Modelpublic
ferrazzipietro/meshTask-Llama-3.1-8B-Instruct-ood
0likes5downloads
Model Card
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
meshTask-Llama-3.1-8B-Instruct-ood
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- —Loss: 1.4728
- —F1 Micro: 0.8766
- —F1 Macro: 0.4409
- —F1 Weighted: 0.8834
- —Class/f1 Results Per Class: {}
- —Items/f1 Scores Per Item: {'Cross-Sectional Studies': 0.9161047982774608, 'Child, Preschool': 0.4422286821705427, 'Cell Proliferation': 0.5710828796128252, 'Reproducibility of Results': 0.42560399159663864, 'Child': 0.45245650508808405, 'Aged, 80 and over': 0.5312671317038129, 'Infant': 0.5676868327402135, 'Follow-Up Studies': 0.4372727814530067, 'Middle Aged': 0.7584534368070954, 'Prospective Studies': 0.5736941223114282, 'Young Adult': 0.32530224030252675, 'Retrospective Studies': 0.8819871460830293, 'Adult': 0.4228110599078341, 'Female': 0.355709423058086, 'Rats': 1.0}
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- —learning_rate: 0.0003
- —trainbatchsize: 32
- —evalbatchsize: 32
- —seed: 42
- —distributed_type: multi-GPU
- —gradientaccumulationsteps: 4
- —totaltrainbatch_size: 128
- —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-07 and optimizerargs=No additional optimizer arguments
- —lrschedulertype: cosine
- —lrschedulerwarmup_ratio: 0.1
- —num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | F1 Weighted | Class/f1 Results Per Class | Items/f1 Scores Per Item |
|---|---|---|---|---|---|---|---|---|
| 6.5938 | 0.0517 | 20 | 1.6309 | 0.6452 | 0.0429 | 0.6357 | {} | {'Cross-Sectional Studies': 0.20640526564795525, 'Child, Preschool': 0.3825551271851988, 'Cell Proliferation': 0.2120473372781065, 'Reproducibility of Results': 0.028241215097209064, 'Child': 0.4230357068850168, 'Aged, 80 and over': 0.27159150560725365, 'Infant': 0.19748171235021206, 'Follow-Up Studies': 0.07899971582836032, 'Prospective Studies': 0.2204861111111111, 'Middle Aged': 0.3026921463772675, 'Young Adult': 0.16272185158430005, 'Retrospective Studies': 0.3179988499137435, 'Adult': 0.15460667278849097, 'Female': 0.2439232997654849, 'Rats': 0.5215171183364606} |
| 5.7938 | 0.1034 | 40 | 1.5106 | 0.8639 | 0.8590 | 0.8628 | {} | {'Cross-Sectional Studies': 0.8039878849066129, 'Child, Preschool': 0.8649521999217309, 'Cell Proliferation': 0.7691392733564013, 'Reproducibility of Results': 0.7126558005752637, 'Child': 0.8813025210084033, 'Aged, 80 and over': 0.6334823646299056, 'Infant': 0.7625563552954204, 'Follow-Up Studies': 0.6942572020335154, 'Prospective Studies': 0.7934658278524449, 'Middle Aged': 0.7734291084854994, 'Young Adult': 0.7042913225937457, 'Retrospective Studies': 0.8658747110629956, 'Adult': 0.7435790873576593, 'Female': 0.6710811984368215, 'Rats': 0.7685536500227652} |
| 5.7125 | 0.1551 | 60 | 1.4978 | 0.8627 | 0.4312 | 0.8637 | {} | {'Cross-Sectional Studies': 0.7938470353597127, 'Child, Preschool': 0.8320977686435702, 'Cell Proliferation': 0.8021193771626298, 'Reproducibility of Results': 0.5012634178778379, 'Child': 0.880801687763713, 'Aged, 80 and over': 0.7130778627917443, 'Infant': 0.8695707391414782, 'Follow-Up Studies': 0.6724904510018918, 'Prospective Studies': 0.8401111878785932, 'Middle Aged': 0.7072401160451475, 'Young Adult': 0.3482505705865408, 'Retrospective Studies': 0.892454954954955, 'Adult': 0.6937965260545906, 'Female': 0.6500234129373202, 'Rats': 0.7449832775919732} |
