Hugging Face's logo

TransferGraph
/
Jeevesh8_init_bert_ft_qqp-33-finetuned-lora-tweet_eval_irony

Text Classification
PEFT
Safetensors
parquet
Eval Results
Model card Files Community
hilco commited on
Commit
5c5ff30
·
verified ·
1 Parent(s): 1c0696d

Finished training.

Browse files
Files changed (2) hide show
  1. README.md +9 -8
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  args: irony
23
  metrics:
24
  - type: accuracy
25
- value: 0.5005235602094241
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-33](https://huggingface.co/Jeevesh8/init_bert_ft_qqp-33) on the tweet_eval dataset.
35
  It achieves the following results on the evaluation set:
36
- - accuracy: 0.5005
37
 
38
  ## Model description
39
 
@@ -52,23 +52,24 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.0004
56
  - train_batch_size: 32
57
  - eval_batch_size: 32
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 4
62
 
63
  ### Training results
64
 
65
  | accuracy | train_loss | epoch |
66
  |:--------:|:----------:|:-----:|
67
  | 0.5152 | None | 0 |
68
- | 0.5215 | 0.8020 | 0 |
69
- | 0.4806 | 0.6958 | 1 |
70
- | 0.4890 | 0.6930 | 2 |
71
- | 0.5005 | 0.6909 | 3 |
 
72
 
73
 
74
  ### Framework versions
 
22
  args: irony
23
  metrics:
24
  - type: accuracy
25
+ value: 0.5507853403141362
26
  name: accuracy
27
  ---
28
 
 
33
 
34
  This model is a fine-tuned version of [Jeevesh8/init_bert_ft_qqp-33](https://huggingface.co/Jeevesh8/init_bert_ft_qqp-33) on the tweet_eval dataset.
35
  It achieves the following results on the evaluation set:
36
+ - accuracy: 0.5508
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.0005
56
  - train_batch_size: 32
57
  - eval_batch_size: 32
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 5
62
 
63
  ### Training results
64
 
65
  | accuracy | train_loss | epoch |
66
  |:--------:|:----------:|:-----:|
67
  | 0.5152 | None | 0 |
68
+ | 0.5204 | 0.7877 | 0 |
69
+ | 0.4869 | 0.6948 | 1 |
70
+ | 0.5277 | 0.6879 | 2 |
71
+ | 0.5403 | 0.6730 | 3 |
72
+ | 0.5508 | 0.6677 | 4 |
73
 
74
 
75
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd6c3ccc474aea0b1ad852fa4ded96f4d574a40216fea06da0020512695a646d
3
  size 160400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc6e058eeb368c570634934adcb341134ae3c061417794a64109058e7b99642
3
  size 160400