srivatsavaasista
commited on
Commit
•
5870cc4
1
Parent(s):
aac2247
Training in progress epoch 0
Browse files- README.md +7 -9
- config.json +1 -1
- special_tokens_map.json +1 -0
- tf_model.h5 +1 -1
- tokenizer.json +6 -1
README.md
CHANGED
@@ -3,20 +3,20 @@ license: mit
|
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
6 |
-
- name: textgenerator
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
-
# textgenerator
|
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:
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -42,14 +42,12 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
| 10.
|
46 |
-
| 9.2278 | 8.8362 | 1 |
|
47 |
-
| 8.2564 | 7.8994 | 2 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
51 |
|
52 |
-
- Transformers 4.
|
53 |
- TensorFlow 2.8.2
|
54 |
- Datasets 2.4.0
|
55 |
- Tokenizers 0.12.1
|
|
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
6 |
+
- name: srivatsavaasista/textgenerator
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
+
# srivatsavaasista/textgenerator
|
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: 10.2937
|
18 |
+
- Validation Loss: 9.6742
|
19 |
+
- Epoch: 0
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 10.2937 | 9.6742 | 0 |
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- Transformers 4.21.0
|
51 |
- TensorFlow 2.8.2
|
52 |
- Datasets 2.4.0
|
53 |
- Tokenizers 0.12.1
|
config.json
CHANGED
@@ -32,7 +32,7 @@
|
|
32 |
"max_length": 50
|
33 |
}
|
34 |
},
|
35 |
-
"transformers_version": "4.
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 52000
|
38 |
}
|
|
|
32 |
"max_length": 50
|
33 |
}
|
34 |
},
|
35 |
+
"transformers_version": "4.21.0",
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 52000
|
38 |
}
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
|
|
4 |
"unk_token": "<|endoftext|>"
|
5 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
"unk_token": "<|endoftext|>"
|
6 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 503289960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaf5a369affcf3a7511b84c08305b00c94a2c1e1203d0d5726938c36eafccc6
|
3 |
size 503289960
|
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 |
{
|