Training in progress, step 500
Browse files- config.json +35 -0
- model.safetensors +3 -0
- runs/Mar11_16-40-54_4ae41b207cb2/events.out.tfevents.1710175258.4ae41b207cb2.1481.0 +3 -0
- runs/Mar11_16-42-10_4ae41b207cb2/events.out.tfevents.1710175333.4ae41b207cb2.1481.1 +3 -0
- runs/Mar11_16-43-56_4ae41b207cb2/events.out.tfevents.1710175455.4ae41b207cb2.4245.0 +3 -0
- runs/Mar11_16-45-56_4ae41b207cb2/events.out.tfevents.1710175561.4ae41b207cb2.4894.0 +3 -0
- runs/Mar11_16-45-56_4ae41b207cb2/events.out.tfevents.1710175867.4ae41b207cb2.4894.1 +3 -0
- runs/Mar11_16-45-56_4ae41b207cb2/events.out.tfevents.1710178317.4ae41b207cb2.4894.2 +3 -0
- runs/Mar11_17-34-53_4ae41b207cb2/events.out.tfevents.1710178498.4ae41b207cb2.16973.0 +3 -0
- runs/Mar11_17-35-07_4ae41b207cb2/events.out.tfevents.1710178512.4ae41b207cb2.16973.1 +3 -0
- runs/Mar11_17-35-20_4ae41b207cb2/events.out.tfevents.1710178525.4ae41b207cb2.16973.2 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "thenlper/gte-base-zh",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model_type": "bert",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pooler_fc_size": 768,
|
24 |
+
"pooler_num_attention_heads": 12,
|
25 |
+
"pooler_num_fc_layers": 3,
|
26 |
+
"pooler_size_per_head": 128,
|
27 |
+
"pooler_type": "first_token_transform",
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "multi_label_classification",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.38.2",
|
32 |
+
"type_vocab_size": 2,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 21128
|
35 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b04eec7f7cbe7af36c1f480b7734be24db1602d71386352ed51df03f8943a917
|
3 |
+
size 409100240
|
runs/Mar11_16-40-54_4ae41b207cb2/events.out.tfevents.1710175258.4ae41b207cb2.1481.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f51b96e30ddbf698ad9d4adc6e94cb09beecbf88e4bf99b0f0f2a42f4acf7ebc
|
3 |
+
size 4895
|
runs/Mar11_16-42-10_4ae41b207cb2/events.out.tfevents.1710175333.4ae41b207cb2.1481.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8683d4539130b1ac36318789f79c8366be04e78066400159b04a7ac9d00f118
|
3 |
+
size 4184
|
runs/Mar11_16-43-56_4ae41b207cb2/events.out.tfevents.1710175455.4ae41b207cb2.4245.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f86205ff8cc5c268bb62940039559ced18c7100dae1604db685ea28f14dd2b1
|
3 |
+
size 4184
|
runs/Mar11_16-45-56_4ae41b207cb2/events.out.tfevents.1710175561.4ae41b207cb2.4894.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcdf06185cef66aaf2348292cec066b9e33a31cc1e6308d30f19c415f1a810a7
|
3 |
+
size 4893
|
runs/Mar11_16-45-56_4ae41b207cb2/events.out.tfevents.1710175867.4ae41b207cb2.4894.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05337bcde4f142e46df96de2967c2c95e0c4bcf516c52cd17849c9332e6d7397
|
3 |
+
size 4941
|
runs/Mar11_16-45-56_4ae41b207cb2/events.out.tfevents.1710178317.4ae41b207cb2.4894.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56b1f9d01ee73aff6def593405f8413d31d206280b6202d09dc90567ec679181
|
3 |
+
size 4184
|
runs/Mar11_17-34-53_4ae41b207cb2/events.out.tfevents.1710178498.4ae41b207cb2.16973.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a8302c2aa83e63f42181c4653776621230e60b69d09d44101f814f0e42b6bb
|
3 |
+
size 4895
|
runs/Mar11_17-35-07_4ae41b207cb2/events.out.tfevents.1710178512.4ae41b207cb2.16973.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6001797bceafa57f3e84ff42a5581f599a10af49a6c95761a59eec9dbc1966d
|
3 |
+
size 4893
|
runs/Mar11_17-35-20_4ae41b207cb2/events.out.tfevents.1710178525.4ae41b207cb2.16973.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b02b985820238f30806e476823dd400a861ec753e7a1e31c2fa4862d65032237
|
3 |
+
size 4893
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 256,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f231c397c6b059d29b072c6a6560e1e8a98738b1bcb810801baf2dc106c38849
|
3 |
+
size 4920
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|