DimasikKurd commited on
Commit
0d27d67
·
verified ·
1 Parent(s): c5cb8ef

Training complete

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 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: severinsimmler/xlm-roberta-longformer-base-16384
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: longformer_pos
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # longformer_pos
20
+
21
+ This model is a fine-tuned version of [severinsimmler/xlm-roberta-longformer-base-16384](https://huggingface.co/severinsimmler/xlm-roberta-longformer-base-16384) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.6453
24
+ - Precision: 0.5508
25
+ - Recall: 0.5803
26
+ - F1: 0.5651
27
+ - Accuracy: 0.8941
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
+ - train_batch_size: 4
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 100
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.35 | 50 | 0.7424 | 0.0 | 0.0 | 0.0 | 0.7648 |
59
+ | No log | 2.7 | 100 | 0.4849 | 0.0415 | 0.0388 | 0.0401 | 0.8160 |
60
+ | No log | 4.05 | 150 | 0.3986 | 0.0902 | 0.1163 | 0.1016 | 0.8418 |
61
+ | No log | 5.41 | 200 | 0.3393 | 0.1827 | 0.1880 | 0.1853 | 0.8675 |
62
+ | No log | 6.76 | 250 | 0.3370 | 0.275 | 0.2132 | 0.2402 | 0.8788 |
63
+ | No log | 8.11 | 300 | 0.2937 | 0.3605 | 0.5310 | 0.4295 | 0.8864 |
64
+ | No log | 9.46 | 350 | 0.2793 | 0.4088 | 0.4302 | 0.4193 | 0.8997 |
65
+ | No log | 10.81 | 400 | 0.2500 | 0.4457 | 0.5969 | 0.5104 | 0.9066 |
66
+ | No log | 12.16 | 450 | 0.2894 | 0.5031 | 0.6221 | 0.5563 | 0.9107 |
67
+ | 0.3689 | 13.51 | 500 | 0.3678 | 0.5269 | 0.5116 | 0.5192 | 0.9036 |
68
+ | 0.3689 | 14.86 | 550 | 0.3156 | 0.5216 | 0.6085 | 0.5617 | 0.9100 |
69
+ | 0.3689 | 16.22 | 600 | 0.3824 | 0.5551 | 0.5756 | 0.5652 | 0.9115 |
70
+ | 0.3689 | 17.57 | 650 | 0.3347 | 0.4276 | 0.4981 | 0.4602 | 0.9075 |
71
+ | 0.3689 | 18.92 | 700 | 0.3705 | 0.4610 | 0.6880 | 0.5521 | 0.8920 |
72
+ | 0.3689 | 20.27 | 750 | 0.3276 | 0.5447 | 0.6492 | 0.5924 | 0.9100 |
73
+ | 0.3689 | 21.62 | 800 | 0.4603 | 0.5650 | 0.5562 | 0.5605 | 0.9107 |
74
+ | 0.3689 | 22.97 | 850 | 0.3142 | 0.5677 | 0.6260 | 0.5954 | 0.9177 |
75
+ | 0.3689 | 24.32 | 900 | 0.3887 | 0.5747 | 0.6260 | 0.5993 | 0.9164 |
76
+ | 0.3689 | 25.68 | 950 | 0.5906 | 0.4670 | 0.6860 | 0.5557 | 0.8789 |
77
+ | 0.0798 | 27.03 | 1000 | 0.5407 | 0.6218 | 0.5736 | 0.5968 | 0.8989 |
78
+ | 0.0798 | 28.38 | 1050 | 0.4645 | 0.5044 | 0.5504 | 0.5264 | 0.9051 |
79
+ | 0.0798 | 29.73 | 1100 | 0.3217 | 0.5107 | 0.6027 | 0.5529 | 0.9104 |
80
+ | 0.0798 | 31.08 | 1150 | 0.4471 | 0.5523 | 0.6647 | 0.6033 | 0.9055 |
81
+ | 0.0798 | 32.43 | 1200 | 0.4611 | 0.5029 | 0.6725 | 0.5755 | 0.8980 |
82
+ | 0.0798 | 33.78 | 1250 | 0.4495 | 0.5783 | 0.6085 | 0.5930 | 0.9155 |
83
+ | 0.0798 | 35.14 | 1300 | 0.5293 | 0.5727 | 0.6105 | 0.5910 | 0.9128 |
84
+ | 0.0798 | 36.49 | 1350 | 0.4453 | 0.5652 | 0.5795 | 0.5722 | 0.9100 |
85
+ | 0.0798 | 37.84 | 1400 | 0.3912 | 0.5988 | 0.5988 | 0.5988 | 0.9162 |
86
+ | 0.0798 | 39.19 | 1450 | 0.3862 | 0.5917 | 0.6066 | 0.5990 | 0.9182 |
87
+ | 0.0393 | 40.54 | 1500 | 0.4303 | 0.5337 | 0.6744 | 0.5959 | 0.9137 |
88
+ | 0.0393 | 41.89 | 1550 | 0.3846 | 0.5129 | 0.6550 | 0.5753 | 0.9119 |
89
+ | 0.0393 | 43.24 | 1600 | 0.5571 | 0.5735 | 0.6047 | 0.5887 | 0.9124 |
90
+ | 0.0393 | 44.59 | 1650 | 0.4528 | 0.5719 | 0.6395 | 0.6038 | 0.9182 |
91
+ | 0.0393 | 45.95 | 1700 | 0.5202 | 0.6037 | 0.6260 | 0.6147 | 0.9130 |
92
+ | 0.0393 | 47.3 | 1750 | 0.5163 | 0.5743 | 0.5019 | 0.5357 | 0.8990 |
93
+ | 0.0393 | 48.65 | 1800 | 0.3528 | 0.5771 | 0.6531 | 0.6127 | 0.9157 |
94
