Hugging Face's logo

AurrieMartinez
/
roberta-base-lora-text-classification

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
AurrieMartinez commited on
Commit
5f33ab4
•
1 Parent(s): f200b07

AurrieMartinez/roberta-base-lora-text-classification-by-finetuning-roberta

Browse files
Files changed (6) hide show
  1. README.md +7 -13
  2. adapter_model.safetensors +1 -1
  3. runs/Jun05_16-12-54_40dde6e293b3/events.out.tfevents.1717603975.40dde6e293b3.854.0 +3 -0
  4. runs/Jun05_16-32-28_40dde6e293b3/events.out.tfevents.1717605148.40dde6e293b3.6571.0 +3 -0
  5. runs/Jun05_16-33-40_40dde6e293b3/events.out.tfevents.1717605221.40dde6e293b3.6989.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6577
22
- - Accuracy: {'accuracy': 0.933}
23
 
24
  ## Model description
25
 
@@ -44,22 +44,16 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 10
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------------------:|
53
- | No log | 1.0 | 250 | 0.2663 | {'accuracy': 0.936} |
54
- | 0.4315 | 2.0 | 500 | 0.3082 | {'accuracy': 0.934} |
55
- | 0.4315 | 3.0 | 750 | 0.4077 | {'accuracy': 0.937} |
56
- | 0.1531 | 4.0 | 1000 | 0.5257 | {'accuracy': 0.93} |
57
- | 0.1531 | 5.0 | 1250 | 0.5102 | {'accuracy': 0.939} |
58
- | 0.0797 | 6.0 | 1500 | 0.5795 | {'accuracy': 0.934} |
59
- | 0.0797 | 7.0 | 1750 | 0.5838 | {'accuracy': 0.933} |
60
- | 0.0373 | 8.0 | 2000 | 0.6731 | {'accuracy': 0.933} |
61
- | 0.0373 | 9.0 | 2250 | 0.6507 | {'accuracy': 0.938} |
62
- | 0.0218 | 10.0 | 2500 | 0.6577 | {'accuracy': 0.933} |
63
 
64
 
65
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4099
22
+ - Accuracy: {'accuracy': 0.934}
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 4
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------------------:|
53
+ | No log | 1.0 | 250 | 0.2177 | {'accuracy': 0.944} |
54
+ | 0.3854 | 2.0 | 500 | 0.2950 | {'accuracy': 0.934} |
55
+ | 0.3854 | 3.0 | 750 | 0.3770 | {'accuracy': 0.931} |
56
+ | 0.12 | 4.0 | 1000 | 0.4099 | {'accuracy': 0.934} |
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45bd8a6e0c0180b2d6305c03d6847ff1dd5e9b4df8921a27f6e6c82a38956fcc
3
  size 2667328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e5121acb7df84e9a70bd4c6da84660791f981fe0d57fd459ba9ec81fd6e6d6
3
  size 2667328
runs/Jun05_16-12-54_40dde6e293b3/events.out.tfevents.1717603975.40dde6e293b3.854.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62246fcd21a49cefe4a599d4f70bfff3ae65d4e0213b1138ff7d915feb47772b
3
+ size 9113
runs/Jun05_16-32-28_40dde6e293b3/events.out.tfevents.1717605148.40dde6e293b3.6571.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c827641d70b6c4e5cd7a27c0180f8707adb01c6b00ab22a0c54f99c51fc8e1
3
+ size 4136
runs/Jun05_16-33-40_40dde6e293b3/events.out.tfevents.1717605221.40dde6e293b3.6989.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9871d60704377c6343590f8eab074b03430c9e3aa9aa187f7aa73cbb4494bdc4
3
+ size 6805
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cfde429cd6aaef7fcc412ffe08c7ad2f1a343914eee80376bb0f8490a5c637b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c5fa7eda04e03dd93d33de45ade8c80687726a71d4871a2c76099aed3d347ff
3
  size 5176