jikkyjohn
/

roberta-base-finetuned-dapt-hotqa-v3-squad

Question Answering

generated_from_keras_callback

Inference Endpoints

Model card Files Files and versions Community

jikkyjohn commited on May 30, 2023

Commit

676df63

•

1 Parent(s): d0d98d6

Training in progress epoch 0

Files changed (3) hide show

README.md +8 -8
config.json +1 -1
tf_model.h5 +1 -1

README.md CHANGED Viewed

@@ -11,14 +11,14 @@ probably proofread and complete it, then remove this comment. -->
 # jikkyjohn/roberta-base-finetuned-dapt-hotqa-v3-squad
-This model is a fine-tuned version of [jikkyjohn/roberta-base-MLM-retrainedonHotQA](https://huggingface.co/jikkyjohn/roberta-base-MLM-retrainedonHotQA) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.2221
-- Train End Logits Accuracy: 0.6817
-- Train Start Logits Accuracy: 0.6389
-- Validation Loss: 0.9468
-- Validation End Logits Accuracy: 0.7485
-- Validation Start Logits Accuracy: 0.7098
 - Epoch: 0
 ## Model description
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
-| 1.2221     | 0.6817                    | 0.6389                      | 0.9468          | 0.7485                         | 0.7098                           | 0     |
 ### Framework versions

 # jikkyjohn/roberta-base-finetuned-dapt-hotqa-v3-squad
+This model is a fine-tuned version of [jikkyjohn/roberta-base-finetuned-dapt-hotqa-v3-squad](https://huggingface.co/jikkyjohn/roberta-base-finetuned-dapt-hotqa-v3-squad) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 0.8094
+- Train End Logits Accuracy: 0.7766
+- Train Start Logits Accuracy: 0.7335
+- Validation Loss: 0.9129
+- Validation End Logits Accuracy: 0.7572
+- Validation Start Logits Accuracy: 0.7202
 - Epoch: 0
 ## Model description
 | Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
+| 0.8094     | 0.7766                    | 0.7335                      | 0.9129          | 0.7572                         | 0.7202                           | 0     |
 ### Framework versions

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "jikkyjohn/roberta-base-MLM-retrainedonHotQA",
   "architectures": [
     "RobertaForQuestionAnswering"
   ],

 {
+  "_name_or_path": "jikkyjohn/roberta-base-finetuned-dapt-hotqa-v3-squad",
   "architectures": [
     "RobertaForQuestionAnswering"
   ],

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe36a1b030b7b4037ffb1df2d7f14de54b5fd6d118317d2c3fa626440ea2d603
 size 496513256

 version https://git-lfs.github.com/spec/v1
+oid sha256:e06f43e3ed6d8a91d01e200ad4d2271f9bb971e00a440f8cde52a71d95d6658e
 size 496513256