928990923,
"learning_rate": 2.455063178501513e-05,
"loss": 0.0010287969112396241,
"step": 286000
},
{
"epoch": 152.69620928990923,
"eval_loss": 0.2560558617115021,
"eval_micro_f1": 0.8607968514429177,
"step": 286000
},
{
"epoch": 153.76401494927924,
"learning_rate": 2.437266417512013e-05,
"loss": 0.0009526887536048889,
"step": 288000
},
{
"epoch": 153.76401494927924,
"eval_loss": 0.24886192381381989,
"eval_micro_f1": 0.8603226092142635,
"step": 288000
},
{
"epoch": 154.83182060864922,
"learning_rate": 2.419469656522513e-05,
"loss": 0.0010319234132766723,
"step": 290000
},
{
"epoch": 154.83182060864922,
"eval_loss": 0.23924922943115234,
"eval_micro_f1": 0.8608907315590667,
"step": 290000
},
{
"epoch": 155.89962626801923,
"learning_rate": 2.401672895533013e-05,
"loss": 0.0008182660341262818,
"step": 292000
},
{
"epoch": 155.89962626801923,
"eval_loss": 0.25134485960006714,
"eval_micro_f1": 0.8606087931865082,
"step": 292000
},
{
"epoch": 156.9674319273892,
"learning_rate": 2.3838761345435133e-05,
"loss": 0.0008630349636077881,
"step": 294000
},
{
"epoch": 156.9674319273892,
"eval_loss": 0.2563447952270508,
"eval_micro_f1": 0.8603146062415097,
"step": 294000
},
{
"epoch": 158.03523758675922,
"learning_rate": 2.366079373554013e-05,
"loss": 0.0008723941445350647,
"step": 296000
},
{
"epoch": 158.03523758675922,
"eval_loss": 0.2523575723171234,
"eval_micro_f1": 0.8653759966318011,
"step": 296000
},
{
"epoch": 159.1030432461292,
"learning_rate": 2.3482826125645133e-05,
"loss": 0.0008800521492958069,
"step": 298000
},
{
"epoch": 159.1030432461292,
"eval_loss": 0.2509215772151947,
"eval_micro_f1": 0.8613237275503564,
"step": 298000
},
{
"epoch": 160.1708489054992,
"learning_rate": 2.3304858515750135e-05,
"loss": 0.0010090428590774536,
"step": 300000
},
{
"epoch": 160.1708489054992,
"eval_loss": 0.2551473081111908,
"eval_micro_f1": 0.8616657667242543,
"step": 300000
},
{
"epoch": 161.2386545648692,
"learning_rate": 2.3126890905855136e-05,
"loss": 0.0008130142688751221,
"step": 302000
},
{
"epoch": 161.2386545648692,
"eval_loss": 0.2587306797504425,
"eval_micro_f1": 0.8586712212926177,
"step": 302000
},
{
"epoch": 162.30646022423917,
"learning_rate": 2.2948923295960138e-05,
"loss": 0.0008016359210014343,
"step": 304000
},
{
"epoch": 162.30646022423917,
"eval_loss": 0.25998491048812866,
"eval_micro_f1": 0.8628702408590985,
"step": 304000
},
{
"epoch": 163.37426588360918,
"learning_rate": 2.2770955686065137e-05,
"loss": 0.0008784607648849487,
"step": 306000
},
{
"epoch": 163.37426588360918,
"eval_loss": 0.26444926857948303,
"eval_micro_f1": 0.8624955176068034,
"step": 306000
},
{
"epoch": 164.44207154297916,
"learning_rate": 2.2592988076170138e-05,
"loss": 0.0009348033666610717,
"step": 308000
},
{
"epoch": 164.44207154297916,
"eval_loss": 0.2617838680744171,
"eval_micro_f1": 0.8615784981763052,
"step": 308000
},
{
"epoch": 165.50987720234917,
"learning_rate": 2.241502046627514e-05,
"loss": 0.0007647403478622436,
"step": 310000
},
{
"epoch": 165.50987720234917,
"eval_loss": 0.2663569748401642,
"eval_micro_f1": 0.8584011139564154,
"step": 310000
},
{
"epoch": 166.57768286171915,
"learning_rate": 2.223705285638014e-05,
"loss": 0.0007336395978927612,
"step": 312000
},
{
"epoch": 166.57768286171915,
"eval_loss": 0.25297731161117554,
"eval_micro_f1": 0.8612431603215488,
"step": 312000
},
{
"epoch": 167.64548852108916,
"learning_rate": 2.205908524648514e-05,
"loss": 0.0007980742454528809,
"step": 314000
},
{
"epoch": 167.64548852108916,
"eval_loss": 0.25412553548812866,
"eval_micro_f1": 0.861997847419608,
"step": 314000
},
{
"epoch": 168.71329418045914,
"learning_rate": 2.1881117636590142e-05,
"loss": 0.000984979212284088,
"step": 316000
},
{
"epoch": 168.71329418045914,
"eval_loss": 0.2572042644023895,
"eval_micro_f1": 0.8600278234015747,
"step": 316000
},
{
"epoch": 169.78109983982915,
"learning_rate": 2.1703150026695144e-05,
"loss": 0.0007551251649856567,
"step": 318000
},
{
"epoch": 169.78109983982915,
"eval_loss": 0.2562611401081085,
"eval_micro_f1": 0.860121320551387,
"step": 318000
},
{
"epoch": 170.84890549919913,
"learning_rate": 2.1525182416800145e-05,
"loss": 0.0007607081532478333,
"step": 320000
},
{
"epoch": 170.84890549919913,
"eval_loss": 0.2613609731197357,
"eval_micro_f1": 0.8608820360722034,
