Hugging Face's logo

djsull
/
aha_sentence_classification

Text Classification
Transformers
Safetensors
modernbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
djsull commited on
Commit
f880627
·
verified ·
1 Parent(s): c0e11d0

djsull/sent_classification

Browse files
Files changed (3) hide show
  1. README.md +16 -16
  2. config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7354
21
- - Accuracy: 0.7316
22
- - F1 Micro: 0.7316
23
- - F1 Macro: 0.4222
24
- - Precision Macro: 0.4524
25
- - Recall Macro: 0.4113
26
 
27
  ## Model description
28
 
@@ -54,16 +54,16 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Micro | F1 Macro | Precision Macro | Recall Macro |
56
  |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:--------:|:---------------:|:------------:|
57
- | 1.1113 | 0.5949 | 1000 | 0.9240 | 0.7121 | 0.7121 | 0.3417 | 0.3851 | 0.3598 |
58
- | 0.8622 | 1.1898 | 2000 | 0.8069 | 0.7146 | 0.7146 | 0.3950 | 0.4231 | 0.3979 |
59
- | 0.7967 | 1.7847 | 3000 | 0.7669 | 0.7212 | 0.7212 | 0.4115 | 0.4250 | 0.4221 |
60
- | 0.6931 | 2.3795 | 4000 | 0.7529 | 0.7219 | 0.7219 | 0.4319 | 0.4444 | 0.4246 |
61
- | 0.7087 | 2.9744 | 5000 | 0.7354 | 0.7316 | 0.7316 | 0.4222 | 0.4524 | 0.4113 |
62
- | 0.5718 | 3.5693 | 6000 | 0.7762 | 0.7184 | 0.7184 | 0.4239 | 0.4342 | 0.4215 |
63
- | 0.4475 | 4.1642 | 7000 | 0.8555 | 0.708 | 0.708 | 0.3976 | 0.4119 | 0.3899 |
64
- | 0.4542 | 4.7591 | 8000 | 0.8205 | 0.7224 | 0.7224 | 0.4015 | 0.4148 | 0.3925 |
65
- | 0.3716 | 5.3540 | 9000 | 0.9603 | 0.7039 | 0.7039 | 0.3931 | 0.4080 | 0.3939 |
66
- | 0.3644 | 5.9488 | 10000 | 0.9151 | 0.7099 | 0.7099 | 0.3965 | 0.4078 | 0.3922 |
67
 
68
 
69
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.8977
21
+ - Accuracy: 0.6701
22
+ - F1 Micro: 0.6701
23
+ - F1 Macro: 0.6301
24
+ - Precision Macro: 0.5833
25
+ - Recall Macro: 0.7331
26
 
27
  ## Model description
28
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Micro | F1 Macro | Precision Macro | Recall Macro |
56
  |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:--------:|:---------------:|:------------:|
57
+ | 1.3115 | 0.5949 | 1000 | 1.3492 | 0.5285 | 0.5285 | 0.5233 | 0.5079 | 0.6638 |
58
+ | 0.9152 | 1.1898 | 2000 | 1.0651 | 0.6243 | 0.6243 | 0.6065 | 0.5681 | 0.7156 |
59
+ | 0.8716 | 1.7847 | 3000 | 1.0069 | 0.6374 | 0.6374 | 0.6044 | 0.5635 | 0.7218 |
60
+ | 0.7678 | 2.3795 | 4000 | 0.9808 | 0.6293 | 0.6293 | 0.6154 | 0.5790 | 0.7316 |
61
+ | 0.7341 | 2.9744 | 5000 | 0.8977 | 0.6701 | 0.6701 | 0.6301 | 0.5833 | 0.7331 |
62
+ | 0.6194 | 3.5693 | 6000 | 0.9595 | 0.6499 | 0.6499 | 0.6221 | 0.5894 | 0.7091 |
63
+ | 0.4718 | 4.1642 | 7000 | 0.9216 | 0.6731 | 0.6731 | 0.6361 | 0.6053 | 0.6995 |
64
+ | 0.4739 | 4.7591 | 8000 | 0.9148 | 0.6739 | 0.6739 | 0.6484 | 0.6171 | 0.7059 |
65
+ | 0.433 | 5.3540 | 9000 | 1.0006 | 0.6616 | 0.6616 | 0.6298 | 0.5953 | 0.7092 |
66
+ | 0.3989 | 5.9488 | 10000 | 0.9988 | 0.6626 | 0.6626 | 0.6412 | 0.6157 | 0.7024 |
67
 
68
 
69
  ### Framework versions
config.json CHANGED
@@ -60,6 +60,6 @@
60
  "tokenizer_class": "BertTokenizer",
61
  "transformers_version": "4.56.1",
62
  "type_vocab_size": 1,
63
- "use_cache": false,
64
  "vocab_size": 32000
65
  }
 
60
  "tokenizer_class": "BertTokenizer",
61
  "transformers_version": "4.56.1",
62
  "type_vocab_size": 1,
63
+ "use_cache": true,
64
  "vocab_size": 32000
65
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a242d056612e4624f4de4d31513c4d0a8c4a879c3d73e0fb0dfa2e18b17db85c
3
  size 442545808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5029cc5e5c4f78dbe3082b65b81081564ee6b3cb0782b23de8341e0360a0ff23
3
  size 442545808