wins1502
/

MLMA_biogpt_tuned_1412

Token Classification

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

wins1502 commited on Apr 13

Commit

43555dd

•

1 Parent(s): 3108f45

Training complete

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1569
-- Precision: 0.4752
-- Recall: 0.5541
-- F1: 0.5116
-- Accuracy: 0.9544
 ## Model description
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.3317 | 1.0 | 679 | 0.1753 | 0.3832 | 0.4923 | 0.4309 | 0.9436 |
-| 0.1765 | 2.0 | 1358 | 0.1625 | 0.4394 | 0.5531 | 0.4897 | 0.9496 |
-| 0.1057 | 3.0 | 2037 | 0.1569 | 0.4752 | 0.5541 | 0.5116 | 0.9544 |
 ### Framework versions

 This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1566
+- Precision: 0.4828
+- Recall: 0.5685
+- F1: 0.5222
+- Accuracy: 0.9542
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.329 | 1.0 | 679 | 0.1783 | 0.375 | 0.5154 | 0.4341 | 0.9407 |
+| 0.1756 | 2.0 | 1358 | 0.1703 | 0.4751 | 0.5521 | 0.5107 | 0.9520 |
+| 0.1045 | 3.0 | 2037 | 0.1566 | 0.4828 | 0.5685 | 0.5222 | 0.9542 |
 ### Framework versions