+ | 0.0393 | 50.0 | 1850 | 0.4441 | 0.5654 | 0.6531 | 0.6061 | 0.9155 |
95
+ | 0.0393 | 51.35 | 1900 | 0.4517 | 0.6262 | 0.6105 | 0.6183 | 0.9151 |
96
+ | 0.0393 | 52.7 | 1950 | 0.4142 | 0.5812 | 0.6105 | 0.5955 | 0.9142 |
97
+ | 0.0315 | 54.05 | 2000 | 0.4539 | 0.5694 | 0.6357 | 0.6007 | 0.9180 |
98
+ | 0.0315 | 55.41 | 2050 | 0.4912 | 0.4107 | 0.5795 | 0.4807 | 0.9097 |
99
+ | 0.0315 | 56.76 | 2100 | 0.4442 | 0.5514 | 0.5194 | 0.5349 | 0.9190 |
100
+ | 0.0315 | 58.11 | 2150 | 0.4871 | 0.5414 | 0.6337 | 0.5839 | 0.9074 |
101
+ | 0.0315 | 59.46 | 2200 | 0.6469 | 0.5937 | 0.5465 | 0.5691 | 0.9072 |
102
+ | 0.0315 | 60.81 | 2250 | 0.4975 | 0.6346 | 0.6395 | 0.6371 | 0.9167 |
103
+ | 0.0315 | 62.16 | 2300 | 0.4800 | 0.6060 | 0.6260 | 0.6158 | 0.9151 |
104
+ | 0.0315 | 63.51 | 2350 | 0.5273 | 0.6047 | 0.5988 | 0.6018 | 0.9137 |
105
+ | 0.0315 | 64.86 | 2400 | 0.4613 | 0.5794 | 0.6221 | 0.6 | 0.9145 |
106
+ | 0.0315 | 66.22 | 2450 | 0.4839 | 0.5996 | 0.6298 | 0.6144 | 0.9189 |
107
+ | 0.0287 | 67.57 | 2500 | 0.4725 | 0.4970 | 0.6415 | 0.5601 | 0.9020 |
108
+ | 0.0287 | 68.92 | 2550 | 0.5888 | 0.6614 | 0.5717 | 0.6133 | 0.8999 |
109
+ | 0.0287 | 70.27 | 2600 | 0.4525 | 0.6021 | 0.5601 | 0.5803 | 0.9086 |
110
+ | 0.0287 | 71.62 | 2650 | 0.4416 | 0.5743 | 0.6066 | 0.5900 | 0.9157 |
111
+ | 0.0287 | 72.97 | 2700 | 0.4290 | 0.5084 | 0.6473 | 0.5695 | 0.8974 |
112
+ | 0.0287 | 74.32 | 2750 | 0.5249 | 0.5778 | 0.5543 | 0.5658 | 0.9103 |
113
+ | 0.0287 | 75.68 | 2800 | 0.5481 | 0.6149 | 0.5601 | 0.5862 | 0.9042 |
114
+
115
+
116
+ ### Framework versions
117
+
118
+ - Transformers 4.38.2
119
+ - Pytorch 2.1.2
120
+ - Datasets 2.1.0
121
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "severinsimmler/xlm-roberta-longformer-base-16384",
3
+ "architectures": [
4
+ "LongformerForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 256,
9
+ 256,
10
+ 256,
11
+ 256,
12
+ 256,
13
+ 256,
14
+ 256,
15
+ 256,
16
+ 256,
17
+ 256,
18
+ 256,
19
+ 256
20
+ ],
21
+ "bos_token_id": 0,
22
+ "classifier_dropout": null,
23
+ "eos_token_id": 2,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 768,
27
+ "id2label": {
28
+ "0": "O",
29
+ "1": "B-symp",
30
+ "2": "I-symp"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "0": "O",
36
+ "1": "B-symp",
37
+ "2": "I-symp"
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "max_position_embeddings": 16386,
41
+ "model_type": "longformer",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "onnx_export": false,
45
+ "pad_token_id": 1,
46
+ "position_embedding_type": "absolute",
47
+ "sep_token_id": 2,
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.38.2",
50
+ "type_vocab_size": 1,
51
+ "vocab_size": 250002
52
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88b95f516ab9d228005da137585905b70742576ee2b89da92b1e1ddb2c94c8a
3
+ size 1243659772
runs/May07_12-02-53_8dd371958cdf/events.out.tfevents.1715083375.8dd371958cdf.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4206c95daa0e60a71dfd7c83b9ea0151f20314457080414cb70540b797cfa4f
3
+ size 32731
runs/May07_12-02-53_8dd371958cdf/events.out.tfevents.1715085555.8dd371958cdf.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad997ebc694ff6d7e045dd68d45decd4da9c662b6f523fb768397045fa9767ff
3
+ size 560
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a1396e1ff4e78518af44b7521d9e5b9c6219fed36303610d202b685bab9782
3
+ size 17082856
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "250001": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 16384,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ec717d97078bf63b767df4d1c63c868997ea4e102dd41e1ed06c0d1cf2af56
3
+ size 4920