Commit
•
2030dda
1
Parent(s):
a4228fd
Update README.md
Browse files
README.md
CHANGED
@@ -102,7 +102,7 @@ The following table summarizes the results for [fnet-base](https://huggingface.c
|
|
102 |
|
103 |
On average the PyTorch version of FNet-base requires *ca.* 32% less time for GLUE fine-tuning on GPU.
|
104 |
|
105 |
-
The following table summarizes the results for [fnet-base](https://huggingface.co/google/fnet-base) (called *FNet (PyTorch) - Reproduced*) and [bert-base-cased](https://hf.co/models/bert-base-cased) (called *Bert (PyTorch) - Reproduced*) in terms of performance and compares it to the reported performance of the official FNet-base model (called *FNet (Flax) - Official*).
|
106 |
|
107 |
| Task/Model | Metric | FNet-base (PyTorch) | Bert-base (PyTorch) | FNet-Base (Flax - official) |
|
108 |
|:----:|:-----------:|:----:|:-----------:|:----:|
|
|
|
102 |
|
103 |
On average the PyTorch version of FNet-base requires *ca.* 32% less time for GLUE fine-tuning on GPU.
|
104 |
|
105 |
+
The following table summarizes the results for [fnet-base](https://huggingface.co/google/fnet-base) (called *FNet (PyTorch) - Reproduced*) and [bert-base-cased](https://hf.co/models/bert-base-cased) (called *Bert (PyTorch) - Reproduced*) in terms of performance and compares it to the reported performance of the official FNet-base model (called *FNet (Flax) - Official*). Note that the training hyperparameters of the reproduced models were not the same as the official model, so the performance may differ significantly for some tasks (for example: CoLA).
|
106 |
|
107 |
| Task/Model | Metric | FNet-base (PyTorch) | Bert-base (PyTorch) | FNet-Base (Flax - official) |
|
108 |
|:----:|:-----------:|:----:|:-----------:|:----:|
|