update model card README.md
Browse files
README.md
CHANGED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: Debertalarg_model_multichoice_Version2
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# Debertalarg_model_multichoice_Version2
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [VuongQuoc/Debertalarg_model_multichoice_Version2](https://huggingface.co/VuongQuoc/Debertalarg_model_multichoice_Version2) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.7733
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 7e-07
|
| 36 |
+
- train_batch_size: 2
|
| 37 |
+
- eval_batch_size: 4
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_ratio: 0.6
|
| 42 |
+
- num_epochs: 2
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 1.4268 | 0.04 | 500 | 1.3693 |
|
| 49 |
+
| 1.4108 | 0.08 | 1000 | 1.3603 |
|
| 50 |
+
| 1.419 | 0.12 | 1500 | 1.3444 |
|
| 51 |
+
| 1.3911 | 0.15 | 2000 | 1.3143 |
|
| 52 |
+
| 1.3992 | 0.19 | 2500 | 1.3018 |
|
| 53 |
+
| 1.3495 | 0.23 | 3000 | 1.2723 |
|
| 54 |
+
| 1.3268 | 0.27 | 3500 | 1.2392 |
|
| 55 |
+
| 1.3156 | 0.31 | 4000 | 1.2489 |
|
| 56 |
+
| 1.3059 | 0.35 | 4500 | 1.1842 |
|
| 57 |
+
| 1.2759 | 0.39 | 5000 | 1.1568 |
|
| 58 |
+
| 1.2281 | 0.42 | 5500 | 1.1469 |
|
| 59 |
+
| 1.2769 | 0.46 | 6000 | 1.0952 |
|
| 60 |
+
| 1.2902 | 0.5 | 6500 | 1.1061 |
|
| 61 |
+
| 1.2502 | 0.54 | 7000 | 1.0716 |
|
| 62 |
+
| 1.199 | 0.58 | 7500 | 1.0360 |
|
| 63 |
+
| 1.155 | 0.62 | 8000 | 1.0077 |
|
| 64 |
+
| 1.077 | 0.65 | 8500 | 0.9857 |
|
| 65 |
+
| 0.9807 | 0.69 | 9000 | 1.0340 |
|
| 66 |
+
| 1.1629 | 0.73 | 9500 | 0.9626 |
|
| 67 |
+
| 1.2101 | 0.77 | 10000 | 0.9675 |
|
| 68 |
+
| 1.1597 | 0.81 | 10500 | 0.9190 |
|
| 69 |
+
| 1.1831 | 0.85 | 11000 | 0.9314 |
|
| 70 |
+
| 1.1691 | 0.89 | 11500 | 0.9056 |
|
| 71 |
+
| 1.1335 | 0.92 | 12000 | 0.8997 |
|
| 72 |
+
| 1.1413 | 0.96 | 12500 | 0.8887 |
|
| 73 |
+
| 1.1218 | 1.0 | 13000 | 0.8684 |
|
| 74 |
+
| 1.0662 | 1.04 | 13500 | 0.8655 |
|
| 75 |
+
| 1.0599 | 1.08 | 14000 | 0.8869 |
|
| 76 |
+
| 1.0523 | 1.12 | 14500 | 0.8401 |
|
| 77 |
+
| 1.075 | 1.16 | 15000 | 0.8672 |
|
| 78 |
+
| 1.0394 | 1.19 | 15500 | 0.8323 |
|
| 79 |
+
| 1.0957 | 1.23 | 16000 | 0.8146 |
|
| 80 |
+
| 1.0363 | 1.27 | 16500 | 0.8549 |
|
| 81 |
+
| 1.0995 | 1.31 | 17000 | 0.8001 |
|
| 82 |
+
| 1.0742 | 1.35 | 17500 | 0.7952 |
|
| 83 |
+
| 1.0417 | 1.39 | 18000 | 0.8050 |
|
| 84 |
+
| 1.0712 | 1.43 | 18500 | 0.7935 |
|
| 85 |
+
| 1.0654 | 1.46 | 19000 | 0.7746 |
|
| 86 |
+
| 1.113 | 1.5 | 19500 | 0.7679 |
|
| 87 |
+
| 1.0387 | 1.54 | 20000 | 0.8220 |
|
| 88 |
+
| 1.0564 | 1.58 | 20500 | 0.7756 |
|
| 89 |
+
| 1.037 | 1.62 | 21000 | 0.7907 |
|
| 90 |
+
| 1.0565 | 1.66 | 21500 | 0.7760 |
|
| 91 |
+
| 1.0553 | 1.7 | 22000 | 0.8027 |
|
| 92 |
+
| 1.0582 | 1.73 | 22500 | 0.7729 |
|
| 93 |
+
| 1.0546 | 1.77 | 23000 | 0.7844 |
|
| 94 |
+
| 1.0346 | 1.81 | 23500 | 0.7736 |
|
| 95 |
+
| 1.0416 | 1.85 | 24000 | 0.7791 |
|
| 96 |
+
| 1.0402 | 1.89 | 24500 | 0.7795 |
|
| 97 |
+
| 1.1279 | 1.93 | 25000 | 0.7698 |
|
| 98 |
+
| 1.0703 | 1.96 | 25500 | 0.7733 |
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
### Framework versions
|
| 102 |
+
|
| 103 |
+
- Transformers 4.30.2
|
| 104 |
+
- Pytorch 2.0.0
|
| 105 |
+
- Datasets 2.1.0
|
| 106 |
+
- Tokenizers 0.13.3
|