yasmineee
/

finetune-t5-base-on-opus100-Ar2En-with-lora

PEFT

Safetensors

Generated from Trainer

Model card Files Files and versions Community

yasmineee commited on Jul 28, 2024

Commit

c9c8172

verified ·

1 Parent(s): cb1efd4

finetune-t5-base-on-opus100-Ar2En-with-lora

Browse files

Files changed (1) hide show

README.md +16 -35

README.md CHANGED Viewed

@@ -14,15 +14,16 @@ model-index:
 <!-- 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. -->
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/FinalProject_/T5/runs/rvi5w1wn)
 # finetune-t5-base-on-opus100-Ar2En-with-lora
 This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3108
-- Bleu: 6.8569
-- Rouge: 0.3022
-- Gen Len: 11.5385
 ## Model description
@@ -47,40 +48,20 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 27
 - mixed_precision_training: Native AMP
 ### Training results
-| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Rouge  | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:-------:|
-| 15.3205       | 1.0   | 700   | 5.2666          | 1.1169 | 0.1132 | 11.1805 |
-| 6.621         | 2.0   | 1400  | 4.6248          | 3.116  | 0.229  | 10.1985 |
-| 5.8348        | 3.0   | 2100  | 3.9764          | 3.5395 | 0.2286 | 10.181  |
-| 5.1873        | 4.0   | 2800  | 3.8395          | 3.7821 | 0.2293 | 10.546  |
-| 4.9175        | 5.0   | 3500  | 3.7278          | 4.3934 | 0.2382 | 10.4825 |
-| 4.7382        | 6.0   | 4200  | 3.6304          | 4.5833 | 0.2454 | 10.5095 |
-| 4.615         | 7.0   | 4900  | 3.5695          | 5.2035 | 0.2618 | 10.9995 |
-| 4.5242        | 8.0   | 5600  | 3.5183          | 5.1712 | 0.2633 | 11.188  |
-| 4.4707        | 9.0   | 6300  | 3.4968          | 5.4002 | 0.2652 | 11.0745 |
-| 4.4178        | 10.0  | 7000  | 3.4632          | 5.697  | 0.2704 | 11.442  |
-| 4.3806        | 11.0  | 7700  | 3.4465          | 5.8389 | 0.278  | 11.3195 |
-| 4.3356        | 12.0  | 8400  | 3.4190          | 5.8889 | 0.2789 | 11.389  |
-| 4.3172        | 13.0  | 9100  | 3.4074          | 6.1714 | 0.2869 | 11.1865 |
-| 4.262         | 14.0  | 9800  | 3.3940          | 6.2538 | 0.291  | 11.2835 |
-| 4.2517        | 15.0  | 10500 | 3.3711          | 6.6821 | 0.2947 | 11.4705 |
-| 4.2225        | 16.0  | 11200 | 3.3631          | 6.6337 | 0.2915 | 11.5375 |
-| 4.2032        | 17.0  | 11900 | 3.3606          | 6.6492 | 0.2954 | 11.3655 |
-| 4.2062        | 18.0  | 12600 | 3.3476          | 6.5354 | 0.2956 | 11.388  |
-| 4.1743        | 19.0  | 13300 | 3.3420          | 6.7065 | 0.2986 | 11.5025 |
-| 4.1636        | 20.0  | 14000 | 3.3332          | 6.7179 | 0.299  | 11.538  |
-| 4.1448        | 21.0  | 14700 | 3.3278          | 6.6867 | 0.298  | 11.502  |
-| 4.1378        | 22.0  | 15400 | 3.3209          | 6.8417 | 0.2993 | 11.5215 |
-| 4.127         | 23.0  | 16100 | 3.3182          | 6.7923 | 0.298  | 11.5035 |
-| 4.1259        | 24.0  | 16800 | 3.3141          | 6.8933 | 0.3033 | 11.5165 |
-| 4.1239        | 25.0  | 17500 | 3.3119          | 6.8698 | 0.3022 | 11.5275 |
-| 4.1299        | 26.0  | 18200 | 3.3108          | 6.8569 | 0.3022 | 11.5385 |
-| 4.1101        | 27.0  | 18900 | 3.3112          | 6.969  | 0.3029 | 11.5485 |
 ### Framework versions

 <!-- 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. -->
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/FinalProject_/T5/runs/vvxagyr8)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/FinalProject_/T5/runs/vvxagyr8)
 # finetune-t5-base-on-opus100-Ar2En-with-lora
 This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 3.7552
+- Bleu: 4.3018
+- Rouge: 0.2386
+- Gen Len: 10.572
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 7
 - mixed_precision_training: Native AMP
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Rouge  | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:-------:|
+| 6.6745        | 1.0   | 700  | 4.6813          | 3.2487 | 0.2249 | 10.726  |
+| 6.1243        | 2.0   | 1400 | 4.0666          | 3.3995 | 0.2273 | 10.0245 |
+| 5.3863        | 3.0   | 2100 | 3.9208          | 3.8728 | 0.2335 | 10.3965 |
+| 5.1275        | 4.0   | 2800 | 3.8485          | 3.9535 | 0.2331 | 10.5655 |
+| 4.975         | 5.0   | 3500 | 3.7971          | 3.9941 | 0.2318 | 10.572  |
+| 4.8991        | 6.0   | 4200 | 3.7639          | 4.0786 | 0.2349 | 10.6005 |
+| 4.857         | 7.0   | 4900 | 3.7552          | 4.3018 | 0.2386 | 10.572  |
 ### Framework versions