Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: distilbert-base-uncased-distilled-squad
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # hankokk/my_awesome_qa_model
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased-distilled-squad](https://huggingface.co/distilbert-base-uncased-distilled-squad) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.4910
-- Validation Loss: 1.6589
-- Epoch: 2
+- Train Loss: 0.5701
+- Validation Loss: 0.4619
+- Epoch: 0
 
 ## Model description
 
@@ -43,9 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.3070     | 1.9674          | 0     |
-| 1.7356     | 1.6589          | 1     |
-| 1.4910     | 1.6589          | 2     |
+| 0.5701     | 0.4619          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased-distilled-squad",
   "activation": "gelu",
   "architectures": [
     "DistilBertForQuestionAnswering"

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e215b4e13a4507144d0e246e017023fe58f10b3dbcb2e7709306097f0109d1a0
+oid sha256:db10342bc69df9f1f5a2baa728d3b0d00da38a666b2f348b8d8f0c6cebd9ddec
 size 265583592