CoolFace
Modelpublic

CLMBR/binding-case-lstm-3

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes119downloads
README.md95 linesDownload Raw Back to root
1---2tags:3- generated_from_trainer4model-index:5- name: binding-case-lstm-36  results: []7---8 9<!-- This model card has been generated automatically according to the information the Trainer had access to. You10should probably proofread and complete it, then remove this comment. -->11 12# binding-case-lstm-313 14This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.15It achieves the following results on the evaluation set:16- Loss: 3.974817 18## Model description19 20More information needed21 22## Intended uses & limitations23 24More information needed25 26## Training and evaluation data27 28More information needed29 30## Training procedure31 32### Training hyperparameters33 34The following hyperparameters were used during training:35- learning_rate: 5e-0536- train_batch_size: 3237- eval_batch_size: 3238- seed: 339- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0840- lr_scheduler_type: linear41- training_steps: 305272642 43### Training results44 45| Training Loss | Epoch | Step    | Validation Loss |46|:-------------:|:-----:|:-------:|:---------------:|47| 4.793         | 0.03  | 76320   | 4.7610          |48| 4.5078        | 1.03  | 152640  | 4.4815          |49| 4.3662        | 0.03  | 228960  | 4.3454          |50| 4.2772        | 1.03  | 305280  | 4.2625          |51| 4.2165        | 0.03  | 381600  | 4.2062          |52| 4.1704        | 0.03  | 457920  | 4.1645          |53| 4.1336        | 1.03  | 534240  | 4.1334          |54| 4.0998        | 0.03  | 610560  | 4.1087          |55| 4.0754        | 0.03  | 686880  | 4.0897          |56| 4.0505        | 1.03  | 763200  | 4.0733          |57| 4.0282        | 0.03  | 839520  | 4.0602          |58| 4.0115        | 1.03  | 915840  | 4.0487          |59| 3.9943        | 0.03  | 992160  | 4.0396          |60| 3.9766        | 1.03  | 1068480 | 4.0313          |61| 3.9675        | 0.03  | 1144800 | 4.0246          |62| 3.9447        | 1.03  | 1221120 | 4.0192          |63| 3.9354        | 0.03  | 1297440 | 4.0142          |64| 3.9278        | 1.03  | 1373760 | 4.0092          |65| 3.918         | 0.03  | 1450080 | 4.0055          |66| 3.9146        | 1.03  | 1526400 | 4.0013          |67| 3.9107        | 0.03  | 1602720 | 3.9987          |68| 3.9089        | 1.03  | 1679040 | 3.9956          |69| 3.9035        | 0.03  | 1755360 | 3.9926          |70| 3.898         | 1.03  | 1831680 | 3.9903          |71| 3.8927        | 0.03  | 1908000 | 3.9885          |72| 3.8853        | 1.03  | 1984320 | 3.9868          |73| 3.8795        | 0.03  | 2060640 | 3.9850          |74| 3.876         | 0.03  | 2136960 | 3.9838          |75| 3.871         | 1.03  | 2213280 | 3.9824          |76| 3.8615        | 0.03  | 2289600 | 3.9814          |77| 3.8613        | 1.03  | 2365920 | 3.9803          |78| 3.8485        | 0.03  | 2442240 | 3.9792          |79| 3.8443        | 1.03  | 2518560 | 3.9786          |80| 3.8438        | 0.03  | 2594880 | 3.9778          |81| 3.8407        | 0.03  | 2671200 | 3.9770          |82| 3.842         | 1.03  | 2747520 | 3.9764          |83| 3.8433        | 0.03  | 2823840 | 3.9758          |84| 3.8447        | 0.03  | 2900160 | 3.9755          |85| 3.8456        | 0.03  | 2976480 | 3.9751          |86| 3.8445        | 0.02  | 3052726 | 3.9748          |87 88 89### Framework versions90 91- Transformers 4.33.392- Pytorch 2.0.193- Datasets 2.12.094- Tokenizers 0.13.395