Training in progress epoch 0
Browse files- README.md +13 -74
- added_tokens.json +3 -0
- config.json +39 -25
- generation_config.json +3 -2
- merges.txt +0 -0
- special_tokens_map.json +3 -4
- tf_model.h5 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +11 -38
- vocab.json +0 -0
README.md
CHANGED
@@ -1,5 +1,7 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
@@ -12,10 +14,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# node-py/my_awesome_eli5_clm-model
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss:
|
18 |
-
-
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -39,78 +42,14 @@ The following hyperparameters were used during training:
|
|
39 |
|
40 |
### Training results
|
41 |
|
42 |
-
| Train Loss | Epoch |
|
43 |
-
|
44 |
-
|
|
45 |
-
| 5.8251 | 1 |
|
46 |
-
| 5.3850 | 2 |
|
47 |
-
| 5.0469 | 3 |
|
48 |
-
| 4.8048 | 4 |
|
49 |
-
| 4.6144 | 5 |
|
50 |
-
| 4.4743 | 6 |
|
51 |
-
| 4.3366 | 7 |
|
52 |
-
| 4.2178 | 8 |
|
53 |
-
| 4.1022 | 9 |
|
54 |
-
| 3.9908 | 10 |
|
55 |
-
| 3.8856 | 11 |
|
56 |
-
| 3.7700 | 12 |
|
57 |
-
| 3.6673 | 13 |
|
58 |
-
| 3.5560 | 14 |
|
59 |
-
| 3.4401 | 15 |
|
60 |
-
| 3.3328 | 16 |
|
61 |
-
| 3.2248 | 17 |
|
62 |
-
| 3.1290 | 18 |
|
63 |
-
| 3.0121 | 19 |
|
64 |
-
| 2.8978 | 20 |
|
65 |
-
| 2.7830 | 21 |
|
66 |
-
| 2.6913 | 22 |
|
67 |
-
| 2.5822 | 23 |
|
68 |
-
| 2.4772 | 24 |
|
69 |
-
| 2.3761 | 25 |
|
70 |
-
| 2.2792 | 26 |
|
71 |
-
| 2.1664 | 27 |
|
72 |
-
| 2.0731 | 28 |
|
73 |
-
| 1.9734 | 29 |
|
74 |
-
| 1.8900 | 30 |
|
75 |
-
| 1.7927 | 31 |
|
76 |
-
| 1.7036 | 32 |
|
77 |
-
| 1.6202 | 33 |
|
78 |
-
| 1.5329 | 34 |
|
79 |
-
| 1.4535 | 35 |
|
80 |
-
| 1.3778 | 36 |
|
81 |
-
| 1.3093 | 37 |
|
82 |
-
| 1.2413 | 38 |
|
83 |
-
| 1.1709 | 39 |
|
84 |
-
| 1.1114 | 40 |
|
85 |
-
| 1.0563 | 41 |
|
86 |
-
| 0.9950 | 42 |
|
87 |
-
| 0.9344 | 43 |
|
88 |
-
| 0.8830 | 44 |
|
89 |
-
| 0.8380 | 45 |
|
90 |
-
| 0.7966 | 46 |
|
91 |
-
| 0.7552 | 47 |
|
92 |
-
| 0.7162 | 48 |
|
93 |
-
| 0.6754 | 49 |
|
94 |
-
| 0.6420 | 50 |
|
95 |
-
| 0.6081 | 51 |
|
96 |
-
| 0.5825 | 52 |
|
97 |
-
| 0.5506 | 53 |
|
98 |
-
| 0.5213 | 54 |
|
99 |
-
| 0.4942 | 55 |
|
100 |
-
| 0.4716 | 56 |
|
101 |
-
| 0.4485 | 57 |
|
102 |
-
| 0.4256 | 58 |
|
103 |
-
| 0.4087 | 59 |
|
104 |
-
| 0.3921 | 60 |
|
105 |
-
| 0.3736 | 61 |
|
106 |
-
| 0.3574 | 62 |
|
107 |
-
| 0.3412 | 63 |
|
108 |
-
| 0.3272 | 64 |
|
109 |
|
110 |
|
111 |
### Framework versions
|
112 |
|
113 |
-
- Transformers 4.44.
|
114 |
-
- TensorFlow 2.
|
115 |
-
- Datasets
|
116 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: distilgpt2
|
5 |
tags:
|
6 |
- generated_from_keras_callback
|
7 |
model-index:
|
|
|
14 |
|
15 |
# node-py/my_awesome_eli5_clm-model
|
16 |
|
17 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Train Loss: 2.2705
|
20 |
+
- Validation Loss: 2.1315
|
21 |
+
- Epoch: 0
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
+
| Train Loss | Validation Loss | Epoch |
|
46 |
+
|:----------:|:---------------:|:-----:|
|
47 |
+
| 2.2705 | 2.1315 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
51 |
|
52 |
+
- Transformers 4.44.2
|
53 |
+
- TensorFlow 2.17.0
|
54 |
+
- Datasets 3.0.0
|
55 |
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 50257
|
3 |
+
}
|
config.json
CHANGED
@@ -1,31 +1,45 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
-
"
|
14 |
-
|
15 |
-
|
16 |
-
"
|
17 |
-
"model_type": "
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
"use_cache": true,
|
30 |
-
"vocab_size":
|
31 |
}
|
|
|
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,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"transformers_version": "4.44.2",
|
43 |
"use_cache": true,
|
44 |
+
"vocab_size": 50257
|
45 |
}
|
generation_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"
|
4 |
-
"
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.44.2"
|
6 |
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
"pad_token": "[PAD]",
|
5 |
-
"
|
6 |
-
"unk_token": "[UNK]"
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
"pad_token": "[PAD]",
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55dab45c5f83dd4240c06a6c8e684c9d764be7819ef5f33515adf8e2fc2843a3
|
3 |
+
size 327745472
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,39 +1,16 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
-
"normalized":
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "[
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"101": {
|
20 |
-
"content": "[CLS]",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"102": {
|
28 |
-
"content": "[SEP]",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"103": {
|
36 |
-
"content": "[MASK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
@@ -41,15 +18,11 @@
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"mask_token": "[MASK]",
|
48 |
-
"model_max_length": 512,
|
49 |
"pad_token": "[PAD]",
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "BertTokenizer",
|
54 |
-
"unk_token": "[UNK]"
|
55 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"50257": {
|
13 |
+
"content": "[PAD]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
|
|
18 |
"special": true
|
19 |
}
|
20 |
},
|
21 |
+
"bos_token": "<|endoftext|>",
|
22 |
"clean_up_tokenization_spaces": true,
|
23 |
+
"eos_token": "<|endoftext|>",
|
24 |
+
"model_max_length": 1024,
|
|
|
|
|
25 |
"pad_token": "[PAD]",
|
26 |
+
"tokenizer_class": "GPT2Tokenizer",
|
27 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
28 |
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|