Hugging Face's logo

daze-unlv
/
almanach-camembert-base

Multiple Choice
Transformers
TensorBoard
Safetensors
camembert
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
daze-unlv commited on
Commit
c4119ec
•
1 Parent(s): d160d4e

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. added_tokens.json +3 -0
  2. config.json +28 -0
  3. log.txt +5 -0
  4. model.safetensors +3 -0
  5. runs/Mar12_15-49-50_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710283793.cehsc-app-001.ad.unlv.edu.2430388.0 +3 -0
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +20 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +83 -0
  10. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>NOTUSED": 32005
3
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembert-base",
3
+ "architectures": [
4
+ "CamembertForMultipleChoice"
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
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "camembert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.39.0.dev0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 32005
28
+ }
log.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {'loss': 1.3866, 'grad_norm': 0.25656482577323914, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18}
2
+ {'loss': 1.3856, 'grad_norm': 0.15997980535030365, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35}
3
+ {'loss': 1.3868, 'grad_norm': 0.17803697288036346, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53}
4
+ {'loss': 1.3868, 'grad_norm': 0.15967394411563873, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7}
5
+ {'loss': 1.3866, 'grad_norm': 0.14670728147029877, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66723152edee1dd3814cb373e414edd6a8f61e610a509d3965aff0e60b9c4736
3
+ size 442514996
runs/Mar12_15-49-50_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710283793.cehsc-app-001.ad.unlv.edu.2430388.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e1295d8f8d4ae84b2533046f3cb2f95bce70a74f5ea5ff173ea2c154f80536a
3
+ size 6039
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<unk>NOTUSED"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32004": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32005": {
60
+ "content": "<unk>NOTUSED",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<unk>NOTUSED"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": true,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "mask_token": "<mask>",
78
+ "model_max_length": 512,
79
+ "pad_token": "<pad>",
80
+ "sep_token": "</s>",
81
+ "tokenizer_class": "CamembertTokenizer",
82
+ "unk_token": "<unk>"
83
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48cdc78be42ead4feeec2f390d414bdbe208f4d9a61a4d167a3a8271d3ea3d73
3
+ size 4920