Hugging Face's logo

TransferGraph
/
Jeevesh8_init_bert_ft_qqp-28-finetuned-lora-tweet_eval_irony

Text Classification
PEFT
Safetensors
parquet
Eval Results
Model card Files Community
hilco commited on
Commit
a9e1e05
•
1 Parent(s): ba60d1a

Finished training.

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  args: irony
23
  metrics:
24
  - type: accuracy
25
- value: 0.625130890052356
26
  name: accuracy
27
  ---
28
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [Jeevesh8/init_bert_ft_qqp-28](https://huggingface.co/Jeevesh8/init_bert_ft_qqp-28) on the tweet_eval dataset.
35
  It achieves the following results on the evaluation set:
36
- - accuracy: 0.6251
37
 
38
  ## Model description
39
 
@@ -65,14 +65,14 @@ The following hyperparameters were used during training:
65
  | accuracy | train_loss | epoch |
66
  |:--------:|:----------:|:-----:|
67
  | 0.5204 | None | 0 |
68
- | 0.5351 | 0.8160 | 0 |
69
- | 0.5497 | 0.6798 | 1 |
70
- | 0.5634 | 0.6626 | 2 |
71
- | 0.5843 | 0.6540 | 3 |
72
- | 0.5979 | 0.6398 | 4 |
73
- | 0.6136 | 0.6319 | 5 |
74
- | 0.6094 | 0.6197 | 6 |
75
- | 0.6251 | 0.6157 | 7 |
76
 
77
 
78
  ### Framework versions
 
22
  args: irony
23
  metrics:
24
  - type: accuracy
25
+ value: 0.6167539267015707
26
  name: accuracy
27
  ---
28
 
 
33
 
34
  This model is a fine-tuned version of [Jeevesh8/init_bert_ft_qqp-28](https://huggingface.co/Jeevesh8/init_bert_ft_qqp-28) on the tweet_eval dataset.
35
  It achieves the following results on the evaluation set:
36
+ - accuracy: 0.6168
37
 
38
  ## Model description
39
 
 
65
  | accuracy | train_loss | epoch |
66
  |:--------:|:----------:|:-----:|
67
  | 0.5204 | None | 0 |
68
+ | 0.5246 | 0.8160 | 0 |
69
+ | 0.5319 | 0.6805 | 1 |
70
+ | 0.5644 | 0.6623 | 2 |
71
+ | 0.5770 | 0.6547 | 3 |
72
+ | 0.6010 | 0.6398 | 4 |
73
+ | 0.6147 | 0.6311 | 5 |
74
+ | 0.6031 | 0.6199 | 6 |
75
+ | 0.6168 | 0.6153 | 7 |
76
 
77
 
78
  ### Framework versions
adapter_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "value",
23
- "query"
24
  ],
25
  "task_type": "SEQ_CLS",
26
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "query",
23
+ "value"
24
  ],
25
  "task_type": "SEQ_CLS",
26
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:252006528fd8f8797957ed1dfb8c1886fe1cfd419163cdba6330c42102e78483
3
  size 160400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:272f2c12e87bf14ad988913647c1fb591ece88b271cf6b0fd387028570f9f176
3
  size 160400