sjrhuschlee
commited on
Commit
•
01a7127
1
Parent(s):
05c4045
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
license: cc-by-4.0
|
|
|
4 |
tags:
|
5 |
- flan
|
6 |
- flan-t5
|
@@ -24,7 +25,16 @@ This is the [flan-t5-xl](https://huggingface.co/google/flan-t5-xl) model, fine-t
|
|
24 |
## Hyperparameters
|
25 |
|
26 |
```
|
27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
```
|
29 |
|
30 |
## Usage
|
@@ -55,6 +65,9 @@ model = AutoModelForQuestionAnswering.from_pretrained(model_name)
|
|
55 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
56 |
```
|
57 |
|
|
|
|
|
|
|
58 |
|
59 |
## About us
|
60 |
<div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
|
|
|
1 |
---
|
2 |
language: en
|
3 |
license: cc-by-4.0
|
4 |
+
base_model: google/flan-t5-xl
|
5 |
tags:
|
6 |
- flan
|
7 |
- flan-t5
|
|
|
25 |
## Hyperparameters
|
26 |
|
27 |
```
|
28 |
+
learning_rate: 1e-05
|
29 |
+
train_batch_size: 4
|
30 |
+
eval_batch_size: 8
|
31 |
+
seed: 42
|
32 |
+
gradient_accumulation_steps: 16
|
33 |
+
total_train_batch_size: 64
|
34 |
+
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
35 |
+
lr_scheduler_type: linear
|
36 |
+
lr_scheduler_warmup_ratio: 0.1
|
37 |
+
num_epochs: 4.0
|
38 |
```
|
39 |
|
40 |
## Usage
|
|
|
65 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
66 |
```
|
67 |
|
68 |
+
## Authors
|
69 |
+
Sebastian Husch Lee: sebastian.huschlee [at] deepset.ai
|
70 |
+
|
71 |
|
72 |
## About us
|
73 |
<div class="grid lg:grid-cols-2 gap-x-4 gap-y-3">
|