update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: t5-base-pt-asqa-cb
|
| 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 |
+
# t5-base-pt-asqa-cb
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [din0s/t5-base-msmarco-nlgen-cb](https://huggingface.co/din0s/t5-base-msmarco-nlgen-cb) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.7735
|
| 18 |
+
- Rougelsum: 26.3056
|
| 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: 1e-05
|
| 38 |
+
- train_batch_size: 16
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 20
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Rougelsum |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 50 |
+
| No log | 1.0 | 273 | 2.9031 | 24.6325 |
|
| 51 |
+
| 3.2031 | 2.0 | 546 | 2.8656 | 24.9190 |
|
| 52 |
+
| 3.2031 | 3.0 | 819 | 2.8442 | 25.1197 |
|
| 53 |
+
| 3.0839 | 4.0 | 1092 | 2.8303 | 25.2855 |
|
| 54 |
+
| 3.0839 | 5.0 | 1365 | 2.8189 | 25.4891 |
|
| 55 |
+
| 3.0276 | 6.0 | 1638 | 2.8099 | 25.6116 |
|
| 56 |
+
| 3.0276 | 7.0 | 1911 | 2.8036 | 25.7411 |
|
| 57 |
+
| 3.0043 | 8.0 | 2184 | 2.7976 | 25.8238 |
|
| 58 |
+
| 3.0043 | 9.0 | 2457 | 2.7930 | 25.9201 |
|
| 59 |
+
| 2.9791 | 10.0 | 2730 | 2.7890 | 26.0322 |
|
| 60 |
+
| 2.9545 | 11.0 | 3003 | 2.7851 | 26.0934 |
|
| 61 |
+
| 2.9545 | 12.0 | 3276 | 2.7826 | 26.1574 |
|
| 62 |
+
| 2.9344 | 13.0 | 3549 | 2.7802 | 26.2041 |
|
| 63 |
+
| 2.9344 | 14.0 | 3822 | 2.7785 | 26.2330 |
|
| 64 |
+
| 2.9252 | 15.0 | 4095 | 2.7769 | 26.2394 |
|
| 65 |
+
| 2.9252 | 16.0 | 4368 | 2.7756 | 26.2676 |
|
| 66 |
+
| 2.9109 | 17.0 | 4641 | 2.7747 | 26.2864 |
|
| 67 |
+
| 2.9109 | 18.0 | 4914 | 2.7740 | 26.3146 |
|
| 68 |
+
| 2.9103 | 19.0 | 5187 | 2.7736 | 26.2993 |
|
| 69 |
+
| 2.9103 | 20.0 | 5460 | 2.7735 | 26.3056 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.23.0.dev0
|
| 75 |
+
- Pytorch 1.12.1+cu102
|
| 76 |
+
- Datasets 2.4.0
|
| 77 |
+
- Tokenizers 0.12.1
|