pierreguillou
commited on
Commit
•
a3ddd61
1
Parent(s):
27f9596
Training in progress, step 500
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +48 -0
- pytorch_model.bin +3 -0
- runs/Jan15_13-56-56_c253277b4c99/1673791031.5098708/events.out.tfevents.1673791031.c253277b4c99.1282.1 +3 -0
- runs/Jan15_13-56-56_c253277b4c99/events.out.tfevents.1673791031.c253277b4c99.1282.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nielsr/lilt-xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"LiltForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"channel_shrink_ratio": 4,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "B-HEADER",
|
17 |
+
"2": "I-HEADER",
|
18 |
+
"3": "B-QUESTION",
|
19 |
+
"4": "I-QUESTION",
|
20 |
+
"5": "B-ANSWER",
|
21 |
+
"6": "I-ANSWER"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"B-ANSWER": 5,
|
27 |
+
"B-HEADER": 1,
|
28 |
+
"B-QUESTION": 3,
|
29 |
+
"I-ANSWER": 6,
|
30 |
+
"I-HEADER": 2,
|
31 |
+
"I-QUESTION": 4,
|
32 |
+
"O": 0
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-05,
|
35 |
+
"max_2d_position_embeddings": 1024,
|
36 |
+
"max_position_embeddings": 514,
|
37 |
+
"model_type": "lilt",
|
38 |
+
"num_attention_heads": 12,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"output_past": true,
|
41 |
+
"pad_token_id": 1,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.25.1",
|
45 |
+
"type_vocab_size": 1,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 250002
|
48 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcbb6bbb00f57a3141d3dde5c727865b3842363d6c884b6996ea4a6ffae312e2
|
3 |
+
size 1134413265
|
runs/Jan15_13-56-56_c253277b4c99/1673791031.5098708/events.out.tfevents.1673791031.c253277b4c99.1282.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76d9d4f5cca91e8501474431c8b3fb87ff37dcabaee8083ae8a90d66886b31cc
|
3 |
+
size 5606
|
runs/Jan15_13-56-56_c253277b4c99/events.out.tfevents.1673791031.c253277b4c99.1282.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:722c57e1ad6658b680a4ab9e6d792db382d6b9f05bd46c2083d082097905ee82
|
3 |
+
size 6764
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
|
3 |
+
size 17082758
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "nielsr/lilt-xlm-roberta-base",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90061b07e50ecb13cdac721e62855f54c2761288a0cfb3b21c6265ce91a06fd8
|
3 |
+
size 3451
|