Commit
•
fcf527d
1
Parent(s):
98fa242
Model save
Browse files- README.md +73 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: riotu-lab/ArabianGPT-03B
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: model_outputs
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# model_outputs
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [riotu-lab/ArabianGPT-03B](https://huggingface.co/riotu-lab/ArabianGPT-03B) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 5.9804
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0003
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- num_epochs: 4
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 6.1892 | 0.26 | 10 | 4.8197 |
|
| 52 |
+
| 4.7341 | 0.51 | 20 | 4.1928 |
|
| 53 |
+
| 4.1782 | 0.77 | 30 | 4.0742 |
|
| 54 |
+
| 4.1255 | 1.03 | 40 | 4.0078 |
|
| 55 |
+
| 3.3704 | 1.28 | 50 | 4.1840 |
|
| 56 |
+
| 3.4364 | 1.54 | 60 | 4.4455 |
|
| 57 |
+
| 3.3383 | 1.79 | 70 | 4.3615 |
|
| 58 |
+
| 3.1346 | 2.05 | 80 | 4.3538 |
|
| 59 |
+
| 2.451 | 2.31 | 90 | 5.5225 |
|
| 60 |
+
| 2.456 | 2.56 | 100 | 5.2477 |
|
| 61 |
+
| 2.3692 | 2.82 | 110 | 5.0649 |
|
| 62 |
+
| 2.2492 | 3.08 | 120 | 5.3660 |
|
| 63 |
+
| 1.8112 | 3.33 | 130 | 5.8835 |
|
| 64 |
+
| 1.8044 | 3.59 | 140 | 5.9958 |
|
| 65 |
+
| 1.8347 | 3.85 | 150 | 5.9804 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.39.3
|
| 71 |
+
- Pytorch 2.1.2
|
| 72 |
+
- Datasets 2.18.0
|
| 73 |
+
- 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 1475630744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:595e3fadff69572cd1977c0f59c9c7d932e0b1473a6f802e16afd6fbecaa5e54
|
| 3 |
size 1475630744
|