"step": 320000
},
{
"epoch": 171.91671115856914,
"learning_rate": 2.1347214806905144e-05,
"loss": 0.0006600691080093383,
"step": 322000
},
{
"epoch": 171.91671115856914,
"eval_loss": 0.25861597061157227,
"eval_micro_f1": 0.8640889920539992,
"step": 322000
},
{
"epoch": 172.98451681793912,
"learning_rate": 2.1169247197010145e-05,
"loss": 0.000769602656364441,
"step": 324000
},
{
"epoch": 172.98451681793912,
"eval_loss": 0.25972098112106323,
"eval_micro_f1": 0.8642030670396399,
"step": 324000
},
{
"epoch": 174.05232247730913,
"learning_rate": 2.0991279587115144e-05,
"loss": 0.0006964576244354249,
"step": 326000
},
{
"epoch": 174.05232247730913,
"eval_loss": 0.2538943290710449,
"eval_micro_f1": 0.8636934668366303,
"step": 326000
},
{
"epoch": 175.1201281366791,
"learning_rate": 2.0813311977220146e-05,
"loss": 0.0008574907779693604,
"step": 328000
},
{
"epoch": 175.1201281366791,
"eval_loss": 0.26138514280319214,
"eval_micro_f1": 0.8597618507693155,
"step": 328000
},
{
"epoch": 176.18793379604912,
"learning_rate": 2.0635344367325147e-05,
"loss": 0.0008722195625305175,
"step": 330000
},
{
"epoch": 176.18793379604912,
"eval_loss": 0.25858089327812195,
"eval_micro_f1": 0.8622905148434257,
"step": 330000
},
{
"epoch": 177.2557394554191,
"learning_rate": 2.045737675743015e-05,
"loss": 0.0007537572979927063,
"step": 332000
},
{
"epoch": 177.2557394554191,
"eval_loss": 0.26679086685180664,
"eval_micro_f1": 0.8609652071318175,
"step": 332000
},
{
"epoch": 178.3235451147891,
"learning_rate": 2.027940914753515e-05,
"loss": 0.000703163206577301,
"step": 334000
},
{
"epoch": 178.3235451147891,
"eval_loss": 0.26131951808929443,
"eval_micro_f1": 0.8626904574980484,
"step": 334000
},
{
"epoch": 179.3913507741591,
"learning_rate": 2.010144153764015e-05,
"loss": 0.0006894363760948181,
"step": 336000
},
{
"epoch": 179.3913507741591,
"eval_loss": 0.2489156275987625,
"eval_micro_f1": 0.8643473565657395,
"step": 336000
},
{
"epoch": 180.4591564335291,
"learning_rate": 1.992347392774515e-05,
"loss": 0.0006050315499305726,
"step": 338000
},
{
"epoch": 180.4591564335291,
"eval_loss": 0.25196483731269836,
"eval_micro_f1": 0.8628171787342397,
"step": 338000
},
{
"epoch": 181.52696209289908,
"learning_rate": 1.9745506317850153e-05,
"loss": 0.0007403541207313538,
"step": 340000
},
{
"epoch": 181.52696209289908,
"eval_loss": 0.26088252663612366,
"eval_micro_f1": 0.8619216756835593,
"step": 340000
},
{
"epoch": 182.5947677522691,
"learning_rate": 1.956753870795515e-05,
"loss": 0.0006391159296035766,
"step": 342000
},
{
"epoch": 182.5947677522691,
"eval_loss": 0.2674732506275177,
"eval_micro_f1": 0.8629587925645528,
"step": 342000
},
{
"epoch": 183.66257341163907,
"learning_rate": 1.9389571098060156e-05,
"loss": 0.0006817908883094788,
"step": 344000
},
{
"epoch": 183.66257341163907,
"eval_loss": 0.26260262727737427,
"eval_micro_f1": 0.8595924225181685,
"step": 344000
},
{
"epoch": 184.73037907100908,
"learning_rate": 1.9211603488165154e-05,
"loss": 0.0008664788007736207,
"step": 346000
},
{
"epoch": 184.73037907100908,
"eval_loss": 0.26331964135169983,
"eval_micro_f1": 0.863709967114182,
"step": 346000
},
{
"epoch": 185.79818473037906,
"learning_rate": 1.9033635878270156e-05,
"loss": 0.0006178488135337829,
"step": 348000
},
{
"epoch": 185.79818473037906,
"eval_loss": 0.2656555473804474,
"eval_micro_f1": 0.8634277997698376,
"step": 348000
},
{
"epoch": 186.86599038974907,
"learning_rate": 1.8855668268375158e-05,
"loss": 0.0006683124303817749,
"step": 350000
},
{
"epoch": 186.86599038974907,
"eval_loss": 0.26426076889038086,
"eval_micro_f1": 0.8620921773934069,
"step": 350000
},
{
"epoch": 187.93379604911905,
"learning_rate": 1.8677700658480156e-05,
"loss": 0.0006965393424034119,
"step": 352000
},
{
"epoch": 187.93379604911905,
"eval_loss": 0.2517392635345459,
"eval_micro_f1": 0.862600233755265,
"step": 352000
},
{
"epoch": 189.00160170848906,
"learning_rate": 1.8499733048585158e-05,
"loss": 0.0005091822743415833,
"step": 354000
},
{
"epoch": 189.00160170848906,
"eval_loss": 0.2640840709209442,
"eval_micro_f1": 0.8604221987167459,
"step": 354000
},
{
"epoch": 190.06940736785904,
"learning_rate": 1.832176543869016e-05,
"loss": 0.0006101802587509155,
"step": 356000
},
{
"epoch": 190.06940736785904,
"eval_loss": 0.26344960927963257,
