bigmorning
commited on
Commit
•
1d58b15
1
Parent(s):
4040269
add model
Browse files- README.md +8 -27
- config.json +13 -8
- tf_model.h5 +2 -2
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
@@ -12,11 +12,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# try-m
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss: 0.
|
18 |
-
-
|
19 |
-
- Epoch: 19
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -40,28 +39,10 @@ The following hyperparameters were used during training:
|
|
40 |
|
41 |
### Training results
|
42 |
|
43 |
-
| Train Loss |
|
44 |
-
|
45 |
-
| 0.
|
46 |
-
| 0.
|
47 |
-
| 0.0180 | 0.0220 | 2 |
|
48 |
-
| 0.0110 | 0.0187 | 3 |
|
49 |
-
| 0.0098 | 0.0130 | 4 |
|
50 |
-
| 0.0056 | 0.0111 | 5 |
|
51 |
-
| 0.0039 | 0.0102 | 6 |
|
52 |
-
| 0.0034 | 0.0101 | 7 |
|
53 |
-
| 0.0027 | 0.0092 | 8 |
|
54 |
-
| 0.0024 | 0.0088 | 9 |
|
55 |
-
| 0.0021 | 0.0085 | 10 |
|
56 |
-
| 0.0019 | 0.0081 | 11 |
|
57 |
-
| 0.0017 | 0.0081 | 12 |
|
58 |
-
| 0.0014 | 0.0079 | 13 |
|
59 |
-
| 0.0012 | 0.0076 | 14 |
|
60 |
-
| 0.0010 | 0.0069 | 15 |
|
61 |
-
| 0.0008 | 0.0073 | 16 |
|
62 |
-
| 0.0008 | 0.0068 | 17 |
|
63 |
-
| 0.0004 | 0.0060 | 18 |
|
64 |
-
| 0.0004 | 0.0062 | 19 |
|
65 |
|
66 |
|
67 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
|
|
12 |
|
13 |
# try-m
|
14 |
|
15 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 0.2158
|
18 |
+
- Epoch: 1
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
39 |
|
40 |
### Training results
|
41 |
|
42 |
+
| Train Loss | Epoch |
|
43 |
+
|:----------:|:-----:|
|
44 |
+
| 0.5434 | 0 |
|
45 |
+
| 0.2158 | 1 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
config.json
CHANGED
@@ -1,25 +1,31 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
6 |
],
|
7 |
-
"attn_pdrop": 0.
|
8 |
"bos_token_id": 50256,
|
9 |
-
"embd_pdrop": 0.
|
10 |
-
"eos_token_id":
|
11 |
-
"
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
"n_embd": 768,
|
17 |
"n_head": 12,
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
-
"resid_pdrop": 0.
|
23 |
"scale_attn_by_inverse_layer_idx": false,
|
24 |
"scale_attn_weights": true,
|
25 |
"summary_activation": null,
|
@@ -33,7 +39,6 @@
|
|
33 |
"max_length": 50
|
34 |
}
|
35 |
},
|
36 |
-
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.17.0",
|
38 |
"use_cache": false,
|
39 |
"vocab_size": 5998
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
"GPT2LMHeadModel"
|
7 |
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
"layer_norm_epsilon": 1e-05,
|
20 |
"model_type": "gpt2",
|
21 |
"n_ctx": 1024,
|
22 |
"n_embd": 768,
|
23 |
"n_head": 12,
|
24 |
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
"n_positions": 1024,
|
27 |
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
"scale_attn_by_inverse_layer_idx": false,
|
30 |
"scale_attn_weights": true,
|
31 |
"summary_activation": null,
|
|
|
39 |
"max_length": 50
|
40 |
}
|
41 |
},
|
|
|
42 |
"transformers_version": "4.17.0",
|
43 |
"use_cache": false,
|
44 |
"vocab_size": 5998
|
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 sha256:884d2b7ede8ea69141e3f9486f0cc1d2ab1ba9eff4650d9a2a585a267c338d31
|
3 |
+
size 210211336
|