Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: xlm-roberta-base
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: lora_alpha_64_drop_0.3_rank_32_seed_42_merges_40_08062024
|
| 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 |
+
# lora_alpha_64_drop_0.3_rank_32_seed_42_merges_40_08062024
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4618
|
| 22 |
+
- Accuracy: 0.8305
|
| 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: 32
|
| 43 |
+
- eval_batch_size: 32
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 25.0
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 53 |
+
| 0.3456 | 1.0 | 12272 | 0.4626 | 0.8289 |
|
| 54 |
+
| 0.3458 | 2.0 | 24544 | 0.4889 | 0.8253 |
|
| 55 |
+
| 0.3402 | 3.0 | 36816 | 0.4702 | 0.8285 |
|
| 56 |
+
| 0.3445 | 4.0 | 49088 | 0.4648 | 0.8333 |
|
| 57 |
+
| 0.3408 | 5.0 | 61360 | 0.4701 | 0.8301 |
|
| 58 |
+
| 0.341 | 6.0 | 73632 | 0.4628 | 0.8309 |
|
| 59 |
+
| 0.3275 | 7.0 | 85904 | 0.4700 | 0.8281 |
|
| 60 |
+
| 0.3455 | 8.0 | 98176 | 0.4572 | 0.8305 |
|
| 61 |
+
| 0.3455 | 9.0 | 110448 | 0.4795 | 0.8321 |
|
| 62 |
+
| 0.3336 | 10.0 | 122720 | 0.4597 | 0.8273 |
|
| 63 |
+
| 0.3317 | 11.0 | 134992 | 0.4716 | 0.8309 |
|
| 64 |
+
| 0.33 | 12.0 | 147264 | 0.4605 | 0.8341 |
|
| 65 |
+
| 0.3279 | 13.0 | 159536 | 0.4824 | 0.8265 |
|
| 66 |
+
| 0.323 | 14.0 | 171808 | 0.4634 | 0.8285 |
|
| 67 |
+
| 0.3276 | 15.0 | 184080 | 0.4876 | 0.8305 |
|
| 68 |
+
| 0.3254 | 16.0 | 196352 | 0.4658 | 0.8297 |
|
| 69 |
+
| 0.3349 | 17.0 | 208624 | 0.4713 | 0.8297 |
|
| 70 |
+
| 0.334 | 18.0 | 220896 | 0.4759 | 0.8285 |
|
| 71 |
+
| 0.3319 | 19.0 | 233168 | 0.4664 | 0.8321 |
|
| 72 |
+
| 0.3425 | 20.0 | 245440 | 0.4761 | 0.8285 |
|
| 73 |
+
| 0.3366 | 21.0 | 257712 | 0.4599 | 0.8329 |
|
| 74 |
+
| 0.3475 | 22.0 | 269984 | 0.4614 | 0.8313 |
|
| 75 |
+
| 0.3416 | 23.0 | 282256 | 0.4590 | 0.8317 |
|
| 76 |
+
| 0.3455 | 24.0 | 294528 | 0.4630 | 0.8305 |
|
| 77 |
+
| 0.3399 | 25.0 | 306800 | 0.4618 | 0.8305 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- PEFT 0.11.1
|
| 83 |
+
- Transformers 4.41.1
|
| 84 |
+
- Pytorch 2.3.0+cu121
|
| 85 |
+
- Datasets 2.18.0
|
| 86 |
+
- Tokenizers 0.19.1
|