"eval_micro_f1": 0.8603617751631251,
"step": 356000
},
{
"epoch": 191.13721302722905,
"learning_rate": 1.8143797828795158e-05,
"loss": 0.0005475528836250305,
"step": 358000
},
{
"epoch": 191.13721302722905,
"eval_loss": 0.278342604637146,
"eval_micro_f1": 0.8610660899015137,
"step": 358000
},
{
"epoch": 192.20501868659903,
"learning_rate": 1.7965830218900163e-05,
"loss": 0.0005817279815673828,
"step": 360000
},
{
"epoch": 192.20501868659903,
"eval_loss": 0.2674269378185272,
"eval_micro_f1": 0.8616749558112892,
"step": 360000
},
{
"epoch": 193.27282434596904,
"learning_rate": 1.778786260900516e-05,
"loss": 0.0005006568431854248,
"step": 362000
},
{
"epoch": 193.27282434596904,
"eval_loss": 0.28352972865104675,
"eval_micro_f1": 0.861235052150367,
"step": 362000
},
{
"epoch": 194.34063000533902,
"learning_rate": 1.7609894999110163e-05,
"loss": 0.0006235828399658203,
"step": 364000
},
{
"epoch": 194.34063000533902,
"eval_loss": 0.2637020945549011,
"eval_micro_f1": 0.8618615918166135,
"step": 364000
},
{
"epoch": 195.40843566470903,
"learning_rate": 1.7431927389215165e-05,
"loss": 0.0006297585368156433,
"step": 366000
},
{
"epoch": 195.40843566470903,
"eval_loss": 0.2516058683395386,
"eval_micro_f1": 0.8608507565294862,
"step": 366000
},
{
"epoch": 196.476241324079,
"learning_rate": 1.7253959779320163e-05,
"loss": 0.0005582793951034546,
"step": 368000
},
{
"epoch": 196.476241324079,
"eval_loss": 0.2577817738056183,
"eval_micro_f1": 0.8611385024134462,
"step": 368000
},
{
"epoch": 197.54404698344902,
"learning_rate": 1.7075992169425165e-05,
"loss": 0.0005150691270828247,
"step": 370000
},
{
"epoch": 197.54404698344902,
"eval_loss": 0.27647504210472107,
"eval_micro_f1": 0.8631899909801539,
"step": 370000
},
{
"epoch": 198.611852642819,
"learning_rate": 1.6898024559530164e-05,
"loss": 0.0005014644861221313,
"step": 372000
},
{
"epoch": 198.611852642819,
"eval_loss": 0.25295329093933105,
"eval_micro_f1": 0.8607174882891888,
"step": 372000
},
{
"epoch": 199.679658302189,
"learning_rate": 1.672005694963517e-05,
"loss": 0.0004670141637325287,
"step": 374000
},
{
"epoch": 199.679658302189,
"eval_loss": 0.2690587639808655,
"eval_micro_f1": 0.8636506576606826,
"step": 374000
},
{
"epoch": 200.747463961559,
"learning_rate": 1.654208933974017e-05,
"loss": 0.0006685220003128052,
"step": 376000
},
{
"epoch": 200.747463961559,
"eval_loss": 0.2624640166759491,
"eval_micro_f1": 0.8613905851988262,
"step": 376000
},
{
"epoch": 201.815269620929,
"learning_rate": 1.636412172984517e-05,
"loss": 0.00044568902254104616,
"step": 378000
},
{
"epoch": 201.815269620929,
"eval_loss": 0.26438939571380615,
"eval_micro_f1": 0.8606424977052595,
"step": 378000
},
{
"epoch": 202.88307528029898,
"learning_rate": 1.618615411995017e-05,
"loss": 0.00047568479180336,
"step": 380000
},
{
"epoch": 202.88307528029898,
"eval_loss": 0.27162355184555054,
"eval_micro_f1": 0.8608867343769877,
"step": 380000
},
{
"epoch": 203.950880939669,
"learning_rate": 1.600818651005517e-05,
"loss": 0.0004508922696113586,
"step": 382000
},
{
"epoch": 203.950880939669,
"eval_loss": 0.26971521973609924,
"eval_micro_f1": 0.8627680131646995,
"step": 382000
},
{
"epoch": 205.01868659903897,
"learning_rate": 1.583021890016017e-05,
"loss": 0.00036772269010543825,
"step": 384000
},
{
"epoch": 205.01868659903897,
"eval_loss": 0.28165990114212036,
"eval_micro_f1": 0.8636568843757687,
"step": 384000
},
{
"epoch": 206.08649225840898,
"learning_rate": 1.5652251290265172e-05,
"loss": 0.0004915898144245148,
"step": 386000
},
{
"epoch": 206.08649225840898,
"eval_loss": 0.2749684453010559,
"eval_micro_f1": 0.8618848961042639,
"step": 386000
},
{
"epoch": 207.15429791777896,
"learning_rate": 1.5474283680370174e-05,
"loss": 0.0005266410708427429,
"step": 388000
},
{
"epoch": 207.15429791777896,
"eval_loss": 0.26331204175949097,
"eval_micro_f1": 0.8622501679257206,
"step": 388000
},
{
"epoch": 208.22210357714897,
"learning_rate": 1.5296316070475176e-05,
"loss": 0.0005463905930519104,
"step": 390000
},
{
"epoch": 208.22210357714897,
"eval_loss": 0.2669012248516083,
"eval_micro_f1": 0.8612935139372812,
"step": 390000
},
{
"epoch": 209.28990923651895,
"learning_rate": 1.5118348460580176e-05,
"loss": 0.0005083644986152649,
"step": 392000
},
{
"epoch": 209.28990923651895,
