Training in progress epoch 0
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilgpt2
|
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 |
# pippinnie/distilgpt2-finetuned-cyber-readme-v2
|
15 |
|
16 |
-
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 4.
|
19 |
-
- Validation Loss: 4.
|
20 |
- Epoch: 0
|
21 |
|
22 |
## Model description
|
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
| 4.
|
47 |
|
48 |
|
49 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: pippinnie/distilgpt2-finetuned-cyber-readme-v2
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
|
|
13 |
|
14 |
# pippinnie/distilgpt2-finetuned-cyber-readme-v2
|
15 |
|
16 |
+
This model is a fine-tuned version of [pippinnie/distilgpt2-finetuned-cyber-readme-v2](https://huggingface.co/pippinnie/distilgpt2-finetuned-cyber-readme-v2) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 4.1809
|
19 |
+
- Validation Loss: 4.1506
|
20 |
- Epoch: 0
|
21 |
|
22 |
## Model description
|
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 4.1809 | 4.1506 | 0 |
|
47 |
|
48 |
|
49 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilgpt2",
|
3 |
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "pippinnie/distilgpt2-finetuned-cyber-readme-v2",
|
3 |
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
logs/train/events.out.tfevents.1712992708.Tianissimo-Laptop.14085.2.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9dfda696f828ca37cf8f02515de0d54683e5bb834e756c24084a26bfc9c6530
|
3 |
+
size 984859
|
logs/validation/events.out.tfevents.1712993142.Tianissimo-Laptop.14085.3.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d87f249209af5fefca6de9417745c7c651a147f804fc2c9ce64a4976c2484671
|
3 |
+
size 232
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 327745472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:635939dda5560b189090220eed6802fb1d2081c8246d80568a7239005c852385
|
3 |
size 327745472
|