Commit
•
960a4f3
1
Parent(s):
1f0f4df
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: aubmindlab/bert-base-arabert
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: QA_FineTuned_Arabertr
|
| 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 |
+
# QA_FineTuned_Arabertr
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabert](https://huggingface.co/aubmindlab/bert-base-arabert) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.8357
|
| 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: 0.0002
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 16
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 43 |
+
- num_epochs: 3
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 5.518 | 0.13 | 10 | 4.3573 |
|
| 50 |
+
| 4.254 | 0.27 | 20 | 3.8054 |
|
| 51 |
+
| 3.9915 | 0.4 | 30 | 3.5788 |
|
| 52 |
+
| 3.836 | 0.53 | 40 | 3.4054 |
|
| 53 |
+
| 3.6733 | 0.67 | 50 | 3.2506 |
|
| 54 |
+
| 3.4425 | 0.8 | 60 | 3.0882 |
|
| 55 |
+
| 3.2917 | 0.93 | 70 | 2.9934 |
|
| 56 |
+
| 2.9622 | 1.07 | 80 | 3.0029 |
|
| 57 |
+
| 2.3228 | 1.2 | 90 | 3.1190 |
|
| 58 |
+
| 2.4004 | 1.33 | 100 | 2.8613 |
|
| 59 |
+
| 2.3946 | 1.47 | 110 | 2.8983 |
|
| 60 |
+
| 2.3108 | 1.6 | 120 | 2.7711 |
|
| 61 |
+
| 2.3778 | 1.73 | 130 | 2.7062 |
|
| 62 |
+
| 2.3335 | 1.87 | 140 | 2.9916 |
|
| 63 |
+
| 2.4273 | 2.0 | 150 | 2.6713 |
|
| 64 |
+
| 1.4165 | 2.13 | 160 | 2.8003 |
|
| 65 |
+
| 1.1488 | 2.27 | 170 | 2.7959 |
|
| 66 |
+
| 1.2044 | 2.4 | 180 | 3.1311 |
|
| 67 |
+
| 1.2715 | 2.53 | 190 | 2.8319 |
|
| 68 |
+
| 1.1309 | 2.67 | 200 | 2.8048 |
|
| 69 |
+
| 1.3421 | 2.8 | 210 | 2.8158 |
|
| 70 |
+
| 0.9567 | 2.93 | 220 | 2.8357 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.39.3
|
| 76 |
+
- Pytorch 2.1.2
|
| 77 |
+
- Datasets 2.18.0
|
| 78 |
+
- 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 538440512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6436db227a689989f8ee0364da0adb35c215058b3d1d6d05d12cc827fe6f33a
|
| 3 |
size 538440512
|
runs/May13_06-54-17_32317d237a8a/events.out.tfevents.1715583267.32317d237a8a.34.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ce22569b010a1555f63f1f793559adcbbc4fa0a1009854e236eba41e054e606
|
| 3 |
+
size 15631
|