"eval_loss": 0.267261803150177,
"eval_micro_f1": 0.8645931506152448,
"step": 392000
},
{
"epoch": 210.35771489588896,
"learning_rate": 1.4940380850685176e-05,
"loss": 0.0005148137807846069,
"step": 394000
},
{
"epoch": 210.35771489588896,
"eval_loss": 0.2742783725261688,
"eval_micro_f1": 0.8625370848186444,
"step": 394000
},
{
"epoch": 211.42552055525894,
"learning_rate": 1.4762413240790176e-05,
"loss": 0.0003343866765499115,
"step": 396000
},
{
"epoch": 211.42552055525894,
"eval_loss": 0.2746075391769409,
"eval_micro_f1": 0.8653975963677577,
"step": 396000
},
{
"epoch": 212.49332621462895,
"learning_rate": 1.4584445630895178e-05,
"loss": 0.0006268863677978515,
"step": 398000
},
{
"epoch": 212.49332621462895,
"eval_loss": 0.2550153136253357,
"eval_micro_f1": 0.8644235968298892,
"step": 398000
},
{
"epoch": 213.56113187399893,
"learning_rate": 1.4406478021000178e-05,
"loss": 0.0004940591752529144,
"step": 400000
},
{
"epoch": 213.56113187399893,
"eval_loss": 0.26624590158462524,
"eval_micro_f1": 0.8648868038653967,
"step": 400000
},
{
"epoch": 214.62893753336894,
"learning_rate": 1.4228510411105181e-05,
"loss": 0.0003400121033191681,
"step": 402000
},
{
"epoch": 214.62893753336894,
"eval_loss": 0.2809094488620758,
"eval_micro_f1": 0.8644159104274814,
"step": 402000
},
{
"epoch": 215.69674319273892,
"learning_rate": 1.4050542801210181e-05,
"loss": 0.00043562945723533633,
"step": 404000
},
{
"epoch": 215.69674319273892,
"eval_loss": 0.27504539489746094,
"eval_micro_f1": 0.8649986494864301,
"step": 404000
},
{
"epoch": 216.7645488521089,
"learning_rate": 1.3872575191315181e-05,
"loss": 0.0003887164890766144,
"step": 406000
},
{
"epoch": 216.7645488521089,
"eval_loss": 0.2783472239971161,
"eval_micro_f1": 0.8638994834577651,
"step": 406000
},
{
"epoch": 217.8323545114789,
"learning_rate": 1.3694607581420183e-05,
"loss": 0.0004151650667190552,
"step": 408000
},
{
"epoch": 217.8323545114789,
"eval_loss": 0.2731280028820038,
"eval_micro_f1": 0.8643854114765154,
"step": 408000
},
{
"epoch": 218.9001601708489,
"learning_rate": 1.3516639971525183e-05,
"loss": 0.0004558979868888855,
"step": 410000
},
{
"epoch": 218.9001601708489,
"eval_loss": 0.2704256772994995,
"eval_micro_f1": 0.8642207583585355,
"step": 410000
},
{
"epoch": 219.9679658302189,
"learning_rate": 1.3338672361630183e-05,
"loss": 0.0004397291541099548,
"step": 412000
},
{
"epoch": 219.9679658302189,
"eval_loss": 0.27709972858428955,
"eval_micro_f1": 0.8643116831482227,
"step": 412000
},
{
"epoch": 221.03577148958888,
"learning_rate": 1.3160704751735183e-05,
"loss": 0.0003247326612472534,
"step": 414000
},
{
"epoch": 221.03577148958888,
"eval_loss": 0.27233824133872986,
"eval_micro_f1": 0.8646657076235897,
"step": 414000
},
{
"epoch": 222.1035771489589,
"learning_rate": 1.2982737141840185e-05,
"loss": 0.0003739045858383179,
"step": 416000
},
{
"epoch": 222.1035771489589,
"eval_loss": 0.2822801470756531,
"eval_micro_f1": 0.8643754780819728,
"step": 416000
},
{
"epoch": 223.17138280832887,
"learning_rate": 1.2804769531945188e-05,
"loss": 0.00037060940265655517,
"step": 418000
},
{
"epoch": 223.17138280832887,
"eval_loss": 0.2810102701187134,
"eval_micro_f1": 0.8649908136774896,
"step": 418000
},
{
"epoch": 224.23918846769888,
"learning_rate": 1.2626801922050188e-05,
"loss": 0.0004138968288898468,
"step": 420000
},
{
"epoch": 224.23918846769888,
"eval_loss": 0.2606946527957916,
"eval_micro_f1": 0.8649672902736654,
"step": 420000
},
{
"epoch": 225.30699412706886,
"learning_rate": 1.2448834312155188e-05,
"loss": 0.00034263649582862854,
"step": 422000
},
{
"epoch": 225.30699412706886,
"eval_loss": 0.27102988958358765,
"eval_micro_f1": 0.8637733298349901,
"step": 422000
},
{
"epoch": 226.37479978643887,
"learning_rate": 1.2270866702260188e-05,
"loss": 0.00037757593393325804,
"step": 424000
},
{
"epoch": 226.37479978643887,
"eval_loss": 0.27292948961257935,
"eval_micro_f1": 0.862110796103254,
"step": 424000
},
{
"epoch": 227.44260544580885,
"learning_rate": 1.209289909236519e-05,
"loss": 0.00035303232073783877,
"step": 426000
},
{
"epoch": 227.44260544580885,
"eval_loss": 0.2717491686344147,
"eval_micro_f1": 0.8633138746683297,
"step": 426000
},
{
"epoch": 228.51041110517886,
"learning_rate": 1.1914931482470192e-05,
"loss": 0.00041042304039001467,
"step": 428000
},
{
"epoch": 228.51041110517886,
"eval_loss": 0.27461060881614685,
"eval_micro_f1": 0.8622850997864974,
"step": 428000
},
{
"epoch": 229.57821676454884,
"learning_rate": 1.1736963872575192e-05,
"loss": 0.00031202614307403566,
"step": 430000
},
{
"epoch": 229.57821676454884,
"eval_loss": 0.2826366424560547,
"eval_micro_f1": 0.8617674747274999,
"step": 430000
},
{
"epoch": 230.64602242391885,
"learning_rate": 1.1558996262680192e-05,
"loss": 0.0003741350769996643,
"step": 432000
},
{
"epoch": 230.64602242391885,
"eval_loss": 0.2795340418815613,
"eval_micro_f1": 0.8631759033313634,
"step": 432000
},
{
"epoch": 231.71382808328883,
"learning_rate": 1.1381028652785194e-05,
"loss": 0.0003092474043369293,
"step": 434000
},
{
"epoch": 231.71382808328883,
"eval_loss": 0.2903411388397217,
"eval_micro_f1": 0.8638599336184192,
"step": 434000
},
{
"epoch": 232.78163374265884,
"learning_rate": 1.1203061042890195e-05,
"loss": 0.0003111623525619507,
"step": 436000
},
{
"epoch": 232.78163374265884,
"eval_loss": 0.284820020198822,
"eval_micro_f1": 0.8625084435440618,
"step": 436000
},
{
"epoch": 233.84943940202882,
"learning_rate": 1.1025093432995196e-05,
"loss": 0.00029096254706382753,
"step": 438000
},
{
"epoch": 233.84943940202882,
"eval_loss": 0.29393354058265686,
"eval_micro_f1": 0.8625771843378935,
"step": 438000
},
{
"epoch": 234.91724506139883,
"learning_rate": 1.0847125823100196e-05,
"loss": 0.0003892621099948883,
"step": 440000
},
{
"epoch": 234.91724506139883,
"eval_loss": 0.2889274060726166,
"eval_micro_f1": 0.8631825127679008,
"step": 440000
},
{
"epoch": 235.9850507207688,
"learning_rate": 1.0669158213205197e-05,
"loss": 0.0003383939564228058,
"step": 442000
},
{
"epoch": 235.9850507207688,
"eval_loss": 0.28196001052856445,
"eval_micro_f1": 0.8629532974392814,
"step": 442000
},
{
"epoch": 237.05285638013882,
"learning_rate": 1.0491190603310199e-05,
"loss": 0.00029963040351867675,
"step": 444000
},
{
"epoch": 237.05285638013882,
"eval_loss": 0.28485849499702454,
"eval_micro_f1": 0.8609965938717079,
"step": 444000
},
{
"epoch": 238.1206620395088,
"learning_rate": 1.0313222993415199e-05,
"loss": 0.000265901654958725,
"step": 446000
},
{
"epoch": 238.1206620395088,
"eval_loss": 0.29056984186172485,
"eval_micro_f1": 0.8626091648911238,
"step": 446000
},
{
"epoch": 239.1884676988788,
"learning_rate": 1.01352553835202e-05,
"loss": 0.00029662206768989565,
"step": 448000
},
{
"epoch": 239.1884676988788,
"eval_loss": 0.27583956718444824,
"eval_micro_f1": 0.8637222267195064,
"step": 448000
},
{
"epoch": 240.2562733582488,
"learning_rate": 9.957287773625201e-06,
"loss": 0.0003406849205493927,
"step": 450000
},
{
"epoch": 240.2562733582488,
"eval_loss": 0.2796471416950226,
"eval_micro_f1": 0.865392398870295,
"step": 450000
},
{
"epoch": 241.3240790176188,
"learning_rate": 9.779320163730201e-06,
"loss": 0.0002823194861412048,
"step": 452000
},
{
"epoch": 241.3240790176188,
"eval_loss": 0.2789755165576935,
"eval_micro_f1": 0.8654208960950341,
"step": 452000
},
{
"epoch": 242.39188467698878,
"learning_rate": 9.601352553835203e-06,
"loss": 0.0002649376094341278,
"step": 454000
},
{
"epoch": 242.39188467698878,
"eval_loss": 0.28993353247642517,
"eval_micro_f1": 0.8642719052680415,
"step": 454000
},
{
"epoch": 243.4596903363588,
"learning_rate": 9.423384943940203e-06,
"loss": 0.00029733732342720033,
"step": 456000
},
{
"epoch": 243.4596903363588,
"eval_loss": 0.28820255398750305,
"eval_micro_f1": 0.8661883403071255,
"step": 456000
},
{
"epoch": 244.52749599572877,
"learning_rate": 9.245417334045204e-06,
"loss": 0.00022348684072494507,
"step": 458000
},
{
"epoch": 244.52749599572877,
"eval_loss": 0.28838109970092773,
"eval_micro_f1": 0.8649109421173817,
"step": 458000
},
{
"epoch": 245.59530165509878,
"learning_rate": 9.067449724150205e-06,
"loss": 0.00025971943140029905,
"step": 460000
},
{
"epoch": 245.59530165509878,
"eval_loss": 0.29757997393608093,
"eval_micro_f1": 0.8626572920529156,
"step": 460000
},
{
"epoch": 246.66310731446876,
"learning_rate": 8.889482114255206e-06,
"loss": 0.00026321738958358766,
"step": 462000
},
{
"epoch": 246.66310731446876,
"eval_loss": 0.2860535681247711,
"eval_micro_f1": 0.8655913973494201,
"step": 462000
},
{
"epoch": 247.73091297383877,
"learning_rate": 8.711514504360208e-06,