| 5.65 | 0.2069 | 80 | 1.4931 | 0.8792 | 0.5856 | 0.8799 | {} | {'Cross-Sectional Studies': 0.8157452795933188, 'Child, Preschool': 0.8969884604559527, 'Cell Proliferation': 0.7790963284862666, 'Reproducibility of Results': 0.5175438596491228, 'Child': 0.8910108024691358, 'Aged, 80 and over': 0.7376886369692125, 'Infant': 0.891296869625043, 'Follow-Up Studies': 0.6832134734771651, 'Prospective Studies': 0.84425540173373, 'Middle Aged': 0.7699979383568705, 'Young Adult': 0.6123388806315635, 'Retrospective Studies': 0.8980073634805092, 'Adult': 0.7788530465949821, 'Female': 0.6653166421207658, 'Rats': 0.7449832775919732} |
| 5.6406 | 0.2586 | 100 | 1.4904 | 0.8907 | 0.5929 | 0.8912 | {} | {'Cross-Sectional Studies': 0.8342477263740609, 'Child, Preschool': 0.8995694022289766, 'Cell Proliferation': 0.789655172413793, 'Reproducibility of Results': 0.5036731444287627, 'Child': 0.9036847626540782, 'Aged, 80 and over': 0.7761945103354795, 'Infant': 0.8957989843698477, 'Follow-Up Studies': 0.7071654903240722, 'Prospective Studies': 0.84425540173373, 'Middle Aged': 0.7856084939872858, 'Young Adult': 0.6668705402650357, 'Retrospective Studies': 0.9002533539403947, 'Adult': 0.7929193279362109, 'Female': 0.6943596785677958, 'Rats': 0.7685536500227652} |
| 5.6125 | 0.3103 | 120 | 1.4879 | 0.8975 | 0.5964 | 0.8972 | {} | {'Cross-Sectional Studies': 0.8101363084535829, 'Child, Preschool': 0.9030258067934926, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.41983273596176823, 'Child': 0.9057883210867415, 'Aged, 80 and over': 0.782908856774932, 'Infant': 0.863978764617261, 'Follow-Up Studies': 0.6750460274748619, 'Prospective Studies': 0.8441531419059509, 'Middle Aged': 0.7894412779827034, 'Young Adult': 0.7323134720214799, 'Retrospective Studies': 0.892320479924831, 'Adult': 0.823256378510912, 'Female': 0.7215164943377647, 'Rats': 0.7966666666666666} |
| 5.6109 | 0.3620 | 140 | 1.4857 | 0.8922 | 0.5923 | 0.8915 | {} | {'Cross-Sectional Studies': 0.8032329988851727, 'Child, Preschool': 0.895267871336972, 'Cell Proliferation': 0.8449152542372882, 'Reproducibility of Results': 0.4295485322132709, 'Child': 0.8967827057748909, 'Aged, 80 and over': 0.7938055014078407, 'Infant': 0.8067721470610716, 'Follow-Up Studies': 0.6494924977934686, 'Prospective Studies': 0.8531047592227542, 'Middle Aged': 0.7951799284572144, 'Young Adult': 0.6920720958928257, 'Retrospective Studies': 0.8669078347504429, 'Adult': 0.8215790845955107, 'Female': 0.7301011643443405, 'Rats': 0.8308374930671103} |
| 5.6297 | 0.4137 | 160 | 1.4847 | 0.9006 | 0.5992 | 0.9008 | {} | {'Cross-Sectional Studies': 0.8473711518505708, 'Child, Preschool': 0.8969884604559527, 'Cell Proliferation': 0.8113790970933827, 'Reproducibility of Results': 0.471410047266491, 'Child': 0.9043204515848893, 'Aged, 80 and over': 0.7843045112781954, 'Infant': 0.8898680607418472, 'Follow-Up Studies': 0.6750460274748619, 'Prospective Studies': 0.8657510413704268, 'Middle Aged': 0.7850226418730128, 'Young Adult': 0.7444091199101315, 'Retrospective Studies': 0.9007276507276507, 'Adult': 0.8172659414797228, 'Female': 0.7344456156931167, 'Rats': 0.7966666666666666} |
