Model save
Browse files- README.md +84 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: roberta-large
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: roberta-large-finetuned-lora-captures
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# roberta-large-finetuned-lora-captures
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4657
|
| 22 |
+
- Accuracy: 0.9264
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 20
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
|
| 56 |
+
| 0.2608 | 0.9994 | 772 | 0.3877 | 0.8888 |
|
| 57 |
+
| 0.3173 | 2.0 | 1545 | 0.3443 | 0.8932 |
|
| 58 |
+
| 0.2885 | 2.9994 | 2317 | 0.2995 | 0.9161 |
|
| 59 |
+
| 0.2566 | 4.0 | 3090 | 0.2884 | 0.9163 |
|
| 60 |
+
| 0.1908 | 4.9994 | 3862 | 0.3115 | 0.9140 |
|
| 61 |
+
| 0.1973 | 6.0 | 4635 | 0.2891 | 0.9186 |
|
| 62 |
+
| 0.1071 | 6.9994 | 5407 | 0.2913 | 0.9218 |
|
| 63 |
+
| 0.1177 | 8.0 | 6180 | 0.3057 | 0.9212 |
|
| 64 |
+
| 0.1775 | 8.9994 | 6952 | 0.3390 | 0.9184 |
|
| 65 |
+
| 0.0994 | 10.0 | 7725 | 0.3260 | 0.9218 |
|
| 66 |
+
| 0.08 | 10.9994 | 8497 | 0.3303 | 0.9264 |
|
| 67 |
+
| 0.1041 | 12.0 | 9270 | 0.3738 | 0.9209 |
|
| 68 |
+
| 0.0633 | 12.9994 | 10042 | 0.3629 | 0.9271 |
|
| 69 |
+
| 0.0253 | 14.0 | 10815 | 0.3967 | 0.9239 |
|
| 70 |
+
| 0.0625 | 14.9994 | 11587 | 0.4285 | 0.9246 |
|
| 71 |
+
| 0.0627 | 16.0 | 12360 | 0.4360 | 0.9244 |
|
| 72 |
+
| 0.0551 | 16.9994 | 13132 | 0.4430 | 0.9267 |
|
| 73 |
+
| 0.0545 | 18.0 | 13905 | 0.4695 | 0.9251 |
|
| 74 |
+
| 0.0434 | 18.9994 | 14677 | 0.4622 | 0.9271 |
|
| 75 |
+
| 0.021 | 19.9871 | 15440 | 0.4657 | 0.9264 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- PEFT 0.11.1
|
| 81 |
+
- Transformers 4.40.2
|
| 82 |
+
- Pytorch 2.3.0+cu121
|
| 83 |
+
- Datasets 2.19.1
|
| 84 |
+
- Tokenizers 0.19.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7407672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:174f289230069d890d204166fda68fc276acc501ddef3773fa59627fd3460d09
|
| 3 |
size 7407672
|