update model card README.md
Browse files
README.md
CHANGED
|
@@ -3,14 +3,14 @@ base_model: akhooli/gpt2-small-arabic
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
-
- name:
|
| 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 |
-
#
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [akhooli/gpt2-small-arabic](https://huggingface.co/akhooli/gpt2-small-arabic) on the None dataset.
|
| 16 |
|
|
@@ -32,11 +32,11 @@ More information needed
|
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 0.0005
|
| 35 |
-
- train_batch_size:
|
| 36 |
-
- eval_batch_size:
|
| 37 |
- seed: 42
|
| 38 |
- gradient_accumulation_steps: 8
|
| 39 |
-
- total_train_batch_size:
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: cosine
|
| 42 |
- lr_scheduler_warmup_steps: 1000
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
+
- name: GPT2-arabic-poet
|
| 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 |
+
# GPT2-arabic-poet
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [akhooli/gpt2-small-arabic](https://huggingface.co/akhooli/gpt2-small-arabic) on the None dataset.
|
| 16 |
|
|
|
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 0.0005
|
| 35 |
+
- train_batch_size: 10
|
| 36 |
+
- eval_batch_size: 10
|
| 37 |
- seed: 42
|
| 38 |
- gradient_accumulation_steps: 8
|
| 39 |
+
- total_train_batch_size: 80
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: cosine
|
| 42 |
- lr_scheduler_warmup_steps: 1000
|