ctrlsum-led-base-cnndm

alshelt/ctrlsum-led-base-cnndm

ctrlsum-led-base-cnndm is a machine learning model from alshelt. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

7% of all-time downloads

All-time downloads

173

Public

Parameters

162M

316 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors648 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: led
Access: Public
Created: Apr 25, 2024
Updated: May 28, 2024
SHA: c5db38c7

Base models

allenai/led-base-16384

Model card

From the Hugging Face model README

hf

This model is a fine-tuned version of allenai/led-base-16384 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2202

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: polynomial
lr_scheduler_warmup_steps: 500
training_steps: 20000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.255	0.0	500	0.2798
0.211	0.01	1000	0.2655
0.2399	0.01	1500	0.2625
0.2183	0.01	2000	0.2533
0.2375	0.02	2500	0.2501
0.2452	0.02	3000	0.2477
0.2636	0.02	3500	0.2474
0.2289	0.03	4000	0.2476
0.2453	0.03	4500	0.2443
0.2081	0.03	5000	0.2441
0.1655	0.04	5500	0.2422
0.2765	0.04	6000	0.2386
0.2797	0.05	6500	0.2398
0.1902	0.05	7000	0.2393
0.1875	0.05	7500	0.2363
0.2048	0.06	8000	0.2371
0.1695	0.06	8500	0.2341
0.2121	0.06	9000	0.2348
0.2402	0.07	9500	0.2331
0.1865	0.07	10000	0.2324
0.1862	0.07	10500	0.2329
0.2382	0.08	11000	0.2323
0.2703	0.08	11500	0.2300
0.2303	0.08	12000	0.2297
0.2258	0.09	12500	0.2287
0.1924	0.09	13000	0.2271
0.1849	0.09	13500	0.2269
0.2288	0.1	14000	0.2257
0.2461	0.1	14500	0.2259
0.2509	0.1	15000	0.2241
0.2087	0.11	15500	0.2245
0.1707	0.11	16000	0.2243
0.2053	0.11	16500	0.2238
0.2157	0.12	17000	0.2225
0.1976	0.12	17500	0.2218
0.2626	0.13	18000	0.2213
0.2032	0.13	18500	0.2209
0.2928	0.13	19000	0.2207
0.2438	0.14	19500	0.2205
0.2028	0.14	20000	0.2202

Framework versions

Transformers 4.37.2
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.15.1

Library: transformers
Type: led
License: apache-2.0
Created: Apr 25, 2024
Updated: May 28, 2024