Downloads · 30 days
34
0% of all-time downloads
t5-efficient-large-nl36_fine_tune_sum_V2
Samuel-Fipps/t5-efficient-large-nl36_fine_tune_sum_V2
t5-efficient-large-nl36_fine_tune_sum_V2 is a summarization model from Samuel-Fipps. Use it when you need a shorter version of a longer text. It is set up for transformers. The card lists the license as mit.
NOT SELF REPORTED VALUES FOR THE LEADERBOARD, I HAVE NO CLUE WHY ITS BROKE. CHECK PULL REQUEST
All-time downloads
12.1K
Public
Repo size
13.1 GB
Likes
7
Public
Repo makeup
Click a slice to open those files.
.bin4.4 GB · 100%
At a glance
- Task
- Summarization
- Library
- transformers
- License
- mit
- Model type
- t5
- Access
- Public
- Created
- Sep 21, 2022
- Updated
- Oct 6, 2023
- SHA
- ef7d81f4
Try a prompt
Spaces
Model card
From the Hugging Face model README
NOT SELF REPORTED VALUES FOR THE LEADERBOARD, I HAVE NO CLUE WHY ITS BROKE. CHECK PULL REQUEST
Use summarization without adding summarize to the start of the string.
Trained on Samsum train split.
Parameters for training:
no_decay = ["bias", "LayerNorm.weight", "layer_norm.weight"] optimizer_grouped_parameters = [ { "params": [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)], "weight_decay": 0.0, }, { "params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], "weight_decay": 0.0, }, ]
lr = 0.00005 optimizer = torch.optim.RAdam(optimizer_grouped_parameters, lr=lr)
lr_scheduler = get_scheduler( name="linear", optimizer=optimizer, num_warmup_steps=0, num_training_steps=50005)
This was only for 10K steps with a batch size of 10
If you want more info, feel free to message me or email me at: [email protected]
- Task
- Summarization
- Library
- transformers
- Type
- t5
- License
- mit
- Languages
- en
- Created
- Sep 21, 2022
- Updated
- Oct 6, 2023