dev-senolys
commited on
Commit
•
cd05dfc
1
Parent(s):
67ec830
Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +61 -0
- pytorch_model.bin +3 -0
- runs/Jun29_08-05-37_ns3005206/1688025942.0851438/events.out.tfevents.1688025942.ns3005206.424355.1 +3 -0
- runs/Jun29_08-05-37_ns3005206/events.out.tfevents.1688025942.ns3005206.424355.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "camembert-base",
|
3 |
+
"architectures": [
|
4 |
+
"CamembertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 5,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 6,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "agronomy",
|
15 |
+
"1": "business",
|
16 |
+
"2": "design",
|
17 |
+
"3": "digital",
|
18 |
+
"4": "environment",
|
19 |
+
"5": "learning",
|
20 |
+
"6": "medical",
|
21 |
+
"7": "people",
|
22 |
+
"8": "production",
|
23 |
+
"9": "resource",
|
24 |
+
"10": "science",
|
25 |
+
"11": "security",
|
26 |
+
"12": "society",
|
27 |
+
"13": "transport"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"agronomy": 0,
|
33 |
+
"business": 1,
|
34 |
+
"design": 2,
|
35 |
+
"digital": 3,
|
36 |
+
"environment": 4,
|
37 |
+
"learning": 5,
|
38 |
+
"medical": 6,
|
39 |
+
"people": 7,
|
40 |
+
"production": 8,
|
41 |
+
"resource": 9,
|
42 |
+
"science": 10,
|
43 |
+
"security": 11,
|
44 |
+
"society": 12,
|
45 |
+
"transport": 13
|
46 |
+
},
|
47 |
+
"layer_norm_eps": 1e-05,
|
48 |
+
"max_position_embeddings": 514,
|
49 |
+
"model_type": "camembert",
|
50 |
+
"num_attention_heads": 12,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"output_past": true,
|
53 |
+
"pad_token_id": 1,
|
54 |
+
"position_embedding_type": "absolute",
|
55 |
+
"problem_type": "single_label_classification",
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.29.2",
|
58 |
+
"type_vocab_size": 1,
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32005
|
61 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92b83a6aeee8e6048f454cbf27319dae1ed6be8617c89ecd5ac6e4de15e77dd5
|
3 |
+
size 442601397
|
runs/Jun29_08-05-37_ns3005206/1688025942.0851438/events.out.tfevents.1688025942.ns3005206.424355.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e518a8d7196de520d237cf66a9ad555b8b627556d559e7cd934a843d83ce7f41
|
3 |
+
size 6030
|
runs/Jun29_08-05-37_ns3005206/events.out.tfevents.1688025942.ns3005206.424355.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0546f5f22a7cde10f3a14049229930d2ed191cb72904783c36beebeba681f736
|
3 |
+
size 6006
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
3 |
+
size 810912
|
special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"clean_up_tokenization_spaces": true,
|
8 |
+
"cls_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"mask_token": {
|
11 |
+
"__type": "AddedToken",
|
12 |
+
"content": "<mask>",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"model_max_length": 512,
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"tokenizer_class": "CamembertTokenizer",
|
22 |
+
"unk_token": "<unk>"
|
23 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d373d231164602a9062f7e94d3f57b7551ad8919bbfa4862039948b33e953b
|
3 |
+
size 3963
|