Hugging Face's logo

JulesGo
/
camembert-secabilite-regressor

Transformers
Safetensors
camembert
Generated from Trainer
Model card Files
xet
Community
JulesGo commited on
Commit
e562aba
·
verified ·
1 Parent(s): a83bb2c

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. added_tokens.json +3 -0
  2. all_results.json +15 -0
  3. config.json +33 -0
  4. eval_results.json +10 -0
  5. model.safetensors +3 -0
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +20 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +84 -0
  10. train_results.json +8 -0
  11. trainer_state.json +90 -0
  12. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>NOTUSED": 32005
3
+ }
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.1344040334224701,
4
+ "eval_mae": 0.32635048031806946,
5
+ "eval_model_preparation_time": 0.0013,
6
+ "eval_mse": 0.13417871296405792,
7
+ "eval_runtime": 1.7064,
8
+ "eval_samples_per_second": 9.963,
9
+ "eval_steps_per_second": 1.758,
10
+ "total_flos": 52095521212416.0,
11
+ "train_loss": 0.16883156034681532,
12
+ "train_runtime": 116.4464,
13
+ "train_samples_per_second": 1.7,
14
+ "train_steps_per_second": 0.232
15
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CamembertForTokenRegression"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 5,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 6,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 514,
22
+ "model_type": "camembert",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 1,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.51.3",
30
+ "type_vocab_size": 1,
31
+ "use_cache": true,
32
+ "vocab_size": 32005
33
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.1344040334224701,
4
+ "eval_mae": 0.32635048031806946,
5
+ "eval_model_preparation_time": 0.0013,
6
+ "eval_mse": 0.13417871296405792,
7
+ "eval_runtime": 1.7064,
8
+ "eval_samples_per_second": 9.963,
9
+ "eval_steps_per_second": 1.758
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:637553b58933b0cd8bee491c61655eba96d7ee77dc33c48020adb8ff9fbca56f
3
+ size 442515412
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 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "extra_special_tokens": {},
78
+ "mask_token": "<mask>",
79
+ "model_max_length": 512,
80
+ "pad_token": "<pad>",
81
+ "sep_token": "</s>",
82
+ "tokenizer_class": "CamembertTokenizer",
83
+ "unk_token": "<unk>"
84
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 52095521212416.0,
4
+ "train_loss": 0.16883156034681532,
5
+ "train_runtime": 116.4464,
6
+ "train_samples_per_second": 1.7,
7
+ "train_steps_per_second": 0.232
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 27,
3
+ "best_metric": 0.13417871296405792,
4
+ "best_model_checkpoint": "./camembert-secabilite-regressor/checkpoint-27",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 27,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_loss": 0.19791264832019806,
15
+ "eval_mae": 0.39102548360824585,
16
+ "eval_model_preparation_time": 0.0013,
17
+ "eval_mse": 0.19728119671344757,
18
+ "eval_runtime": 1.1628,
19
+ "eval_samples_per_second": 14.62,
20
+ "eval_steps_per_second": 2.58,
21
+ "step": 9
22
+ },
23
+ {
24
+ "epoch": 1.1111111111111112,
25
+ "grad_norm": 3.790409564971924,
26
+ "learning_rate": 1.9999999999999998e-05,
27
+ "loss": 0.2129,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.13820508122444153,
33
+ "eval_mae": 0.3387083411216736,
34
+ "eval_model_preparation_time": 0.0013,
35
+ "eval_mse": 0.13782182335853577,
36
+ "eval_runtime": 0.8693,
37
+ "eval_samples_per_second": 19.555,
38
+ "eval_steps_per_second": 3.451,
39
+ "step": 18
40
+ },
41
+ {
42
+ "epoch": 2.2222222222222223,
43
+ "grad_norm": 1.1181731224060059,
44
+ "learning_rate": 8.888888888888888e-06,
45
+ "loss": 0.1443,
46
+ "step": 20
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_loss": 0.1344040334224701,
51
+ "eval_mae": 0.32635048031806946,
52
+ "eval_model_preparation_time": 0.0013,
53
+ "eval_mse": 0.13417871296405792,
54
+ "eval_runtime": 0.777,
55
+ "eval_samples_per_second": 21.878,
56
+ "eval_steps_per_second": 3.861,
57
+ "step": 27
58
+ },
59
+ {
60
+ "epoch": 3.0,
61
+ "step": 27,
62
+ "total_flos": 52095521212416.0,
63
+ "train_loss": 0.16883156034681532,
64
+ "train_runtime": 116.4464,
65
+ "train_samples_per_second": 1.7,
66
+ "train_steps_per_second": 0.232
67
+ }
68
+ ],
69
+ "logging_steps": 10,
70
+ "max_steps": 27,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 3,
73
+ "save_steps": 500,
74
+ "stateful_callbacks": {
75
+ "TrainerControl": {
76
+ "args": {
77
+ "should_epoch_stop": false,
78
+ "should_evaluate": false,
79
+ "should_log": false,
80
+ "should_save": true,
81
+ "should_training_stop": true
82
+ },
83
+ "attributes": {}
84
+ }
85
+ },
86
+ "total_flos": 52095521212416.0,
87
+ "train_batch_size": 8,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3296f4b4b84fad66a4fd91bc8e0bbe0f78bc89a7c88e05291e756c247a93fb73
3
+ size 5713