"loss": 0.00023912547528743744,
"step": 464000
},
{
"epoch": 247.73091297383877,
"eval_loss": 0.28043827414512634,
"eval_micro_f1": 0.8662265925216304,
"step": 464000
},
{
"epoch": 248.79871863320875,
"learning_rate": 8.533546894465208e-06,
"loss": 0.00022691623866558075,
"step": 466000
},
{
"epoch": 248.79871863320875,
"eval_loss": 0.29101118445396423,
"eval_micro_f1": 0.8660315161838972,
"step": 466000
},
{
"epoch": 249.86652429257876,
"learning_rate": 8.355579284570208e-06,
"loss": 0.00027305057644844057,
"step": 468000
},
{
"epoch": 249.86652429257876,
"eval_loss": 0.291027307510376,
"eval_micro_f1": 0.8656247188029134,
"step": 468000
},
{
"epoch": 250.93432995194874,
"learning_rate": 8.17761167467521e-06,
"loss": 0.00033196577429771425,
"step": 470000
},
{
"epoch": 250.93432995194874,
"eval_loss": 0.29175546765327454,
"eval_micro_f1": 0.8663159309716725,
"step": 470000
},
{
"epoch": 252.00213561131875,
"learning_rate": 7.999644064780212e-06,
"loss": 0.00022890016436576843,
"step": 472000
},
{
"epoch": 252.00213561131875,
"eval_loss": 0.28582608699798584,
"eval_micro_f1": 0.8657186566865019,
"step": 472000
},
{
"epoch": 253.06994127068873,
"learning_rate": 7.821676454885212e-06,
"loss": 0.00027167096734046934,
"step": 474000
},
{
"epoch": 253.06994127068873,
"eval_loss": 0.2900039553642273,
"eval_micro_f1": 0.8657600641290006,
"step": 474000
},
{
"epoch": 254.13774693005874,
"learning_rate": 7.643708844990212e-06,
"loss": 0.0002083786129951477,
"step": 476000
},
{
"epoch": 254.13774693005874,
"eval_loss": 0.2912232577800751,
"eval_micro_f1": 0.8684718662204941,
"step": 476000
},
{
"epoch": 255.20555258942872,
"learning_rate": 7.4657412350952126e-06,
"loss": 0.0002075246125459671,
"step": 478000
},
{
"epoch": 255.20555258942872,
"eval_loss": 0.29398486018180847,
"eval_micro_f1": 0.8660907122429112,
"step": 478000
},
{
"epoch": 256.27335824879873,
"learning_rate": 7.287773625200214e-06,
"loss": 0.000255573570728302,
"step": 480000
},
{
"epoch": 256.27335824879873,
"eval_loss": 0.2895210385322571,
"eval_micro_f1": 0.8654192150450923,
"step": 480000
},
{
"epoch": 257.3411639081687,
"learning_rate": 7.109806015305215e-06,
"loss": 0.0002233431786298752,
"step": 482000
},
{
"epoch": 257.3411639081687,
"eval_loss": 0.2900688350200653,
"eval_micro_f1": 0.8640816137282435,
"step": 482000
},
{
"epoch": 258.4089695675387,
"learning_rate": 6.931838405410215e-06,
"loss": 0.00025748267769813536,
"step": 484000
},
{
"epoch": 258.4089695675387,
"eval_loss": 0.28978070616722107,
"eval_micro_f1": 0.8662237380526454,
"step": 484000
},
{
"epoch": 259.4767752269087,
"learning_rate": 6.753870795515217e-06,
"loss": 0.00026493585109710696,
"step": 486000
},
{
"epoch": 259.4767752269087,
"eval_loss": 0.28252169489860535,
"eval_micro_f1": 0.8639437376660052,
"step": 486000
},
{
"epoch": 260.5445808862787,
"learning_rate": 6.575903185620218e-06,
"loss": 0.00020113718509674072,
"step": 488000
},
{
"epoch": 260.5445808862787,
"eval_loss": 0.29433611035346985,
"eval_micro_f1": 0.8659402264746473,
"step": 488000
},
{
"epoch": 261.6123865456487,
"learning_rate": 6.397935575725218e-06,
"loss": 0.000184002086520195,
"step": 490000
},
{
"epoch": 261.6123865456487,
"eval_loss": 0.294036865234375,
"eval_micro_f1": 0.8657536710018634,
"step": 490000
},
{
"epoch": 262.68019220501867,
"learning_rate": 6.21996796583022e-06,
"loss": 0.00018357382714748383,
"step": 492000
},
{
"epoch": 262.68019220501867,
"eval_loss": 0.3013167977333069,
"eval_micro_f1": 0.8634135367160337,
"step": 492000
},
{
"epoch": 263.7479978643887,
"learning_rate": 6.04200035593522e-06,
"loss": 0.00019059236347675323,
"step": 494000
},
{
"epoch": 263.7479978643887,
"eval_loss": 0.2986176609992981,
"eval_micro_f1": 0.8660907122429112,
"step": 494000
},
{
"epoch": 264.8158035237587,
"learning_rate": 5.8640327460402214e-06,
"loss": 0.0001792261153459549,
"step": 496000
},
{
"epoch": 264.8158035237587,
"eval_loss": 0.29999303817749023,
"eval_micro_f1": 0.8641096132376995,
"step": 496000
},
{
"epoch": 265.88360918312867,
"learning_rate": 5.6860651361452215e-06,
"loss": 0.00015837018191814422,
"step": 498000
},
{
"epoch": 265.88360918312867,
"eval_loss": 0.307789146900177,
"eval_micro_f1": 0.8663635949448588,
"step": 498000
},
{
"epoch": 266.95141484249865,
