Hugging Face's logo

iwan-rg
/
XLM-Roberta-base-Finetuned-EN-AR-Parallel

Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
Community
malduwais commited on
Commit
76cab87
·
verified ·
1 Parent(s): 546202e

End of training

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. README.md +159 -0
  3. config.json +28 -0
  4. model.safetensors +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +15 -0
  7. tokenizer.json +3 -0
  8. tokenizer_config.json +56 -0
  9. training_args.bin +3 -0
.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 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Parallel-mlm-0.15-base-27OCT
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-Parallel-mlm-0.15-base-27OCT
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: 0.9339
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 | 0.0998 | 100 | 1.4204 |
53
+ | No log | 0.1997 | 200 | 1.3432 |
54
+ | No log | 0.2995 | 300 | 1.3054 |
55
+ | No log | 0.3993 | 400 | 1.2756 |
56
+ | 1.5915 | 0.4992 | 500 | 1.2552 |
57
+ | 1.5915 | 0.5990 | 600 | 1.2327 |
58
+ | 1.5915 | 0.6988 | 700 | 1.2152 |
59
+ | 1.5915 | 0.7987 | 800 | 1.2012 |
60
+ | 1.5915 | 0.8985 | 900 | 1.2002 |
61
+ | 1.3946 | 0.9983 | 1000 | 1.1854 |
62
+ | 1.3946 | 1.0982 | 1100 | 1.1824 |
63
+ | 1.3946 | 1.1980 | 1200 | 1.1723 |
64
+ | 1.3946 | 1.2979 | 1300 | 1.1589 |
65
+ | 1.3946 | 1.3977 | 1400 | 1.1490 |
66
+ | 1.321 | 1.4975 | 1500 | 1.1387 |
67
+ | 1.321 | 1.5974 | 1600 | 1.1356 |
68
+ | 1.321 | 1.6972 | 1700 | 1.1252 |
69
+ | 1.321 | 1.7970 | 1800 | 1.1259 |
70
+ | 1.321 | 1.8969 | 1900 | 1.1182 |
71
+ | 1.2735 | 1.9967 | 2000 | 1.1144 |
72
+ | 1.2735 | 2.0965 | 2100 | 1.0966 |
73
+ | 1.2735 | 2.1964 | 2200 | 1.1005 |
74
+ | 1.2735 | 2.2962 | 2300 | 1.0952 |
75
+ | 1.2735 | 2.3960 | 2400 | 1.0935 |
76
+ | 1.235 | 2.4959 | 2500 | 1.0840 |
77
+ | 1.235 | 2.5957 | 2600 | 1.0766 |
78
+ | 1.235 | 2.6955 | 2700 | 1.0719 |
79
+ | 1.235 | 2.7954 | 2800 | 1.0665 |
80
+ | 1.235 | 2.8952 | 2900 | 1.0644 |
81
+ | 1.1954 | 2.9950 | 3000 | 1.0656 |
82
+ | 1.1954 | 3.0949 | 3100 | 1.0574 |
83
+ | 1.1954 | 3.1947 | 3200 | 1.0495 |
84
+ | 1.1954 | 3.2945 | 3300 | 1.0475 |
85
+ | 1.1954 | 3.3944 | 3400 | 1.0452 |
86
+ | 1.1707 | 3.4942 | 3500 | 1.0399 |
87
+ | 1.1707 | 3.5940 | 3600 | 1.0363 |
88
+ | 1.1707 | 3.6939 | 3700 | 1.0291 |
89
+ | 1.1707 | 3.7937 | 3800 | 1.0338 |
90
+ | 1.1707 | 3.8936 | 3900 | 1.0348 |
91
+ | 1.1509 | 3.9934 | 4000 | 1.0319 |
92
+ | 1.1509 | 4.0932 | 4100 | 1.0219 |
93
+ | 1.1509 | 4.1931 | 4200 | 1.0214 |
94
+ | 1.1509 | 4.2929 | 4300 | 1.0161 |
95
+ | 1.1509 | 4.3927 | 4400 | 1.0158 |
96
+ | 1.1275 | 4.4926 | 4500 | 1.0153 |
97
+ | 1.1275 | 4.5924 | 4600 | 1.0067 |
98
+ | 1.1275 | 4.6922 | 4700 | 1.0058 |
99
+ | 1.1275 | 4.7921 | 4800 | 1.0097 |
100
+ | 1.1275 | 4.8919 | 4900 | 1.0037 |
101
+ | 1.1127 | 4.9917 | 5000 | 1.0048 |
102
+ | 1.1127 | 5.0916 | 5100 | 1.0022 |
103
+ | 1.1127 | 5.1914 | 5200 | 0.9947 |
104
+ | 1.1127 | 5.2912 | 5300 | 0.9947 |
105
+ | 1.1127 | 5.3911 | 5400 | 0.9907 |
106
+ | 1.0944 | 5.4909 | 5500 | 0.9909 |
107
+ | 1.0944 | 5.5907 | 5600 | 0.9861 |
108
+ | 1.0944 | 5.6906 | 5700 | 0.9858 |
109
+ | 1.0944 | 5.7904 | 5800 | 0.9861 |
110
+ | 1.0944 | 5.8902 | 5900 | 0.9791 |
111
+ | 1.0847 | 5.9901 | 6000 | 0.9787 |
112
+ | 1.0847 | 6.0899 | 6100 | 0.9744 |
113
+ | 1.0847 | 6.1897 | 6200 | 0.9752 |
114
+ | 1.0847 | 6.2896 | 6300 | 0.9712 |
115
+ | 1.0847 | 6.3894 | 6400 | 0.9723 |
116
+ | 1.0662 | 6.4893 | 6500 | 0.9706 |
117
+ | 1.0662 | 6.5891 | 6600 | 0.9688 |
118
+ | 1.0662 | 6.6889 | 6700 | 0.9692 |
119
+ | 1.0662 | 6.7888 | 6800 | 0.9655 |
120
+ | 1.0662 | 6.8886 | 6900 | 0.9637 |
121
+ | 1.0559 | 6.9884 | 7000 | 0.9629 |
122
+ | 1.0559 | 7.0883 | 7100 | 0.9618 |
123
+ | 1.0559 | 7.1881 | 7200 | 0.9622 |
124
+ | 1.0559 | 7.2879 | 7300 | 0.9605 |
125
+ | 1.0559 | 7.3878 | 7400 | 0.9560 |
126
+ | 1.0439 | 7.4876 | 7500 | 0.9562 |
127
+ | 1.0439 | 7.5874 | 7600 | 0.9566 |
128
+ | 1.0439 | 7.6873 | 7700 | 0.9515 |
129
+ | 1.0439 | 7.7871 | 7800 | 0.9514 |
130
+ | 1.0439 | 7.8869 | 7900 | 0.9542 |
131
+ | 1.0358 | 7.9868 | 8000 | 0.9504 |
132
+ | 1.0358 | 8.0866 | 8100 | 0.9502 |
133
+ | 1.0358 | 8.1864 | 8200 | 0.9494 |
134
+ | 1.0358 | 8.2863 | 8300 | 0.9451 |
135
+ | 1.0358 | 8.3861 | 8400 | 0.9461 |
136
+ | 1.0242 | 8.4859 | 8500 | 0.9447 |
137
+ | 1.0242 | 8.5858 | 8600 | 0.9455 |
138
+ | 1.0242 | 8.6856 | 8700 | 0.9441 |
139
+ | 1.0242 | 8.7854 | 8800 | 0.9399 |
140
+ | 1.0242 | 8.8853 | 8900 | 0.9410 |
141
+ | 1.0198 | 8.9851 | 9000 | 0.9391 |
142
+ | 1.0198 | 9.0850 | 9100 | 0.9390 |
143
+ | 1.0198 | 9.1848 | 9200 | 0.9379 |
144
+ | 1.0198 | 9.2846 | 9300 | 0.9382 |
145
+ | 1.0198 | 9.3845 | 9400 | 0.9377 |
146
+ | 1.0094 | 9.4843 | 9500 | 0.9363 |
147
+ | 1.0094 | 9.5841 | 9600 | 0.9354 |
148
+ | 1.0094 | 9.6840 | 9700 | 0.9353 |
149
+ | 1.0094 | 9.7838 | 9800 | 0.9351 |
150
+ | 1.0094 | 9.8836 | 9900 | 0.9342 |
151
+ | 1.011 | 9.9835 | 10000 | 0.9339 |
152
+
153
+
154
+ ### Framework versions
155
+
156
+ - Transformers 4.43.4
157
+ - Pytorch 2.1.1+cu121
158
+ - Datasets 3.0.2
159
+ - 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:c59f23b1b878ee2bc1d24d190d2ec72355c57263f1d2a48fbce13a47467e6509
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 sha256:8a08e15efb3a887cae9235e98fa7dc1693c876370ae46da3ce8c846199e6a57f
3
+ size 5240