malduwais commited on
Commit
a40094a
1 Parent(s): 21494a7

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: xlm-roberta-base-finetuned-ANAD-mlm-0.15-base-25OCT
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # xlm-roberta-base-finetuned-ANAD-mlm-0.15-base-25OCT
15
+
16
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.5193
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 32
42
+ - total_train_batch_size: 256
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:-----:|:---------------:|
52
+ | No log | 0.0941 | 100 | 1.9039 |
53
+ | No log | 0.1881 | 200 | 1.8793 |
54
+ | No log | 0.2822 | 300 | 1.8643 |
55
+ | No log | 0.3763 | 400 | 1.8479 |
56
+ | 2.0696 | 0.4703 | 500 | 1.8380 |
57
+ | 2.0696 | 0.5644 | 600 | 1.8336 |
58
+ | 2.0696 | 0.6585 | 700 | 1.8226 |
59
+ | 2.0696 | 0.7525 | 800 | 1.8231 |
60
+ | 2.0696 | 0.8466 | 900 | 1.8136 |
61
+ | 2.0049 | 0.9407 | 1000 | 1.8161 |
62
+ | 2.0049 | 1.0347 | 1100 | 1.8056 |
63
+ | 2.0049 | 1.1288 | 1200 | 1.7934 |
64
+ | 2.0049 | 1.2229 | 1300 | 1.7887 |
65
+ | 2.0049 | 1.3169 | 1400 | 1.7749 |
66
+ | 1.9612 | 1.4110 | 1500 | 1.7726 |
67
+ | 1.9612 | 1.5051 | 1600 | 1.7679 |
68
+ | 1.9612 | 1.5992 | 1700 | 1.7543 |
69
+ | 1.9612 | 1.6932 | 1800 | 1.7473 |
70
+ | 1.9612 | 1.7873 | 1900 | 1.7413 |
71
+ | 1.911 | 1.8814 | 2000 | 1.7334 |
72
+ | 1.911 | 1.9754 | 2100 | 1.7302 |
73
+ | 1.911 | 2.0695 | 2200 | 1.7172 |
74
+ | 1.911 | 2.1636 | 2300 | 1.7187 |
75
+ | 1.911 | 2.2576 | 2400 | 1.7076 |
76
+ | 1.8628 | 2.3517 | 2500 | 1.7011 |
77
+ | 1.8628 | 2.4458 | 2600 | 1.7001 |
78
+ | 1.8628 | 2.5398 | 2700 | 1.6929 |
79
+ | 1.8628 | 2.6339 | 2800 | 1.6929 |
80
+ | 1.8628 | 2.7280 | 2900 | 1.6848 |
81
+ | 1.8328 | 2.8220 | 3000 | 1.6804 |
82
+ | 1.8328 | 2.9161 | 3100 | 1.6762 |
83
+ | 1.8328 | 3.0102 | 3200 | 1.6759 |
84
+ | 1.8328 | 3.1042 | 3300 | 1.6715 |
85
+ | 1.8328 | 3.1983 | 3400 | 1.6653 |
86
+ | 1.8018 | 3.2924 | 3500 | 1.6590 |
87
+ | 1.8018 | 3.3864 | 3600 | 1.6519 |
88
+ | 1.8018 | 3.4805 | 3700 | 1.6493 |
89
+ | 1.8018 | 3.5746 | 3800 | 1.6458 |
90
+ | 1.8018 | 3.6686 | 3900 | 1.6415 |
91
+ | 1.7708 | 3.7627 | 4000 | 1.6397 |
92
+ | 1.7708 | 3.8568 | 4100 | 1.6345 |
93
+ | 1.7708 | 3.9508 | 4200 | 1.6351 |
94
+ | 1.7708 | 4.0449 | 4300 | 1.6324 |
95
+ | 1.7708 | 4.1390 | 4400 | 1.6271 |
96
+ | 1.7501 | 4.2331 | 4500 | 1.6253 |
97
+ | 1.7501 | 4.3271 | 4600 | 1.6248 |
98
+ | 1.7501 | 4.4212 | 4700 | 1.6153 |
99
+ | 1.7501 | 4.5153 | 4800 | 1.6191 |
100
+ | 1.7501 | 4.6093 | 4900 | 1.6135 |
101
+ | 1.7283 | 4.7034 | 5000 | 1.6087 |
102
+ | 1.7283 | 4.7975 | 5100 | 1.6072 |
103
+ | 1.7283 | 4.8915 | 5200 | 1.5991 |
104
+ | 1.7283 | 4.9856 | 5300 | 1.6026 |
105
+ | 1.7283 | 5.0797 | 5400 | 1.5989 |
106
+ | 1.7105 | 5.1737 | 5500 | 1.6011 |
107
+ | 1.7105 | 5.2678 | 5600 | 1.5958 |
108
+ | 1.7105 | 5.3619 | 5700 | 1.5894 |
109
+ | 1.7105 | 5.4559 | 5800 | 1.5871 |
110
+ | 1.7105 | 5.5500 | 5900 | 1.5865 |