"learning_rate": 5.508097526250223e-06,
"loss": 0.0002700957357883453,
"step": 500000
},
{
"epoch": 266.95141484249865,
"eval_loss": 0.30223917961120605,
"eval_micro_f1": 0.8657159561331583,
"step": 500000
},
{
"epoch": 268.0192205018687,
"learning_rate": 5.330129916355223e-06,
"loss": 0.00020858097076416015,
"step": 502000
},
{
"epoch": 268.0192205018687,
"eval_loss": 0.2934473156929016,
"eval_micro_f1": 0.8676510303813547,
"step": 502000
},
{
"epoch": 269.08702616123867,
"learning_rate": 5.152162306460224e-06,
"loss": 0.00021539990603923798,
"step": 504000
},
{
"epoch": 269.08702616123867,
"eval_loss": 0.2963155210018158,
"eval_micro_f1": 0.8651071071453801,
"step": 504000
},
{
"epoch": 270.15483182060865,
"learning_rate": 4.974194696565225e-06,
"loss": 0.00025649312138557433,
"step": 506000
},
{
"epoch": 270.15483182060865,
"eval_loss": 0.2870093882083893,
"eval_micro_f1": 0.8662620808665342,
"step": 506000
},
{
"epoch": 271.22263747997863,
"learning_rate": 4.796227086670226e-06,
"loss": 0.00016110974550247192,
"step": 508000
},
{
"epoch": 271.22263747997863,
"eval_loss": 0.29277411103248596,
"eval_micro_f1": 0.8673162403512727,
"step": 508000
},
{
"epoch": 272.2904431393486,
"learning_rate": 4.618259476775228e-06,
"loss": 0.00013517826795578003,
"step": 510000
},
{
"epoch": 272.2904431393486,
"eval_loss": 0.2979615032672882,
"eval_micro_f1": 0.8668043824710203,
"step": 510000
},
{
"epoch": 273.35824879871865,
"learning_rate": 4.440291866880228e-06,
"loss": 0.0001818493753671646,
"step": 512000
},
{
"epoch": 273.35824879871865,
"eval_loss": 0.2921217978000641,
"eval_micro_f1": 0.8664058630729359,
"step": 512000
},
{
"epoch": 274.42605445808863,
"learning_rate": 4.2623242569852295e-06,
"loss": 0.00018301022052764893,
"step": 514000
},
{
"epoch": 274.42605445808863,
"eval_loss": 0.2982611060142517,
"eval_micro_f1": 0.8649643220776951,
"step": 514000
},
{
"epoch": 275.4938601174586,
"learning_rate": 4.0843566470902295e-06,
"loss": 0.00016295631229877472,
"step": 516000
},
{
"epoch": 275.4938601174586,
"eval_loss": 0.3031657338142395,
"eval_micro_f1": 0.8650177307923078,
"step": 516000
},
{
"epoch": 276.5616657768286,
"learning_rate": 3.9063890371952304e-06,
"loss": 0.00017553234100341797,
"step": 518000
},
{
"epoch": 276.5616657768286,
"eval_loss": 0.2996635437011719,
"eval_micro_f1": 0.8651660146861714,
"step": 518000
},
{
"epoch": 277.6294714361986,
"learning_rate": 3.7284214273002313e-06,
"loss": 0.00018722890317440032,
"step": 520000
},
{
"epoch": 277.6294714361986,
"eval_loss": 0.3086036145687103,
"eval_micro_f1": 0.8637649907410123,
"step": 520000
},
{
"epoch": 278.6972770955686,
"learning_rate": 3.5504538174052326e-06,
"loss": 0.0001714794486761093,
"step": 522000
},
{
"epoch": 278.6972770955686,
"eval_loss": 0.3072482943534851,
"eval_micro_f1": 0.8672064772327251,
"step": 522000
},
{
"epoch": 279.7650827549386,
"learning_rate": 3.372486207510233e-06,
"loss": 0.00018714405596256256,
"step": 524000
},
{
"epoch": 279.7650827549386,
"eval_loss": 0.3024003803730011,
"eval_micro_f1": 0.8678072935116343,
"step": 524000
},
{
"epoch": 280.83288841430857,
"learning_rate": 3.194518597615234e-06,
"loss": 0.00017753753066062928,
"step": 526000
},
{
"epoch": 280.83288841430857,
"eval_loss": 0.30150511860847473,
"eval_micro_f1": 0.8659152384539367,
"step": 526000
},
{
"epoch": 281.9006940736786,
"learning_rate": 3.016550987720235e-06,
"loss": 0.00016199514269828796,
"step": 528000
},
{
"epoch": 281.9006940736786,
"eval_loss": 0.30575352907180786,
"eval_micro_f1": 0.865300607471105,
"step": 528000
},
{
"epoch": 282.9684997330486,
"learning_rate": 2.838583377825236e-06,
"loss": 0.00014350686967372895,
"step": 530000
},
{
"epoch": 282.9684997330486,
"eval_loss": 0.30429428815841675,
"eval_micro_f1": 0.8668106546475187,
"step": 530000
},
{
"epoch": 284.03630539241857,
"learning_rate": 2.6606157679302367e-06,
"loss": 0.00016596193611621856,
"step": 532000
},
{
"epoch": 284.03630539241857,
"eval_loss": 0.30487513542175293,
"eval_micro_f1": 0.8677734282127577,
"step": 532000
},
{
"epoch": 285.10411105178855,
"learning_rate": 2.4826481580352376e-06,
"loss": 0.00013490228354930877,
"step": 534000
},
{
"epoch": 285.10411105178855,
"eval_loss": 0.30887937545776367,
"eval_micro_f1": 0.8666035945803424,
"step": 534000
},
{
