CoolFace
Modelpublic

CLMBR/binding-case-transformer-2

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes82downloads
README.md95 linesDownload Raw Back to root
1---2tags:3- generated_from_trainer4model-index:5- name: binding-case-transformer-26  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-transformer-213 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: 3.866517 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: 239- 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| 4.2236        | 0.03  | 76320   | 4.1964          |48| 4.0182        | 1.03  | 152640  | 4.0272          |49| 3.91          | 0.03  | 228960  | 3.9534          |50| 3.8414        | 1.03  | 305280  | 3.9119          |51| 3.7918        | 0.03  | 381600  | 3.8873          |52| 3.7502        | 0.03  | 457920  | 3.8712          |53| 3.7204        | 1.03  | 534240  | 3.8612          |54| 3.6869        | 0.03  | 610560  | 3.8549          |55| 3.6592        | 1.03  | 686880  | 3.8507          |56| 3.635         | 0.03  | 763200  | 3.8488          |57| 3.6105        | 1.03  | 839520  | 3.8465          |58| 3.5921        | 0.03  | 915840  | 3.8457          |59| 3.571         | 1.03  | 992160  | 3.8463          |60| 3.5534        | 0.03  | 1068480 | 3.8462          |61| 3.5396        | 1.03  | 1144800 | 3.8481          |62| 3.5192        | 0.03  | 1221120 | 3.8492          |63| 3.5044        | 1.03  | 1297440 | 3.8499          |64| 3.4927        | 0.03  | 1373760 | 3.8517          |65| 3.4786        | 1.03  | 1450080 | 3.8538          |66| 3.4707        | 0.03  | 1526400 | 3.8534          |67| 3.4625        | 1.03  | 1602720 | 3.8559          |68| 3.4549        | 0.03  | 1679040 | 3.8577          |69| 3.4471        | 1.03  | 1755360 | 3.8590          |70| 3.4355        | 0.03  | 1831680 | 3.8603          |71| 3.4219        | 1.03  | 1908000 | 3.8616          |72| 3.4109        | 0.03  | 1984320 | 3.8622          |73| 3.4003        | 1.03  | 2060640 | 3.8631          |74| 3.3907        | 0.03  | 2136960 | 3.8647          |75| 3.376         | 0.03  | 2213280 | 3.8675          |76| 3.3656        | 1.03  | 2289600 | 3.8681          |77| 3.3573        | 0.03  | 2365920 | 3.8685          |78| 3.341         | 1.03  | 2442240 | 3.8701          |79| 3.33          | 0.03  | 2518560 | 3.8698          |80| 3.3222        | 1.03  | 2594880 | 3.8702          |81| 3.3137        | 0.03  | 2671200 | 3.8703          |82| 3.3096        | 1.03  | 2747520 | 3.8693          |83| 3.3045        | 0.03  | 2823840 | 3.8692          |84| 3.2982        | 0.03  | 2900160 | 3.8688          |85| 3.2947        | 1.03  | 2976480 | 3.8677          |86| 3.2868        | 0.02  | 3052726 | 3.8665          |87 88 89### Framework versions90 91- Transformers 4.33.392- Pytorch 2.0.193- Datasets 2.12.094- Tokenizers 0.13.395