Chaido Porlou
commited on
Commit
•
89631e0
1
Parent(s):
be46b02
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- squad_modified_for_t5_qg_2
|
| 7 |
+
model-index:
|
| 8 |
+
- name: greek-nllb-4ep-512
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# greek-nllb-4ep-512
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the squad_modified_for_t5_qg_2 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.2852
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 16
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 4
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 2.2208 | 0.17 | 100 | 1.5566 |
|
| 53 |
+
| 1.7198 | 0.34 | 200 | 1.4767 |
|
| 54 |
+
| 1.5435 | 0.51 | 300 | 1.4467 |
|
| 55 |
+
| 1.5017 | 0.67 | 400 | 1.3955 |
|
| 56 |
+
| 1.4569 | 0.84 | 500 | 1.3711 |
|
| 57 |
+
| 1.4496 | 1.01 | 600 | 1.3556 |
|
| 58 |
+
| 1.3174 | 1.18 | 700 | 1.3488 |
|
| 59 |
+
| 1.3025 | 1.35 | 800 | 1.3398 |
|
| 60 |
+
| 1.3013 | 1.52 | 900 | 1.3286 |
|
| 61 |
+
| 1.2938 | 1.69 | 1000 | 1.3161 |
|
| 62 |
+
| 1.2984 | 1.86 | 1100 | 1.3057 |
|
| 63 |
+
| 1.2494 | 2.03 | 1200 | 1.3097 |
|
| 64 |
+
| 1.1843 | 2.2 | 1300 | 1.2985 |
|
| 65 |
+
| 1.1868 | 2.36 | 1400 | 1.3021 |
|
| 66 |
+
| 1.1875 | 2.53 | 1500 | 1.2958 |
|
| 67 |
+
| 1.1854 | 2.7 | 1600 | 1.2987 |
|
| 68 |
+
| 1.1818 | 2.87 | 1700 | 1.2885 |
|
| 69 |
+
| 1.1696 | 3.04 | 1800 | 1.2912 |
|
| 70 |
+
| 1.1108 | 3.21 | 1900 | 1.2880 |
|
| 71 |
+
| 1.1301 | 3.38 | 2000 | 1.2889 |
|
| 72 |
+
| 1.1139 | 3.55 | 2100 | 1.2869 |
|
| 73 |
+
| 1.1098 | 3.72 | 2200 | 1.2879 |
|
| 74 |
+
| 1.1073 | 3.88 | 2300 | 1.2852 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.27.0.dev0
|
| 80 |
+
- Pytorch 1.13.1+cu116
|
| 81 |
+
- Datasets 2.10.1
|
| 82 |
+
- Tokenizers 0.13.2
|