Commit
โข
364e320
1
Parent(s):
318c5f7
Model save
Browse files- README.md +75 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ZeyadAhmed/AraElectra-Arabic-SQuADv2-QA
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: AraElectra-QA-EgyLaw-Squad
|
| 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 |
+
# AraElectra-QA-EgyLaw-Squad
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [ZeyadAhmed/AraElectra-Arabic-SQuADv2-QA](https://huggingface.co/ZeyadAhmed/AraElectra-Arabic-SQuADv2-QA) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 4.0008
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 3e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 20
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| No log | 1.0 | 89 | 3.2762 |
|
| 49 |
+
| 3.9126 | 2.0 | 178 | 3.0150 |
|
| 50 |
+
| 2.5679 | 3.0 | 267 | 2.8324 |
|
| 51 |
+
| 1.7576 | 4.0 | 356 | 2.9655 |
|
| 52 |
+
| 1.1946 | 5.0 | 445 | 3.1643 |
|
| 53 |
+
| 0.8854 | 6.0 | 534 | 3.0778 |
|
| 54 |
+
| 0.7387 | 7.0 | 623 | 3.2814 |
|
| 55 |
+
| 0.6067 | 8.0 | 712 | 3.2391 |
|
| 56 |
+
| 0.5201 | 9.0 | 801 | 3.3717 |
|
| 57 |
+
| 0.5201 | 10.0 | 890 | 3.5752 |
|
| 58 |
+
| 0.4377 | 11.0 | 979 | 3.6657 |
|
| 59 |
+
| 0.4025 | 12.0 | 1068 | 3.8178 |
|
| 60 |
+
| 0.4077 | 13.0 | 1157 | 3.7404 |
|
| 61 |
+
| 0.3355 | 14.0 | 1246 | 3.7566 |
|
| 62 |
+
| 0.3627 | 15.0 | 1335 | 3.9959 |
|
| 63 |
+
| 0.3376 | 16.0 | 1424 | 3.8815 |
|
| 64 |
+
| 0.3676 | 17.0 | 1513 | 3.9674 |
|
| 65 |
+
| 0.3165 | 18.0 | 1602 | 3.9368 |
|
| 66 |
+
| 0.3165 | 19.0 | 1691 | 3.9836 |
|
| 67 |
+
| 0.3148 | 20.0 | 1780 | 4.0008 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.38.1
|
| 73 |
+
- Pytorch 2.1.2
|
| 74 |
+
- Datasets 2.1.0
|
| 75 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 538441104
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:685eff6cff63e3b5fc6fba652d5b3a292b61358c89afc8d50e09660d5811e243
|
| 3 |
size 538441104
|