111
+ | 1.6816 | 5.6441 | 6000 | 1.5871 |
112
+ | 1.6816 | 5.7381 | 6100 | 1.5840 |
113
+ | 1.6816 | 5.8322 | 6200 | 1.5842 |
114
+ | 1.6816 | 5.9263 | 6300 | 1.5772 |
115
+ | 1.6816 | 6.0203 | 6400 | 1.5769 |
116
+ | 1.6745 | 6.1144 | 6500 | 1.5740 |
117
+ | 1.6745 | 6.2085 | 6600 | 1.5690 |
118
+ | 1.6745 | 6.3025 | 6700 | 1.5700 |
119
+ | 1.6745 | 6.3966 | 6800 | 1.5704 |
120
+ | 1.6745 | 6.4907 | 6900 | 1.5667 |
121
+ | 1.6639 | 6.5847 | 7000 | 1.5653 |
122
+ | 1.6639 | 6.6788 | 7100 | 1.5647 |
123
+ | 1.6639 | 6.7729 | 7200 | 1.5625 |
124
+ | 1.6639 | 6.8670 | 7300 | 1.5572 |
125
+ | 1.6639 | 6.9610 | 7400 | 1.5551 |
126
+ | 1.6509 | 7.0551 | 7500 | 1.5533 |
127
+ | 1.6509 | 7.1492 | 7600 | 1.5522 |
128
+ | 1.6509 | 7.2432 | 7700 | 1.5509 |
129
+ | 1.6509 | 7.3373 | 7800 | 1.5468 |
130
+ | 1.6509 | 7.4314 | 7900 | 1.5488 |
131
+ | 1.6344 | 7.5254 | 8000 | 1.5459 |
132
+ | 1.6344 | 7.6195 | 8100 | 1.5463 |
133
+ | 1.6344 | 7.7136 | 8200 | 1.5452 |
134
+ | 1.6344 | 7.8076 | 8300 | 1.5407 |
135
+ | 1.6344 | 7.9017 | 8400 | 1.5416 |
136
+ | 1.6281 | 7.9958 | 8500 | 1.5400 |
137
+ | 1.6281 | 8.0898 | 8600 | 1.5372 |
138
+ | 1.6281 | 8.1839 | 8700 | 1.5350 |
139
+ | 1.6281 | 8.2780 | 8800 | 1.5341 |
140
+ | 1.6281 | 8.3720 | 8900 | 1.5345 |
141
+ | 1.6132 | 8.4661 | 9000 | 1.5325 |
142
+ | 1.6132 | 8.5602 | 9100 | 1.5293 |
143
+ | 1.6132 | 8.6542 | 9200 | 1.5288 |
144
+ | 1.6132 | 8.7483 | 9300 | 1.5280 |
145
+ | 1.6132 | 8.8424 | 9400 | 1.5287 |
146
+ | 1.6123 | 8.9364 | 9500 | 1.5272 |
147
+ | 1.6123 | 9.0305 | 9600 | 1.5255 |
148
+ | 1.6123 | 9.1246 | 9700 | 1.5251 |
149
+ | 1.6123 | 9.2186 | 9800 | 1.5233 |
150
+ | 1.6123 | 9.3127 | 9900 | 1.5221 |
151
+ | 1.5993 | 9.4068 | 10000 | 1.5223 |
152
+ | 1.5993 | 9.5009 | 10100 | 1.5216 |
153
+ | 1.5993 | 9.5949 | 10200 | 1.5215 |
154
+ | 1.5993 | 9.6890 | 10300 | 1.5207 |
155
+ | 1.5993 | 9.7831 | 10400 | 1.5204 |
156
+ | 1.5959 | 9.8771 | 10500 | 1.5198 |
157
+ | 1.5959 | 9.9712 | 10600 | 1.5193 |
158
+
159
+
160
+ ### Framework versions
161
+
162
+ - Transformers 4.43.4
163
+ - Pytorch 2.1.1+cu121
164
+ - Datasets 3.0.2
165
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
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": "xlm-roberta",
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": "4.43.4",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee0409ec258d33b8d9b9b462ac133bc844fc26306d9a583586d95df529caa9cf
3
+ size 1113205088
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0091a328b3441d754e481db5a390d7f3b8dabc6016869fd13ba350d23ddc4cd
3
+ size 17082832
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 256,
50
+ "pad_token": "<pad>",
51
+ "padding": "max_length",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "truncation": true,
55
+ "unk_token": "<unk>"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4773671ad723e0da59449932c35f64bd923d7f4bb71a30fbd6eb190aa7fe79b2
3
+ size 5240