update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: Davlan/afro-xlmr-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
- f1
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: wandb_v4_5e-5
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# wandb_v4_5e-5
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [Davlan/afro-xlmr-base](https://huggingface.co/Davlan/afro-xlmr-base) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1647
|
| 24 |
+
- Precision: 0.3544
|
| 25 |
+
- Recall: 0.2986
|
| 26 |
+
- F1: 0.3241
|
| 27 |
+
- Accuracy: 0.9519
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 8
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 5
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| 0.1942 | 0.54 | 500 | 0.1416 | 0.3913 | 0.1885 | 0.2544 | 0.9571 |
|
| 59 |
+
| 0.1761 | 1.07 | 1000 | 0.1391 | 0.3919 | 0.1800 | 0.2467 | 0.9574 |
|
| 60 |
+
| 0.1561 | 1.61 | 1500 | 0.1362 | 0.4214 | 0.2081 | 0.2786 | 0.9582 |
|
| 61 |
+
| 0.1538 | 2.15 | 2000 | 0.1436 | 0.3513 | 0.2747 | 0.3083 | 0.9529 |
|
| 62 |
+
| 0.1327 | 2.68 | 2500 | 0.1453 | 0.3424 | 0.2984 | 0.3189 | 0.9510 |
|
| 63 |
+
| 0.1218 | 3.22 | 3000 | 0.1467 | 0.3726 | 0.2862 | 0.3237 | 0.9540 |
|
| 64 |
+
| 0.1068 | 3.76 | 3500 | 0.1583 | 0.3466 | 0.3004 | 0.3218 | 0.9513 |
|
| 65 |
+
| 0.0978 | 4.29 | 4000 | 0.1658 | 0.3413 | 0.3021 | 0.3205 | 0.9505 |
|
| 66 |
+
| 0.0891 | 4.83 | 4500 | 0.1647 | 0.3544 | 0.2986 | 0.3241 | 0.9519 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.31.0
|
| 72 |
+
- Pytorch 2.0.1+cu118
|
| 73 |
+
- Datasets 2.14.4
|
| 74 |
+
- Tokenizers 0.13.3
|