Model save
Browse files- README.md +75 -0
- generation_config.json +7 -0
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/mt5-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mt5-base-bcoqa
|
| 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 |
+
# mt5-base-bcoqa
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.0503
|
| 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: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 2
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| 1.7933 | 0.1 | 3500 | 1.4891 |
|
| 50 |
+
| 1.594 | 0.2 | 7000 | 1.3193 |
|
| 51 |
+
| 1.4983 | 0.3 | 10500 | 1.2550 |
|
| 52 |
+
| 1.4311 | 0.4 | 14000 | 1.2163 |
|
| 53 |
+
| 1.4343 | 0.5 | 17500 | 1.1723 |
|
| 54 |
+
| 1.3635 | 0.61 | 21000 | 1.1518 |
|
| 55 |
+
| 1.3782 | 0.71 | 24500 | 1.1331 |
|
| 56 |
+
| 1.3782 | 0.81 | 28000 | 1.1126 |
|
| 57 |
+
| 1.3091 | 0.91 | 31500 | 1.1197 |
|
| 58 |
+
| 1.2328 | 1.01 | 35000 | 1.0967 |
|
| 59 |
+
| 1.2605 | 1.11 | 38500 | 1.0892 |
|
| 60 |
+
| 1.183 | 1.21 | 42000 | 1.0872 |
|
| 61 |
+
| 1.1713 | 1.31 | 45500 | 1.0963 |
|
| 62 |
+
| 1.2369 | 1.41 | 49000 | 1.0696 |
|
| 63 |
+
| 1.2542 | 1.51 | 52500 | 1.0672 |
|
| 64 |
+
| 1.2226 | 1.61 | 56000 | 1.0608 |
|
| 65 |
+
| 1.2013 | 1.72 | 59500 | 1.0538 |
|
| 66 |
+
| 1.1776 | 1.82 | 63000 | 1.0516 |
|
| 67 |
+
| 1.191 | 1.92 | 66500 | 1.0503 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.39.0.dev0
|
| 73 |
+
- Pytorch 2.2.1+cu121
|
| 74 |
+
- Datasets 2.16.1
|
| 75 |
+
- Tokenizers 0.15.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.39.0.dev0"
|
| 7 |
+
}
|