riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 10:12:23 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

[Flax] Small fixes in run_flax_glue.py (#11820)

Browse Source 
* fix_torch_device_generate_test

* remove @

* correct best seed for flax fine-tuning

Co-authored-by: Patrick von Platen <patrick@huggingface.co>
This commit is contained in:
Patrick von Platen 2021-05-21 16:52:23 +01:00 committed by GitHub
parent b8697bc622
commit 82335185fe
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/flax/text-classification/README.md
View File

@ -59,7 +59,7 @@ On the task other than MRPC and WNLI we train for 3 these epochs because this is
but looking at the training curves of some of them (e.g., SST-2, STS-b), it appears the models
are undertrained and we could get better results when training longer.
In the Tensorboard results linked below, the random seed of each model is equal to the ID of the run. So in order to reproduce run 1, run the command above with `--seed=1`. The best run used random seed 2, which is the default in the script. The results of all runs are in [this Google Sheet](https://docs.google.com/spreadsheets/d/1p3XzReMO75m_XdEJvPue-PIq_PN-96J2IJpJW1yS-10/edit?usp=sharing).
In the Tensorboard results linked below, the random seed of each model is equal to the ID of the run. So in order to reproduce run 1, run the command above with `--seed=1`. The best run used random seed 3, which is the default in the script. The results of all runs are in [this Google Sheet](https://docs.google.com/spreadsheets/d/1p3XzReMO75m_XdEJvPue-PIq_PN-96J2IJpJW1yS-10/edit?usp=sharing).
| Task | Metric | Acc (best run) | Acc (avg/5runs) | Stdev | Metrics |
|-------|------------------------------|----------------|-----------------|-----------|--------------------------------------------------------------------------|

2
examples/flax/text-classification/run_flax_glue.py
View File

@ -123,7 +123,7 @@ def parse_args():
"--num_warmup_steps", type=int, default=0, help="Number of steps for the warmup in the lr scheduler."
)
parser.add_argument("--output_dir", type=str, default=None, help="Where to store the final model.")
parser.add_argument("--seed", type=int, default=5, help="A seed for reproducible training.")
parser.add_argument("--seed", type=int, default=3, help="A seed for reproducible training.")
args = parser.parse_args()
# Sanity checks