haryoaw commited on
Commit
bdc1011
1 Parent(s): 6fa6be8

Initial Commit

Browse files
Files changed (4) hide show
  1. README.md +88 -0
  2. config.json +38 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_data-cl-cardiff_cl_only_delta
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_data-cl-cardiff_cl_only_delta
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: 1.0448
22
+ - Accuracy: 0.4838
23
+ - F1: 0.4798
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: 11213
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 30
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
54
+ | No log | 1.09 | 250 | 1.0988 | 0.3333 | 0.1667 |
55
+ | 1.0959 | 2.17 | 500 | 1.0989 | 0.3333 | 0.1667 |
56
+ | 1.0959 | 3.26 | 750 | 1.1000 | 0.3333 | 0.1667 |
57
+ | 1.0996 | 4.35 | 1000 | 1.1023 | 0.3333 | 0.1667 |
58
+ | 1.0996 | 5.43 | 1250 | 1.0990 | 0.3333 | 0.1667 |
59
+ | 1.1001 | 6.52 | 1500 | 1.0997 | 0.3333 | 0.1667 |
60
+ | 1.1001 | 7.61 | 1750 | 1.0998 | 0.3333 | 0.1667 |
61
+ | 1.0992 | 8.7 | 2000 | 1.0988 | 0.3333 | 0.1667 |
62
+ | 1.0992 | 9.78 | 2250 | 1.0990 | 0.3333 | 0.1667 |
63
+ | 1.0998 | 10.87 | 2500 | 1.0992 | 0.3333 | 0.1667 |
64
+ | 1.0998 | 11.96 | 2750 | 1.0996 | 0.3333 | 0.1667 |
65
+ | 1.0994 | 13.04 | 3000 | 1.0987 | 0.3333 | 0.1667 |
66
+ | 1.0994 | 14.13 | 3250 | 1.0988 | 0.3333 | 0.1667 |
67
+ | 1.0993 | 15.22 | 3500 | 1.0993 | 0.3333 | 0.1667 |
68
+ | 1.0993 | 16.3 | 3750 | 1.0987 | 0.3333 | 0.1667 |
69
+ | 1.0995 | 17.39 | 4000 | 1.0986 | 0.3333 | 0.1667 |
70
+ | 1.0995 | 18.48 | 4250 | 1.0989 | 0.3333 | 0.1667 |
71
+ | 1.0991 | 19.57 | 4500 | 1.0989 | 0.3333 | 0.1667 |
72
+ | 1.0991 | 20.65 | 4750 | 1.0987 | 0.3333 | 0.1667 |
73
+ | 1.0994 | 21.74 | 5000 | 1.0987 | 0.3333 | 0.1667 |
74
+ | 1.0994 | 22.83 | 5250 | 1.0987 | 0.3333 | 0.1667 |
75
+ | 1.0991 | 23.91 | 5500 | 1.0987 | 0.3333 | 0.1667 |
76
+ | 1.0991 | 25.0 | 5750 | 1.0986 | 0.3333 | 0.1667 |
77
+ | 1.0991 | 26.09 | 6000 | 1.0987 | 0.3333 | 0.1667 |
78
+ | 1.0991 | 27.17 | 6250 | 1.0986 | 0.3333 | 0.1667 |
79
+ | 1.0946 | 28.26 | 6500 | 1.0796 | 0.4560 | 0.4220 |
80
+ | 1.0946 | 29.35 | 6750 | 1.0448 | 0.4838 | 0.4798 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.33.3
86
+ - Pytorch 2.1.1+cu121
87
+ - Datasets 2.14.5
88
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/xlm-v-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "xlm-roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.33.3",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 901629
38
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90471a21160546597b1221e998a05d88c741e804dfd53a6f19ead8084e4b62cc
3
+ size 3114051374
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497e2c6d425b9eec31a720c71aedc02adeec0c5301e4ae6501b6f2a40bda48f1
3
+ size 4600