Hugging Face's logo

chathuru
/
CuATR-distilbert-LoRA

Safetensors
Generated from Trainer
Model card Files Community
chathuru commited on
Commit
0714160
•
1 Parent(s): 6501957

CuATR-distilbert-LoRA

Browse files
Files changed (4) hide show
  1. README.md +14 -7
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6865
22
- - Accuracy: 0.6087
23
- - F1: 0.7429
24
 
25
  ## Model description
26
 
@@ -47,16 +47,23 @@ The following hyperparameters were used during training:
47
  - total_train_batch_size: 64
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 4
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
57
- | 0.6894 | 0.67 | 1 | 0.6867 | 0.6087 | 0.7429 |
58
- | 0.6931 | 2.0 | 3 | 0.6865 | 0.6087 | 0.7429 |
59
- | 0.6873 | 2.67 | 4 | 0.6865 | 0.6087 | 0.7429 |
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6999
22
+ - Accuracy: 0.0870
23
+ - F1: 0.0870
24
 
25
  ## Model description
26
 
 
47
  - total_train_batch_size: 64
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 14
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
57
+ | 0.7063 | 0.67 | 1 | 0.7011 | 0.0870 | 0.0870 |
58
+ | 0.6861 | 2.0 | 3 | 0.7008 | 0.0870 | 0.0870 |
59
+ | 0.6976 | 2.67 | 4 | 0.7007 | 0.0870 | 0.0870 |
60
+ | 0.7033 | 4.0 | 6 | 0.7004 | 0.0870 | 0.0870 |
61
+ | 0.7011 | 4.67 | 7 | 0.7003 | 0.0870 | 0.0870 |
62
+ | 0.698 | 6.0 | 9 | 0.7002 | 0.0870 | 0.0870 |
63
+ | 0.7037 | 6.67 | 10 | 0.7001 | 0.0870 | 0.0870 |
64
+ | 0.6977 | 8.0 | 12 | 0.7000 | 0.0870 | 0.0870 |
65
+ | 0.7002 | 8.67 | 13 | 0.7000 | 0.0870 | 0.0870 |
66
+ | 0.6995 | 9.33 | 14 | 0.6999 | 0.0870 | 0.0870 |
67
 
68
 
69
  ### Framework versions
adapter_config.json CHANGED
@@ -16,9 +16,9 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "v_lin",
20
  "q_lin",
21
- "k_lin"
 
22
  ],
23
  "task_type": "TOKEN_CLS"
24
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
19
  "q_lin",
20
+ "k_lin",
21
+ "v_lin"
22
  ],
23
  "task_type": "TOKEN_CLS"
24
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2303adc67ddf09fc04b437f94e611540e087e9104083d01ac994cf027044b73
3
  size 447536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46de21be5f826a8bb505a096e7cce4fa2020dd39e306bcb90c95b3c4c78e1d5
3
  size 447536
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28b83cee47f7fb3807d87d114642f6a24ecf08708f7e1deea6b3572f865871a8
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b498cdae053c0476cb868b3e16d621ff5d43bf34f20c923f0c2ab78edb09fadf
3
  size 4600