Training in progress, epoch 1
Browse files- config.json +42 -0
- model.safetensors +3 -0
- runs/Sep12_22-32-32_legal-tech-0/events.out.tfevents.1726169555.legal-tech-0.639.0 +3 -0
- runs/Sep12_22-34-49_legal-tech-0/events.out.tfevents.1726169689.legal-tech-0.639.1 +3 -0
- runs/Sep12_22-35-26_legal-tech-0/events.out.tfevents.1726169727.legal-tech-0.639.2 +3 -0
- runs/Sep12_22-35-54_legal-tech-0/events.out.tfevents.1726169755.legal-tech-0.639.3 +3 -0
- runs/Sep12_22-36-37_legal-tech-0/events.out.tfevents.1726169797.legal-tech-0.639.4 +3 -0
- runs/Sep12_22-38-15_legal-tech-0/events.out.tfevents.1726169896.legal-tech-0.639.5 +3 -0
- runs/Sep12_22-39-23_legal-tech-0/events.out.tfevents.1726169964.legal-tech-0.639.6 +3 -0
- runs/Sep12_22-40-06_legal-tech-0/events.out.tfevents.1726170008.legal-tech-0.906.0 +3 -0
- runs/Sep12_22-41-16_legal-tech-0/events.out.tfevents.1726170078.legal-tech-0.1152.0 +3 -0
- runs/Sep12_22-52-29_legal-tech-0/events.out.tfevents.1726170750.legal-tech-0.1152.1 +3 -0
- runs/Sep12_22-53-54_legal-tech-0/events.out.tfevents.1726170836.legal-tech-0.1432.0 +3 -0
- runs/Sep12_22-56-43_legal-tech-0/events.out.tfevents.1726171003.legal-tech-0.1432.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Tochka-AI/ruRoPEBert-classic-base-2k",
|
3 |
+
"architectures": [
|
4 |
+
"RoPEBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertConfig",
|
9 |
+
"AutoModel": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertModel",
|
10 |
+
"AutoModelForMaskedLM": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForMaskedLM",
|
11 |
+
"AutoModelForSequenceClassification": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForSequenceClassification"
|
12 |
+
},
|
13 |
+
"classifier_dropout": null,
|
14 |
+
"directionality": "bidi",
|
15 |
+
"hidden_act": "gelu",
|
16 |
+
"hidden_dropout_prob": 0.1,
|
17 |
+
"hidden_size": 768,
|
18 |
+
"id2label": {
|
19 |
+
"0": "common",
|
20 |
+
"1": "toxic"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"common": 0,
|
26 |
+
"toxic": 1
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 2048,
|
30 |
+
"model_type": "bert",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"pooler_type": "mean",
|
35 |
+
"problem_type": "single_label_classification",
|
36 |
+
"rope_scaling": null,
|
37 |
+
"rope_theta": 10000.0,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.44.2",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"vocab_size": 120138
|
42 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:766532e99133d0437568e193f326d390e516d49f3f6795f53e3746dd8a2d8d9f
|
3 |
+
size 709323472
|
runs/Sep12_22-32-32_legal-tech-0/events.out.tfevents.1726169555.legal-tech-0.639.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d621ba85636ce9405bedc210b42cdaf1a17d1f414d165552872d30b4a4ff872
|
3 |
+
size 5452
|
runs/Sep12_22-34-49_legal-tech-0/events.out.tfevents.1726169689.legal-tech-0.639.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19288c0e76b86e43848605c6bc56c51b68b3bed371f092dc0287082a1d36cc3d
|
3 |
+
size 5562
|
runs/Sep12_22-35-26_legal-tech-0/events.out.tfevents.1726169727.legal-tech-0.639.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67e70e0e5a916e517d39bbc7df4db74f0e64ce3bec6fedb2ac52fb1ce76425fc
|
3 |
+
size 5589
|
runs/Sep12_22-35-54_legal-tech-0/events.out.tfevents.1726169755.legal-tech-0.639.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8921627f29d0e246f4b01c8cb6475ebe3376930be1d4ae50eeab59c96cb5892d
|
3 |
+
size 5562
|
runs/Sep12_22-36-37_legal-tech-0/events.out.tfevents.1726169797.legal-tech-0.639.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:216c85504fd3f0c09b31b562386860c4b3c4559678bffdabec06da23baba5641
|
3 |
+
size 5575
|
runs/Sep12_22-38-15_legal-tech-0/events.out.tfevents.1726169896.legal-tech-0.639.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70bd9f1f59ce1c0d9c263f6d9d8e01f01fe8ae2465ee986915c00c82da236328
|
3 |
+
size 5575
|
runs/Sep12_22-39-23_legal-tech-0/events.out.tfevents.1726169964.legal-tech-0.639.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:320ac948d2a669e7aef2817077e115db19060f918f422ef56c06031b70e5579d
|
3 |
+
size 5626
|
runs/Sep12_22-40-06_legal-tech-0/events.out.tfevents.1726170008.legal-tech-0.906.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d70d35d3b3b0246bad0668ec999f3eb09a01d9b49f3fd303a257e9d7fabc94b2
|
3 |
+
size 5575
|
runs/Sep12_22-41-16_legal-tech-0/events.out.tfevents.1726170078.legal-tech-0.1152.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8fc74809e8f9481c1d4fb1aac7cf6cd2d7c70cf0a16a10e0192e4f7bef0350b
|
3 |
+
size 5798
|
runs/Sep12_22-52-29_legal-tech-0/events.out.tfevents.1726170750.legal-tech-0.1152.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:486ad0fd1861fe4e554ff5fb533995dafa50e8bc3847b5ffc1974e6137fe3bc3
|
3 |
+
size 5575
|
runs/Sep12_22-53-54_legal-tech-0/events.out.tfevents.1726170836.legal-tech-0.1432.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a58471d865604819b6f55fd8a00695132f17f5d30fb223e7180f11938850bd0
|
3 |
+
size 5798
|
runs/Sep12_22-56-43_legal-tech-0/events.out.tfevents.1726171003.legal-tech-0.1432.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b439d3f2a21147e11ae551e66fa231fe2ed5764163eb7efa3f52dc1a406b8b3a
|
3 |
+
size 5855
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d94cb99dab90a9a1fb3d6cad477cbcc624059b0b838eed719677c70f1cf6d95
|
3 |
+
size 5240
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|