m4faisal commited on
Commit
a3ec2ba
·
verified ·
1 Parent(s): f3f454b

End of training

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
8
+ model-index:
9
+ - name: NLI-Lora-Fine-Tuning-10K-Roberta
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # NLI-Lora-Fine-Tuning-10K-Roberta
17
+
18
+ This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-sentiment-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-sentiment-latest) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7314
21
+ - Accuracy: 0.6795
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 312 | 1.0705 | 0.4207 |
53
+ | 1.1119 | 2.0 | 624 | 1.0411 | 0.4660 |
54
+ | 1.1119 | 3.0 | 936 | 0.9899 | 0.5193 |
55
+ | 1.0398 | 4.0 | 1248 | 0.9264 | 0.5667 |
56
+ | 0.9603 | 5.0 | 1560 | 0.8394 | 0.6222 |
57
+ | 0.9603 | 6.0 | 1872 | 0.7944 | 0.6380 |
58
+ | 0.8749 | 7.0 | 2184 | 0.7575 | 0.6665 |
59
+ | 0.8749 | 8.0 | 2496 | 0.7439 | 0.6689 |
60
+ | 0.822 | 9.0 | 2808 | 0.7331 | 0.6795 |
61
+ | 0.8073 | 10.0 | 3120 | 0.7314 | 0.6795 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - PEFT 0.9.0
67
+ - Transformers 4.38.2
68
+ - Pytorch 2.2.1+cu121
69
+ - Datasets 2.18.0
70
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ce6ef35375fb36c135334f87b2af5cf81c6505f57564511b69a1aa651596f98
3
  size 2821300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb39bc5c458461f46696d519e47ce70f05d9b2ecdb1a7bc727d708445ea1a835
3
  size 2821300
runs/Mar20_19-14-28_bfa050c8a3ec/events.out.tfevents.1710962086.bfa050c8a3ec.1635.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76fd6b57663c1af2e0da8c6972df777aef4093b92d55898527bddf91447e901a
3
- size 8847
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06352051608b02c84035d8490ba883e1b5e42d91866eb7fdee5150e25eac8c15
3
+ size 9735