"epoch": 286.1719167111586,
"learning_rate": 2.3046805481402385e-06,
"loss": 0.00015608370304107667,
"step": 536000
},
{
"epoch": 286.1719167111586,
"eval_loss": 0.30850809812545776,
"eval_micro_f1": 0.8673722129653629,
"step": 536000
},
{
"epoch": 287.23972237052857,
"learning_rate": 2.12671293824524e-06,
"loss": 0.0001617339700460434,
"step": 538000
},
{
"epoch": 287.23972237052857,
"eval_loss": 0.30749472975730896,
"eval_micro_f1": 0.8668948121800428,
"step": 538000
},
{
"epoch": 288.30752802989855,
"learning_rate": 1.9487453283502407e-06,
"loss": 0.00015108080208301545,
"step": 540000
},
{
"epoch": 288.30752802989855,
"eval_loss": 0.306765615940094,
"eval_micro_f1": 0.8673906181634681,
"step": 540000
},
{
"epoch": 289.37533368926853,
"learning_rate": 1.7707777184552414e-06,
"loss": 0.0001665029525756836,
"step": 542000
},
{
"epoch": 289.37533368926853,
"eval_loss": 0.30816134810447693,
"eval_micro_f1": 0.8669462098791115,
"step": 542000
},
{
"epoch": 290.44313934863857,
"learning_rate": 1.5928101085602423e-06,
"loss": 0.00014112387597560883,
"step": 544000
},
{
"epoch": 290.44313934863857,
"eval_loss": 0.3074408173561096,
"eval_micro_f1": 0.8675630700580119,
"step": 544000
},
{
"epoch": 291.51094500800855,
"learning_rate": 1.414842498665243e-06,
"loss": 0.0001450287103652954,
"step": 546000
},
{
"epoch": 291.51094500800855,
"eval_loss": 0.30664122104644775,
"eval_micro_f1": 0.867841409191565,
"step": 546000
},
{
"epoch": 292.57875066737853,
"learning_rate": 1.2368748887702438e-06,
"loss": 0.0001562301069498062,
"step": 548000
},
{
"epoch": 292.57875066737853,
"eval_loss": 0.30733898282051086,
"eval_micro_f1": 0.8681961308539576,
"step": 548000
},
{
"epoch": 293.6465563267485,
"learning_rate": 1.0589072788752447e-06,
"loss": 0.00013716380298137664,
"step": 550000
},
{
"epoch": 293.6465563267485,
"eval_loss": 0.30761826038360596,
"eval_micro_f1": 0.8687713612556442,
"step": 550000
},
{
"epoch": 294.71436198611855,
"learning_rate": 8.809396689802456e-07,
"loss": 0.00013557393848896026,
"step": 552000
},
{
"epoch": 294.71436198611855,
"eval_loss": 0.30773961544036865,
"eval_micro_f1": 0.8688495092597597,
"step": 552000
}
],
"max_steps": 561900,
"num_train_epochs": 300,
"total_flos": 1077054995569967520,
"trial_name": null,
"trial_params": null
}
{
"best_metric": 0.8688495092597597,
"best_model_checkpoint": "../out/onto_final/ner-roberta-bioe-char-pattern3-subtext-dim50/checkpoints/checkpoint-552000",
"epoch": 294.71436198611855,
"global_step": 552000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0678056593699947,
"learning_rate": 4.982203239010501e-05,
"loss": 0.1441604766845703,
"step": 2000
},
{
"epoch": 1.0678056593699947,
"eval_loss": 0.09690555930137634,
"eval_micro_f1": 0.8483981943974436,
"step": 2000
},
{
"epoch": 2.1356113187399894,
"learning_rate": 4.9644064780210006e-05,
"loss": 0.07054872894287109,
"step": 4000
},
{
"epoch": 2.1356113187399894,
"eval_loss": 0.10765556246042252,
"eval_micro_f1": 0.8489558032884322,
"step": 4000
},
{
"epoch": 3.203416978109984,
"learning_rate": 4.9466097170315004e-05,
"loss": 0.0522383918762207,
"step": 6000
},
{
"epoch": 3.203416978109984,
"eval_loss": 0.10142778605222702,
"eval_micro_f1": 0.858142664372088,
"step": 6000
},
{
"epoch": 4.271222637479979,
"learning_rate": 4.928812956042e-05,
"loss": 0.041123741149902346,
"step": 8000
},
{
"epoch": 4.271222637479979,
"eval_loss": 0.10864394158124924,
"eval_micro_f1": 0.8591757277856453,
"step": 8000
},
{
"epoch": 5.339028296849973,
"learning_rate": 4.911016195052501e-05,
"loss": 0.03384337615966797,
"step": 10000
},
{
"epoch": 5.339028296849973,
"eval_loss": 0.1240122839808464,
"eval_micro_f1": 0.8540363018122469,
"step": 10000
},
{
"epoch": 6.406833956219968,
"learning_rate": 4.8932194340630006e-05,
"loss": 0.027656402587890625,
"step": 12000
},
{
"epoch": 6.406833956219968,
"eval_loss": 0.12531153857707977,
"eval_micro_f1": 0.8595292326055319,
"step": 12000
},
{
"epoch": 7.474639615589963,
"learning_rate": 4.875422673073501e-05,
"loss": 0.023082820892333985,
"step": 14000
},
{
"epoch": 7.474639615589963,
"eval_loss": 0.1331861913204193,
"eval_micro_f1": 0.8607068602067829,
"step": 14000
},
{
"epoch": 8.542445274959958,
"learning_rate": 4.857625912084001e-05,
"loss": 0.019628978729248046,
"step": 16000
},
{