Training in progress epoch 0
Browse files- README.md +5 -6
- config.json +2 -1
- special_tokens_map.json +1 -7
- tf_model.h5 +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_keras_callback
|
| 6 |
model-index:
|
|
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# StaAhmed/Model_QA
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Train Loss:
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -42,8 +42,7 @@ The following hyperparameters were used during training:
|
|
| 42 |
|
| 43 |
| Train Loss | Epoch |
|
| 44 |
|:----------:|:-----:|
|
| 45 |
-
|
|
| 46 |
-
| 3.8285 | 1 |
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model: timpal0l/mdeberta-v3-base-squad2
|
| 4 |
tags:
|
| 5 |
- generated_from_keras_callback
|
| 6 |
model-index:
|
|
|
|
| 13 |
|
| 14 |
# StaAhmed/Model_QA
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [timpal0l/mdeberta-v3-base-squad2](https://huggingface.co/timpal0l/mdeberta-v3-base-squad2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 2.4444
|
| 19 |
+
- Epoch: 0
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 42 |
|
| 43 |
| Train Loss | Epoch |
|
| 44 |
|:----------:|:-----:|
|
| 45 |
+
| 2.4444 | 0 |
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"DebertaV2ForQuestionAnswering"
|
| 5 |
],
|
|
@@ -28,6 +28,7 @@
|
|
| 28 |
"position_buckets": 256,
|
| 29 |
"relative_attention": true,
|
| 30 |
"share_att_key": true,
|
|
|
|
| 31 |
"transformers_version": "4.35.2",
|
| 32 |
"type_vocab_size": 0,
|
| 33 |
"vocab_size": 251000
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "timpal0l/mdeberta-v3-base-squad2",
|
| 3 |
"architectures": [
|
| 4 |
"DebertaV2ForQuestionAnswering"
|
| 5 |
],
|
|
|
|
| 28 |
"position_buckets": 256,
|
| 29 |
"relative_attention": true,
|
| 30 |
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.35.2",
|
| 33 |
"type_vocab_size": 0,
|
| 34 |
"vocab_size": 251000
|
special_tokens_map.json
CHANGED
|
@@ -5,11 +5,5 @@
|
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
"sep_token": "[SEP]",
|
| 8 |
-
"unk_token":
|
| 9 |
-
"content": "[UNK]",
|
| 10 |
-
"lstrip": false,
|
| 11 |
-
"normalized": true,
|
| 12 |
-
"rstrip": false,
|
| 13 |
-
"single_word": false
|
| 14 |
-
}
|
| 15 |
}
|
|
|
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1113165584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d30bc11f57f8d41469b8e6bec914bcefc1a0d398cbdecdbe6c8fb737a6733dc2
|
| 3 |
size 1113165584
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1138eab70286f87e95bdf1fb4f1f173698ab5b130389032f399ea67b917bd07
|
| 3 |
+
size 16316412
|
tokenizer_config.json
CHANGED
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"3": {
|
| 28 |
"content": "[UNK]",
|
| 29 |
"lstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
|
|
|
| 27 |
"3": {
|
| 28 |
"content": "[UNK]",
|
| 29 |
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|