Training in progress, step 440
Browse files- added_tokens.json +3 -0
- config.json +39 -0
- model.safetensors +3 -0
- runs/Dec21_13-17-26_7688b827ad26/events.out.tfevents.1703164659.7688b827ad26.552.0 +3 -0
- runs/Dec21_13-18-49_7688b827ad26/events.out.tfevents.1703164735.7688b827ad26.552.1 +3 -0
- runs/Dec21_13-19-34_7688b827ad26/events.out.tfevents.1703164780.7688b827ad26.552.2 +3 -0
- runs/Dec21_13-20-39_7688b827ad26/events.out.tfevents.1703164845.7688b827ad26.552.3 +3 -0
- runs/Dec21_13-23-03_7688b827ad26/events.out.tfevents.1703164993.7688b827ad26.552.4 +3 -0
- runs/Dec21_13-32-09_7688b827ad26/events.out.tfevents.1703165535.7688b827ad26.552.5 +3 -0
- runs/Dec21_13-36-33_7688b827ad26/events.out.tfevents.1703165800.7688b827ad26.552.6 +3 -0
- runs/Dec21_13-41-33_7688b827ad26/events.out.tfevents.1703166100.7688b827ad26.552.8 +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +69 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 21128
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "yuanzhoulvpi/gpt2_chinese",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 21128,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 21128,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 512,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.35.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 21129
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d02d1cfc8ad7640ca947ad2a6d98b9d007831b437e28df2f33e0a056a7e5001e
|
3 |
+
size 408292992
|
runs/Dec21_13-17-26_7688b827ad26/events.out.tfevents.1703164659.7688b827ad26.552.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f65055186731cc9cbf757610d7552ae533967125310dd436587cba17cdba1d0
|
3 |
+
size 5277
|
runs/Dec21_13-18-49_7688b827ad26/events.out.tfevents.1703164735.7688b827ad26.552.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7bd9213763316341b3388b55232d8e55d4d4c36431ae53fa180ddeacb496cb3
|
3 |
+
size 5011
|
runs/Dec21_13-19-34_7688b827ad26/events.out.tfevents.1703164780.7688b827ad26.552.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d62bcc1721de1ab4872a18539498e03d312608ea76609b07c095a0a0443edcb5
|
3 |
+
size 5006
|
runs/Dec21_13-20-39_7688b827ad26/events.out.tfevents.1703164845.7688b827ad26.552.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4187725c644ccfff367782b2129613c52a1b6c4f4929a98554dfe5f07f8cfb8
|
3 |
+
size 5691
|
runs/Dec21_13-23-03_7688b827ad26/events.out.tfevents.1703164993.7688b827ad26.552.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb3e63a33e11e404bdf3f45dcb0ba7880739b0b3751067f7bbc985f26713c029
|
3 |
+
size 7133
|
runs/Dec21_13-32-09_7688b827ad26/events.out.tfevents.1703165535.7688b827ad26.552.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7afe441ae256e3ae10311227a63d17076f9cadcbfca2a9c6df0f48ae65b3618
|
3 |
+
size 8351
|
runs/Dec21_13-36-33_7688b827ad26/events.out.tfevents.1703165800.7688b827ad26.552.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86127a08c88e864c3e5f8a4ebb82dadb56a1f0f0c2c018afa6359a2d0078f12b
|
3 |
+
size 5271
|
runs/Dec21_13-41-33_7688b827ad26/events.out.tfevents.1703166100.7688b827ad26.552.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f828dabf9a578fcc460d339b50ad39a5a942475657464664545cccc71234f4fd
|
3 |
+
size 18050
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "<|endoftext|>",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
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,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"21128": {
|
44 |
+
"content": "<|endoftext|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"bos_token": "<|endoftext|>",
|
53 |
+
"clean_up_tokenization_spaces": true,
|
54 |
+
"cls_token": "[CLS]",
|
55 |
+
"do_lower_case": false,
|
56 |
+
"eos_token": "<|endoftext|>",
|
57 |
+
"mask_token": "[MASK]",
|
58 |
+
"max_length": 512,
|
59 |
+
"model_max_length": 512,
|
60 |
+
"pad_token": "<|endoftext|>",
|
61 |
+
"sep_token": "[SEP]",
|
62 |
+
"stride": 0,
|
63 |
+
"strip_accents": null,
|
64 |
+
"tokenize_chinese_chars": true,
|
65 |
+
"tokenizer_class": "BertTokenizer",
|
66 |
+
"truncation_side": "right",
|
67 |
+
"truncation_strategy": "longest_first",
|
68 |
+
"unk_token": "<|endoftext|>"
|
69 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a2d62f8a555b7ce404ed9cc3c68016559c71e397c7d0609378106b939bf7bbd
|
3 |
+
size 4536
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|