kmkarakaya
commited on
Commit
•
43066fb
1
Parent(s):
b380be9
Training in progress epoch 0
Browse files- README.md +4 -6
- config.json +1 -1
- special_tokens_map.json +1 -0
- tf_model.h5 +2 -2
- tokenizer.json +6 -1
README.md
CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss:
|
18 |
-
- Validation Loss: 9.
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -42,9 +42,7 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
| 10.
|
46 |
-
| 9.7805 | 9.7440 | 1 |
|
47 |
-
| 9.2776 | 9.3593 | 2 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 10.2672
|
18 |
+
- Validation Loss: 9.9647
|
19 |
+
- Epoch: 0
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 10.2672 | 9.9647 | 0 |
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
config.json
CHANGED
@@ -34,5 +34,5 @@
|
|
34 |
},
|
35 |
"transformers_version": "4.20.1",
|
36 |
"use_cache": true,
|
37 |
-
"vocab_size":
|
38 |
}
|
|
|
34 |
},
|
35 |
"transformers_version": "4.20.1",
|
36 |
"use_cache": true,
|
37 |
+
"vocab_size": 44208
|
38 |
}
|
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<|endoftext|>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
tf_model.h5
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:e590758473d6e975901a6bb5c3e8e1985e5a4591a79d54dd71b47a2fc6f61dcb
|
3 |
+
size 479352936
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 40,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|