judithrosell
commited on
Commit
•
93972a0
1
Parent(s):
b76888d
Training in progress, epoch 1
Browse files- config.json +64 -0
- model.safetensors +3 -0
- runs/Sep01_15-00-06_fcb107e610d6/events.out.tfevents.1725202808.fcb107e610d6.8744.0 +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 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "m3rg-iitd/matscibert",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B-Ceramics_Glasses",
|
14 |
+
"1": "B-Composites_Layers_Coverings",
|
15 |
+
"2": "B-Copolymers_Blends",
|
16 |
+
"3": "B-Metals_Alloys",
|
17 |
+
"4": "B-Natural_Polymer",
|
18 |
+
"5": "B-Synthetic_Polymer",
|
19 |
+
"6": "B-Trade_Name_Biomat",
|
20 |
+
"7": "B-chemical_Material",
|
21 |
+
"8": "I-Ceramics_Glasses",
|
22 |
+
"9": "I-Composites_Layers_Coverings",
|
23 |
+
"10": "I-Copolymers_Blends",
|
24 |
+
"11": "I-Metals_Alloys",
|
25 |
+
"12": "I-Natural_Polymer",
|
26 |
+
"13": "I-Synthetic_Polymer",
|
27 |
+
"14": "I-Trade_Name_Biomat",
|
28 |
+
"15": "I-chemical_Material",
|
29 |
+
"16": "O"
|
30 |
+
},
|
31 |
+
"initializer_range": 0.02,
|
32 |
+
"intermediate_size": 3072,
|
33 |
+
"label2id": {
|
34 |
+
"B-Ceramics_Glasses": 0,
|
35 |
+
"B-Composites_Layers_Coverings": 1,
|
36 |
+
"B-Copolymers_Blends": 2,
|
37 |
+
"B-Metals_Alloys": 3,
|
38 |
+
"B-Natural_Polymer": 4,
|
39 |
+
"B-Synthetic_Polymer": 5,
|
40 |
+
"B-Trade_Name_Biomat": 6,
|
41 |
+
"B-chemical_Material": 7,
|
42 |
+
"I-Ceramics_Glasses": 8,
|
43 |
+
"I-Composites_Layers_Coverings": 9,
|
44 |
+
"I-Copolymers_Blends": 10,
|
45 |
+
"I-Metals_Alloys": 11,
|
46 |
+
"I-Natural_Polymer": 12,
|
47 |
+
"I-Synthetic_Polymer": 13,
|
48 |
+
"I-Trade_Name_Biomat": 14,
|
49 |
+
"I-chemical_Material": 15,
|
50 |
+
"O": 16
|
51 |
+
},
|
52 |
+
"layer_norm_eps": 1e-12,
|
53 |
+
"max_position_embeddings": 512,
|
54 |
+
"model_type": "bert",
|
55 |
+
"num_attention_heads": 12,
|
56 |
+
"num_hidden_layers": 12,
|
57 |
+
"pad_token_id": 0,
|
58 |
+
"position_embedding_type": "absolute",
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.42.4",
|
61 |
+
"type_vocab_size": 2,
|
62 |
+
"use_cache": true,
|
63 |
+
"vocab_size": 31090
|
64 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff0d9c6837d00550814fa0f4d81c4021c2172bf03994c84c8e39b44a6221f12f
|
3 |
+
size 437387124
|
runs/Sep01_15-00-06_fcb107e610d6/events.out.tfevents.1725202808.fcb107e610d6.8744.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bce7ffad375254111abed0bc4774f2dfc67d3da710272f975aca6c9de62f27d
|
3 |
+
size 6627
|
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 |
+
"101": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
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": 1000000000000000019884624838656,
|
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:c5a91fba5fa87c94782b4b0c4ee5a65517e57e09399509ddeb91c33fa195bf1c
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|