Model save

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: riotu-lab/ArabianGPT-01B
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+- rouge
+model-index:
+- name: results_fixed
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results_fixed
+
+This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9809
+- Bleu: 0.3149
+- Rouge1: 0.5865
+- Rouge2: 0.3495
+- Rougel: 0.5486
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 20.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Bleu   | Validation Loss | Rouge1 | Rouge2 | Rougel |
+|:-------------:|:------:|:----:|:------:|:---------------:|:------:|:------:|:------:|
+| 3.9816        | 1.0846 | 500  | 0.2270 | 2.8213          | 0.3851 | 0.1625 | 0.3198 |
+| 3.9816        | 2.0    | 922  | 2.4793 | 0.2481          | 0.4405 | 0.2030 | 0.3844 |
+| 2.6514        | 3.0    | 1383 | 2.2931 | 0.2658          | 0.4828 | 0.2385 | 0.4327 |
+| 2.3308        | 4.0    | 1844 | 2.1801 | 0.2797          | 0.5114 | 0.2679 | 0.4659 |
+| 2.1322        | 5.0    | 2305 | 2.1133 | 0.2886          | 0.5264 | 0.2867 | 0.4852 |
+| 1.9942        | 6.0    | 2766 | 2.0649 | 0.2926          | 0.5417 | 0.2993 | 0.5003 |
+| 1.8884        | 7.0    | 3227 | 2.0354 | 0.2967          | 0.5529 | 0.3108 | 0.5117 |
+| 1.8003        | 8.0    | 3688 | 2.0164 | 0.2973          | 0.5597 | 0.3199 | 0.5204 |
+| 1.7305        | 9.0    | 4149 | 2.0036 | 0.3053          | 0.5660 | 0.3262 | 0.5266 |
+| 1.6672        | 10.0   | 4610 | 1.9933 | 0.3072          | 0.5704 | 0.3319 | 0.5325 |
+| 1.6132        | 11.0   | 5071 | 1.9886 | 0.3093          | 0.5737 | 0.3366 | 0.5363 |
+| 1.5659        | 12.0   | 5532 | 1.9834 | 0.3099          | 0.5777 | 0.3397 | 0.5396 |
+| 1.5659        | 13.0   | 5993 | 1.9819 | 0.3117          | 0.5796 | 0.3423 | 0.5418 |
+| 1.5244        | 14.0   | 6454 | 1.9798 | 0.3126          | 0.5833 | 0.3452 | 0.5451 |
+| 1.4884        | 15.0   | 6915 | 1.9793 | 0.3130          | 0.5832 | 0.3461 | 0.5454 |
+| 1.4594        | 16.0   | 7376 | 1.9800 | 0.3133          | 0.5846 | 0.3469 | 0.5466 |
+| 1.4361        | 17.0   | 7837 | 1.9799 | 0.3151          | 0.5865 | 0.3493 | 0.5485 |
+| 1.4159        | 18.0   | 8298 | 1.9809 | 0.3149          | 0.5865 | 0.3495 | 0.5486 |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 64000,
+  "transformers_version": "4.45.0.dev0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:879a9657de21bd39c427a058cc9eb6d0ab6b29448a75d8cbb49be98cbd0d887b
+oid sha256:eebba2f2ff833170f3124d5c7a39e6a8e26d5c480423329231080b523195e5df
 size 539221632