| 5.6406 | 0.4654 | 180 | 1.4837 | 0.9036 | 0.6011 | 0.9037 | {} | {'Cross-Sectional Studies': 0.8236202589143766, 'Child, Preschool': 0.8969884604559527, 'Cell Proliferation': 0.8418635656618028, 'Reproducibility of Results': 0.48160480124964034, 'Child': 0.9195642795513373, 'Aged, 80 and over': 0.808961953804181, 'Infant': 0.8793793046220231, 'Follow-Up Studies': 0.6783168051460735, 'Prospective Studies': 0.8702156334231805, 'Middle Aged': 0.790167865707434, 'Young Adult': 0.7548637055486371, 'Retrospective Studies': 0.8952125202125202, 'Adult': 0.8287470261697065, 'Female': 0.7344456156931167, 'Rats': 0.8308374930671103} |
| 5.6203 | 0.5171 | 200 | 1.4825 | 0.9036 | 0.6008 | 0.9035 | {} | {'Cross-Sectional Studies': 0.8349503214494447, 'Child, Preschool': 0.8865480198813531, 'Cell Proliferation': 0.858534322820037, 'Reproducibility of Results': 0.5009438648782911, 'Child': 0.91168041684759, 'Aged, 80 and over': 0.779355195793552, 'Infant': 0.8883861744176268, 'Follow-Up Studies': 0.689844086484624, 'Prospective Studies': 0.8702156334231805, 'Middle Aged': 0.8035744302438442, 'Young Adult': 0.7590459765737633, 'Retrospective Studies': 0.9004776378636561, 'Adult': 0.8296877974490767, 'Female': 0.7615996762881035, 'Rats': 0.8308374930671103} |
| 5.5531 | 0.5688 | 220 | 1.4817 | 0.9026 | 0.6007 | 0.9029 | {} | {'Cross-Sectional Studies': 0.8494027303754266, 'Child, Preschool': 0.8986201590151321, 'Cell Proliferation': 0.8418635656618028, 'Reproducibility of Results': 0.511122298670545, 'Child': 0.9167031675658351, 'Aged, 80 and over': 0.7949208200080595, 'Infant': 0.8824537853180443, 'Follow-Up Studies': 0.6832901664042794, 'Prospective Studies': 0.8702156334231805, 'Middle Aged': 0.7804449648711944, 'Young Adult': 0.7261476496204624, 'Retrospective Studies': 0.8952125202125202, 'Adult': 0.8433799704349644, 'Female': 0.7469698415728192, 'Rats': 0.7685536500227652} |
| 5.5984 | 0.6206 | 240 | 1.4808 | 0.9016 | 0.6002 | 0.9020 | {} | {'Cross-Sectional Studies': 0.8473971189111548, 'Child, Preschool': 0.9035005881637124, 'Cell Proliferation': 0.8418635656618028, 'Reproducibility of Results': 0.5036731444287627, 'Child': 0.9200745884773662, 'Aged, 80 and over': 0.7896464646464647, 'Infant': 0.8868489583333333, 'Follow-Up Studies': 0.6874044019385275, 'Prospective Studies': 0.8764909580607927, 'Middle Aged': 0.7860926252886052, 'Young Adult': 0.7162790964536321, 'Retrospective Studies': 0.8954690785494138, 'Adult': 0.8417364360174013, 'Female': 0.7469698415728192, 'Rats': 0.7685536500227652} |
| 5.6125 | 0.6723 | 260 | 1.4805 | 0.9051 | 0.6019 | 0.9051 | {} | {'Cross-Sectional Studies': 0.8412055780476833, 'Child, Preschool': 0.8943722943722943, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.511122298670545, 'Child': 0.9098723856788373, 'Aged, 80 and over': 0.7999719848718307, 'Infant': 0.8679205851619645, 'Follow-Up Studies': 0.6718237471276465, 'Prospective Studies': 0.8702156334231805, 'Middle Aged': 0.8049601477011753, 'Young Adult': 0.7706591779867642, 'Retrospective Studies': 0.8975819366245661, 'Adult': 0.8332788167531822, 'Female': 0.7728174273399151, 'Rats': 0.8308374930671103} |
| 5.6219 | 0.7240 | 280 | 1.4798 | 0.9071 | 0.6034 | 0.9072 | {} | {'Cross-Sectional Studies': 0.8414551987424208, 'Child, Preschool': 0.8943722943722943, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.507346189164371, 'Child': 0.9023617511520737, 'Aged, 80 and over': 0.8077444235980822, 'Infant': 0.8659881255301103, 'Follow-Up Studies': 0.68092059518843, 'Prospective Studies': 0.8764909580607927, 'Middle Aged': 0.8035714285714286, 'Young Adult': 0.7841789416257501, 'Retrospective Studies': 0.9036042076727302, 'Adult': 0.8388878143133462, 'Female': 0.77749303120223, 'Rats': 0.8308374930671103} |
