update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,9 +1,73 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
-
###
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/flan-t5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: peft-finetune-flan-t5-mc-question-generation
|
| 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 |
+
# peft-finetune-flan-t5-mc-question-generation
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.2240
|
| 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: 5e-05
|
| 38 |
+
- train_batch_size: 2
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 16
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 2
|
| 46 |
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.3143 | 0.13 | 100 | 1.7677 |
|
| 52 |
+
| 1.8538 | 0.25 | 200 | 1.4179 |
|
| 53 |
+
| 1.5767 | 0.38 | 300 | 1.3186 |
|
| 54 |
+
| 1.4908 | 0.51 | 400 | 1.2879 |
|
| 55 |
+
| 1.4503 | 0.64 | 500 | 1.2700 |
|
| 56 |
+
| 1.4281 | 0.76 | 600 | 1.2578 |
|
| 57 |
+
| 1.406 | 0.89 | 700 | 1.2489 |
|
| 58 |
+
| 1.4052 | 1.02 | 800 | 1.2415 |
|
| 59 |
+
| 1.3974 | 1.15 | 900 | 1.2387 |
|
| 60 |
+
| 1.3889 | 1.27 | 1000 | 1.2334 |
|
| 61 |
+
| 1.3811 | 1.4 | 1100 | 1.2303 |
|
| 62 |
+
| 1.3808 | 1.53 | 1200 | 1.2266 |
|
| 63 |
+
| 1.3782 | 1.65 | 1300 | 1.2265 |
|
| 64 |
+
| 1.376 | 1.78 | 1400 | 1.2248 |
|
| 65 |
+
| 1.3734 | 1.91 | 1500 | 1.2240 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
|
| 70 |
+
- Transformers 4.31.0
|
| 71 |
+
- Pytorch 2.0.0
|
| 72 |
+
- Datasets 2.1.0
|
| 73 |
+
- Tokenizers 0.13.3
|