Shijia commited on
Commit
b086534
1 Parent(s): 336d573

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 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: yihongLiu/furina
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: furina_seed42_eng_amh_hau_cross_5e-06
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # furina_seed42_eng_amh_hau_cross_5e-06
14
+
15
+ This model is a fine-tuned version of [yihongLiu/furina](https://huggingface.co/yihongLiu/furina) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0212
18
+ - Spearman Corr: 0.7804
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-06
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 128
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 30
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
51
+ |:-------------:|:-----:|:----:|:---------------:|:-------------:|
52
+ | No log | 0.52 | 200 | 0.0431 | 0.2948 |
53
+ | No log | 1.04 | 400 | 0.0295 | 0.6292 |
54
+ | No log | 1.55 | 600 | 0.0256 | 0.6932 |
55
+ | 0.0687 | 2.07 | 800 | 0.0237 | 0.7162 |
56
+ | 0.0687 | 2.59 | 1000 | 0.0237 | 0.7313 |
57
+ | 0.0687 | 3.11 | 1200 | 0.0231 | 0.7308 |
58
+ | 0.0687 | 3.63 | 1400 | 0.0222 | 0.7511 |
59
+ | 0.0309 | 4.15 | 1600 | 0.0218 | 0.7502 |
60
+ | 0.0309 | 4.66 | 1800 | 0.0218 | 0.7596 |
61
+ | 0.0309 | 5.18 | 2000 | 0.0210 | 0.7642 |
62
+ | 0.0309 | 5.7 | 2200 | 0.0203 | 0.7723 |
63
+ | 0.0268 | 6.22 | 2400 | 0.0207 | 0.7731 |
64
+ | 0.0268 | 6.74 | 2600 | 0.0203 | 0.7709 |
65
+ | 0.0268 | 7.25 | 2800 | 0.0211 | 0.7667 |
66
+ | 0.0268 | 7.77 | 3000 | 0.0231 | 0.7691 |
67
+ | 0.0236 | 8.29 | 3200 | 0.0225 | 0.7750 |
68
+ | 0.0236 | 8.81 | 3400 | 0.0216 | 0.7777 |
69
+ | 0.0236 | 9.33 | 3600 | 0.0222 | 0.7725 |
70
+ | 0.0236 | 9.84 | 3800 | 0.0212 | 0.7804 |
71
+
72
+
73
+ ### Framework versions
74
+
75
+ - Transformers 4.37.2
76
+ - Pytorch 2.1.0+cu121
77
+ - Datasets 2.17.0
78
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "yihongLiu/furina",
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
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 514,
23
+ "model_type": "xlm-roberta",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 1,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "regression",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.37.2",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 401145
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a02c89e677ea7db4ba945eb15ad034d94717ab020d705c902845d250c31685
3
+ size 1576513492
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a313a26470baedaede322622492f2a542aa41527ddc5d40de444e945ad3c613
3
+ size 7658320
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": true,
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 sha256:849984098c26f9b2f4a2d6104a148685f09571ecb72597422e478fb9309e50e8
3
+ size 26885962
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
+ "401144": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
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": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>",
55
+ "use_fast": true
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfeb4360c5c25fec1005283350d16b668347d9903732408b618c3ebe30933755
3
+ size 4728