wbigger commited on
Commit
d3eaa49
·
verified ·
1 Parent(s): 2a2cdee

End of training

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. config.json +6 -3
  3. model.safetensors +1 -1
  4. tokenizer_config.json +4 -44
  5. training_args.bin +2 -2
README.md CHANGED
@@ -36,7 +36,7 @@ The following hyperparameters were used during training:
36
  - train_batch_size: 8
37
  - eval_batch_size: 8
38
  - seed: 42
39
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
40
  - lr_scheduler_type: linear
41
  - num_epochs: 3.0
42
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
46
 
47
  ### Framework versions
48
 
49
- - Transformers 4.51.3
50
- - Pytorch 2.6.0+cu124
51
- - Datasets 3.5.1
52
- - Tokenizers 0.21.1
 
36
  - train_batch_size: 8
37
  - eval_batch_size: 8
38
  - seed: 42
39
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
40
  - lr_scheduler_type: linear
41
  - num_epochs: 3.0
42
 
 
46
 
47
  ### Framework versions
48
 
49
+ - Transformers 5.18.0
50
+ - Pytorch 2.11.0+cu130
51
+ - Datasets 4.8.5
52
+ - Tokenizers 0.23.2
config.json CHANGED
@@ -1,10 +1,12 @@
1
  {
 
2
  "architectures": [
3
  "XLMRobertaForSequenceClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "bos_token_id": 0,
7
  "classifier_dropout": null,
 
8
  "eos_token_id": 2,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
@@ -16,6 +18,7 @@
16
  },
17
  "initializer_range": 0.02,
18
  "intermediate_size": 3072,
 
19
  "label2id": {
20
  "negative": 0,
21
  "neutral": 1,
@@ -30,9 +33,9 @@
30
  "pad_token_id": 1,
31
  "position_embedding_type": "absolute",
32
  "problem_type": "single_label_classification",
33
- "torch_dtype": "float32",
34
- "transformers_version": "4.51.3",
35
  "type_vocab_size": 1,
36
- "use_cache": true,
37
  "vocab_size": 250002
38
  }
 
1
  {
2
+ "add_cross_attention": false,
3
  "architectures": [
4
  "XLMRobertaForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "dtype": "float32",
10
  "eos_token_id": 2,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
 
18
  },
19
  "initializer_range": 0.02,
20
  "intermediate_size": 3072,
21
+ "is_decoder": false,
22
  "label2id": {
23
  "negative": 0,
24
  "neutral": 1,
 
33
  "pad_token_id": 1,
34
  "position_embedding_type": "absolute",
35
  "problem_type": "single_label_classification",
36
+ "tie_word_embeddings": true,
37
+ "transformers_version": "5.18.0",
38
  "type_vocab_size": 1,
39
+ "use_cache": false,
40
  "vocab_size": 250002
41
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0766ba5efa8dd4f0171e4dc1890972ca79c4f2bbbe49e3848ccff6266ee7d23
3
  size 1112208084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3686c92f12deb427d48dfd64043f0b00f1a826e511727ae7bd067d0ba70692d9
3
  size 1112208084
tokenizer_config.json CHANGED
@@ -1,51 +1,11 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
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>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "250001": {
36
- "content": "<mask>",
37
- "lstrip": true,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
  "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": false,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
- "extra_special_tokens": {},
 
49
  "mask_token": "<mask>",
50
  "max_length": 128,
51
  "model_max_length": 512,
 
1
  {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "bos_token": "<s>",
 
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
  "mask_token": "<mask>",
10
  "max_length": 128,
11
  "model_max_length": 512,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d1c2600cb0a50ab5e7b9be2f68ceff0f3b65fc9b5122334d92a8cc098592cf3
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d97307cadb03b64e0d3a2046c2065ca40eff6c48e42569f9cb81e227496b6d8
3
+ size 5201