Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: relevant_profession
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# relevant_profession
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.8640
|
| 18 |
+
- Acc At K: 0.9666
|
| 19 |
+
- Acc: 0.7152
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 64
|
| 40 |
+
- eval_batch_size: 64
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 8
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Acc At K | Acc |
|
| 49 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|
|
| 50 |
+
| 3.6523 | 0.5 | 18304 | 2.1025 | 0.8154 | 0.5818 |
|
| 51 |
+
| 1.7365 | 1.0 | 36608 | 1.4014 | 0.9097 | 0.6590 |
|
| 52 |
+
| 1.2636 | 1.5 | 54912 | 1.1711 | 0.9350 | 0.6845 |
|
| 53 |
+
| 1.092 | 2.0 | 73216 | 1.0605 | 0.9473 | 0.6931 |
|
| 54 |
+
| 0.9662 | 2.5 | 91520 | 1.0046 | 0.9533 | 0.7012 |
|
| 55 |
+
| 0.9233 | 3.0 | 109824 | 0.9643 | 0.9573 | 0.7025 |
|
| 56 |
+
| 0.8521 | 3.5 | 128128 | 0.9436 | 0.9594 | 0.7060 |
|
| 57 |
+
| 0.8334 | 4.0 | 146432 | 0.9189 | 0.9616 | 0.7078 |
|
| 58 |
+
| 0.7845 | 4.5 | 164736 | 0.9082 | 0.9631 | 0.7091 |
|
| 59 |
+
| 0.7754 | 5.0 | 183040 | 0.8953 | 0.9639 | 0.7105 |
|
| 60 |
+
| 0.7355 | 5.5 | 201344 | 0.8907 | 0.9646 | 0.7108 |
|
| 61 |
+
| 0.7334 | 6.0 | 219648 | 0.8795 | 0.9649 | 0.7124 |
|
| 62 |
+
| 0.6991 | 6.5 | 237952 | 0.8772 | 0.9657 | 0.7132 |
|
| 63 |
+
| 0.7001 | 7.0 | 256256 | 0.8670 | 0.9662 | 0.7129 |
|
| 64 |
+
| 0.674 | 7.5 | 274560 | 0.8667 | 0.9664 | 0.7149 |
|
| 65 |
+
| 0.672 | 8.0 | 292864 | 0.8640 | 0.9666 | 0.7152 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.26.1
|
| 71 |
+
- Pytorch 2.0.0+cu117
|
| 72 |
+
- Datasets 2.11.0
|
| 73 |
+
- Tokenizers 0.13.3
|