Hugging Face's logo

taln-ls2n
/
AdminBERT-16GB

Fill-Mask
Transformers
Safetensors
French
camembert
BERT
Administrative documents
Inference Endpoints
Model card Files Community
TSebbag commited on
Commit
17fa952
•
1 Parent(s): a6178d9

Model files AdminBERT 16

Browse files
Files changed (10) hide show
  1. added_tokens.json +3 -0
  2. all_results.json +18 -0
  3. config.json +28 -0
  4. model.safetensors +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +20 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +83 -0
  9. train_results.json +18 -0
  10. trainer_state.json +86 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>NOTUSED": 32005
3
+ }
all_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "before_init_mem_cpu": 1261252608,
3
+ "before_init_mem_gpu": 0,
4
+ "epoch": 3.0,
5
+ "init_mem_cpu_alloc_delta": 835670016,
6
+ "init_mem_cpu_peaked_delta": 91971584,
7
+ "init_mem_gpu_alloc_delta": 443396608,
8
+ "init_mem_gpu_peaked_delta": 0,
9
+ "train_loss": 1.5746790189531785,
10
+ "train_mem_cpu_alloc_delta": 1865678848,
11
+ "train_mem_cpu_peaked_delta": 333721600,
12
+ "train_mem_gpu_alloc_delta": 1350910464,
13
+ "train_mem_gpu_peaked_delta": 21529119744,
14
+ "train_runtime": 8836.9123,
15
+ "train_samples": 3234398,
16
+ "train_samples_per_second": 1098.03,
17
+ "train_steps_per_second": 0.429
18
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/gpfswork/rech/khy/uvb95lb/camembert-base",
3
+ "architectures": [
4
+ "CamembertForMaskedLM"
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": "4.35.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 32005
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:996b7ebd77b2d0c25b99af9378b3c21f6ce0dc0300affb6545d6a703df213030
3
+ size 442646188
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
+ }
train_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "before_init_mem_cpu": 1261252608,
3
+ "before_init_mem_gpu": 0,
4
+ "epoch": 3.0,
5
+ "init_mem_cpu_alloc_delta": 835670016,
6
+ "init_mem_cpu_peaked_delta": 91971584,
7
+ "init_mem_gpu_alloc_delta": 443396608,
8
+ "init_mem_gpu_peaked_delta": 0,
9
+ "train_loss": 1.5746790189531785,
10
+ "train_mem_cpu_alloc_delta": 1865678848,
11
+ "train_mem_cpu_peaked_delta": 333721600,
12
+ "train_mem_gpu_alloc_delta": 1350910464,
13
+ "train_mem_gpu_peaked_delta": 21529119744,
14
+ "train_runtime": 8836.9123,
15
+ "train_samples": 3234398,
16
+ "train_samples_per_second": 1098.03,
17
+ "train_steps_per_second": 0.429
18
+ }
trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3792,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0,
14
+ "loss": 4.2141,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.4,
19
+ "learning_rate": 2.4750000000000004e-06,
20
+ "loss": 2.7204,
21
+ "step": 500
22
+ },
23
+ {
24
+ "epoch": 0.79,
25
+ "learning_rate": 4.975000000000001e-06,
26
+ "loss": 1.7191,
27
+ "step": 1000
28
+ },
29
+ {
30
+ "epoch": 1.19,
31
+ "learning_rate": 7.4750000000000004e-06,
32
+ "loss": 1.5429,
33
+ "step": 1500
34
+ },
35
+ {
36
+ "epoch": 1.58,
37
+ "learning_rate": 9.975e-06,
38
+ "loss": 1.4304,
39
+ "step": 2000
40
+ },
41
+ {
42
+ "epoch": 1.98,
43
+ "learning_rate": 1.2475e-05,
44
+ "loss": 1.3428,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 2.37,
49
+ "learning_rate": 1.4975e-05,
50
+ "loss": 1.2759,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 2.77,
55
+ "learning_rate": 1.7475e-05,
56
+ "loss": 1.2186,
57
+ "step": 3500
58
+ },
59
+ {
60
+ "before_init_mem_cpu": 1261252608,
61
+ "before_init_mem_gpu": 0,
62
+ "epoch": 3.0,
63
+ "init_mem_cpu_alloc_delta": 835670016,
64
+ "init_mem_cpu_peaked_delta": 91971584,
65
+ "init_mem_gpu_alloc_delta": 443396608,
66
+ "init_mem_gpu_peaked_delta": 0,
67
+ "step": 3792,
68
+ "total_flos": 2.555110221659767e+18,
69
+ "train_loss": 1.5746790189531785,
70
+ "train_mem_cpu_alloc_delta": 1865678848,
71
+ "train_mem_cpu_peaked_delta": 333721600,
72
+ "train_mem_gpu_alloc_delta": 1350910464,
73
+ "train_mem_gpu_peaked_delta": 21529119744,
74
+ "train_runtime": 8836.9123,
75
+ "train_samples_per_second": 1098.03,
76
+ "train_steps_per_second": 0.429
77
+ }
78
+ ],
79
+ "logging_steps": 500,
80
+ "max_steps": 3792,
81
+ "num_train_epochs": 3,
82
+ "save_steps": 500,
83
+ "total_flos": 2.555110221659767e+18,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }