Hugging Face's logo

haryoaw
/
scenario-TCR-XLMV-XCOPA-2_data-xcopa_all

Multiple Choice
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
haryoaw commited on
Commit
4f6a387
•
1 Parent(s): 3801180

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +122 -0
  2. config.json +27 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/xlm-v-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: scenario-TCR-XLMV-XCOPA-2_data-xcopa_all
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # scenario-TCR-XLMV-XCOPA-2_data-xcopa_all
18
+
19
+ This model is a fine-tuned version of [facebook/xlm-v-base](https://huggingface.co/facebook/xlm-v-base) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.3263
22
+ - Accuracy: 0.5417
23
+ - F1: 0.5291
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 32
45
+ - seed: 34
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 500
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | No log | 0.38 | 5 | 0.6932 | 0.5075 | 0.4793 |
55
+ | No log | 0.77 | 10 | 0.6932 | 0.5025 | 0.4749 |
56
+ | No log | 1.15 | 15 | 0.6931 | 0.51 | 0.4878 |
57
+ | No log | 1.54 | 20 | 0.6931 | 0.5192 | 0.4934 |
58
+ | No log | 1.92 | 25 | 0.6931 | 0.51 | 0.4869 |
59
+ | No log | 2.31 | 30 | 0.6931 | 0.5417 | 0.5089 |
60
+ | No log | 2.69 | 35 | 0.6931 | 0.5533 | 0.5323 |
61
+ | No log | 3.08 | 40 | 0.6931 | 0.5542 | 0.5352 |
62
+ | No log | 3.46 | 45 | 0.6931 | 0.55 | 0.5329 |
63
+ | No log | 3.85 | 50 | 0.6931 | 0.5475 | 0.5233 |
64
+ | No log | 4.23 | 55 | 0.6931 | 0.5217 | 0.4884 |
65
+ | No log | 4.62 | 60 | 0.6932 | 0.5283 | 0.5052 |
66
+ | No log | 5.0 | 65 | 0.6931 | 0.5308 | 0.4969 |
67
+ | No log | 5.38 | 70 | 0.6930 | 0.5217 | 0.4929 |
68
+ | No log | 5.77 | 75 | 0.6930 | 0.53 | 0.5138 |
69
+ | No log | 6.15 | 80 | 0.6931 | 0.5417 | 0.5259 |
70
+ | No log | 6.54 | 85 | 0.6931 | 0.5525 | 0.5318 |
71
+ | No log | 6.92 | 90 | 0.6931 | 0.5417 | 0.5054 |
72
+ | No log | 7.31 | 95 | 0.6931 | 0.56 | 0.5319 |
73
+ | No log | 7.69 | 100 | 0.6930 | 0.555 | 0.5291 |
74
+ | No log | 8.08 | 105 | 0.6931 | 0.5192 | 0.4978 |
75
+ | No log | 8.46 | 110 | 0.6931 | 0.5192 | 0.4943 |
76
+ | No log | 8.85 | 115 | 0.6930 | 0.5383 | 0.5249 |
77
+ | No log | 9.23 | 120 | 0.6930 | 0.5375 | 0.5244 |
78
+ | No log | 9.62 | 125 | 0.6930 | 0.54 | 0.5192 |
79
+ | No log | 10.0 | 130 | 0.6930 | 0.5617 | 0.5450 |
80
+ | No log | 10.38 | 135 | 0.6930 | 0.54 | 0.5217 |
81
+ | No log | 10.77 | 140 | 0.6929 | 0.5475 | 0.5241 |
82
+ | No log | 11.15 | 145 | 0.6926 | 0.57 | 0.5559 |
83
+ | No log | 11.54 | 150 | 0.6920 | 0.5658 | 0.5611 |
84
+ | No log | 11.92 | 155 | 0.6896 | 0.5758 | 0.5661 |
85
+ | No log | 12.31 | 160 | 0.6879 | 0.5275 | 0.5074 |
86
+ | No log | 12.69 | 165 | 0.7069 | 0.4792 | 0.4435 |
87
+ | No log | 13.08 | 170 | 0.6925 | 0.5358 | 0.5276 |
88
+ | No log | 13.46 | 175 | 0.6941 | 0.5275 | 0.5082 |
89
+ | No log | 13.85 | 180 | 0.7034 | 0.52 | 0.5052 |
90
+ | No log | 14.23 | 185 | 0.7386 | 0.54 | 0.5208 |
91
+ | No log | 14.62 | 190 | 0.7108 | 0.5242 | 0.4987 |
92
+ | No log | 15.0 | 195 | 0.7418 | 0.5275 | 0.4978 |
93
+ | No log | 15.38 | 200 | 0.8982 | 0.5292 | 0.5074 |
94
+ | No log | 15.77 | 205 | 0.8073 | 0.5525 | 0.5398 |
95
+ | No log | 16.15 | 210 | 1.0723 | 0.5633 | 0.5459 |
96
+ | No log | 16.54 | 215 | 0.8696 | 0.5508 | 0.5293 |
97
+ | No log | 16.92 | 220 | 0.8563 | 0.5533 | 0.5315 |
98
+ | No log | 17.31 | 225 | 1.1253 | 0.5317 | 0.5147 |
99
+ | No log | 17.69 | 230 | 1.0949 | 0.5483 | 0.5279 |
100
+ | No log | 18.08 | 235 | 0.8768 | 0.5592 | 0.5482 |
101
+ | No log | 18.46 | 240 | 1.1880 | 0.5558 | 0.5401 |
102
+ | No log | 18.85 | 245 | 1.1781 | 0.5617 | 0.5434 |
103
+ | No log | 19.23 | 250 | 0.9759 | 0.5508 | 0.5381 |
104
+ | No log | 19.62 | 255 | 1.2402 | 0.5442 | 0.5321 |
105
+ | No log | 20.0 | 260 | 1.2534 | 0.5308 | 0.5048 |
106
+ | No log | 20.38 | 265 | 1.1987 | 0.5567 | 0.5382 |
107
+ | No log | 20.77 | 270 | 1.1627 | 0.5425 | 0.5344 |
108
+ | No log | 21.15 | 275 | 1.2200 | 0.5417 | 0.5133 |
109
+ | No log | 21.54 | 280 | 1.4727 | 0.5342 | 0.5152 |
110
+ | No log | 21.92 | 285 | 1.1766 | 0.55 | 0.5271 |
111
+ | No log | 22.31 | 290 | 1.3099 | 0.5458 | 0.5265 |
112
+ | No log | 22.69 | 295 | 1.3408 | 0.5558 | 0.5361 |
113
+ | No log | 23.08 | 300 | 1.2960 | 0.5458 | 0.5164 |
114
+ | No log | 23.46 | 305 | 1.3263 | 0.5417 | 0.5291 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - Transformers 4.33.3
120
+ - Pytorch 2.1.1+cu121
121
+ - Datasets 2.14.5
122
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/xlm-v-base",
3
+ "architectures": [
4
+ "XLMRobertaForMultipleChoice"
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
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.33.3",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 901629
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3b5884c29ed9be88180c5de7301eaac088f1521018994905f66fe7978498b9
3
+ size 3114045230
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b64583ee450a0d7aec5ff066e44cab31e9c86972108aba896f5220b4f3dbbec
3
+ size 4536