| 5.6234 | 0.7757 | 300 | 1.4796 | 0.9090 | 0.6045 | 0.9089 | {} | {'Cross-Sectional Studies': 0.8454050999505545, 'Child, Preschool': 0.8943722943722943, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.511122298670545, 'Child': 0.9098723856788373, 'Aged, 80 and over': 0.8131362356508556, 'Infant': 0.8614205273036645, 'Follow-Up Studies': 0.68092059518843, 'Prospective Studies': 0.8810309973045822, 'Middle Aged': 0.8063207083128381, 'Young Adult': 0.7942091409428094, 'Retrospective Studies': 0.9007276507276507, 'Adult': 0.8425057673876504, 'Female': 0.7728174273399151, 'Rats': 0.8308374930671103} |
| 5.6391 | 0.8274 | 320 | 1.4794 | 0.9086 | 0.6045 | 0.9087 | {} | {'Cross-Sectional Studies': 0.843476333000776, 'Child, Preschool': 0.8987185491080931, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.507346189164371, 'Child': 0.9057883210867415, 'Aged, 80 and over': 0.8069933728636205, 'Infant': 0.8743234597361277, 'Follow-Up Studies': 0.689844086484624, 'Prospective Studies': 0.8720095693779905, 'Middle Aged': 0.8035714285714286, 'Young Adult': 0.7866167881818529, 'Retrospective Studies': 0.9152223248355205, 'Adult': 0.8412303061199717, 'Female': 0.77749303120223, 'Rats': 0.8308374930671103} |
| 5.5703 | 0.8791 | 340 | 1.4792 | 0.9090 | 0.6047 | 0.9090 | {} | {'Cross-Sectional Studies': 0.8473971189111548, 'Child, Preschool': 0.8995694022289766, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.511122298670545, 'Child': 0.906441463818513, 'Aged, 80 and over': 0.8042643923240937, 'Infant': 0.8633950649305735, 'Follow-Up Studies': 0.689844086484624, 'Prospective Studies': 0.8764909580607927, 'Middle Aged': 0.7976190476190477, 'Young Adult': 0.7978837366913709, 'Retrospective Studies': 0.9093321825439638, 'Adult': 0.8422987692186701, 'Female': 0.77749303120223, 'Rats': 0.8308374930671103} |
| 5.5828 | 0.9308 | 360 | 1.4790 | 0.9096 | 0.6052 | 0.9097 | {} | {'Cross-Sectional Studies': 0.8454050999505545, 'Child, Preschool': 0.9080594515386226, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.511122298670545, 'Child': 0.906441463818513, 'Aged, 80 and over': 0.8139462163852408, 'Infant': 0.8697802197802198, 'Follow-Up Studies': 0.68092059518843, 'Prospective Studies': 0.8764909580607927, 'Middle Aged': 0.7976190476190477, 'Young Adult': 0.7976846988795518, 'Retrospective Studies': 0.9038371633042039, 'Adult': 0.8422987692186701, 'Female': 0.7823002794092491, 'Rats': 0.8308374930671103} |
| 5.5438 | 0.9825 | 380 | 1.4791 | 0.9090 | 0.6047 | 0.9090 | {} | {'Cross-Sectional Studies': 0.8454050999505545, 'Child, Preschool': 0.9038330162800718, 'Cell Proliferation': 0.8273910582908885, 'Reproducibility of Results': 0.511122298670545, 'Child': 0.906441463818513, 'Aged, 80 and over': 0.8077444235980822, 'Infant': 0.8697802197802198, 'Follow-Up Studies': 0.68092059518843, 'Prospective Studies': 0.8764909580607927, 'Middle Aged': 0.7961584140325233, 'Young Adult': 0.8001367053998634, 'Retrospective Studies': 0.9009707059941815, 'Adult': 0.8422987692186701, 'Female': 0.77749303120223, 'Rats': 0.8308374930671103} |
Framework versions
- —PEFT 0.18.1
- —Transformers 4.51.0
- —Pytorch 2.8.0+cu128
- —Datasets 3.6.0
- —Tokenizers 0.21.0