TED_CLM_gpt2_tedlium4 – AI Model by Lakoc | AlphaNeural AI

You can deploy this model and start earning money today!

Lakoc/
TED_CLM_gpt2_tedlium4

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

TED_CLM_gpt2_tedlium4

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

Loss: 1.9157
Accuracy: 0.5497

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: 0.005
train_batch_size: 128
eval_batch_size: 128
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 512
total_eval_batch_size: 512
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20000
num_epochs: 15.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1599	0.32	3000	2.3060	0.4711
2.0452	0.65	6000	2.1564	0.5013
1.9981	0.97	9000	2.0995	0.5142
1.9806	1.3	12000	2.0596	0.5168
1.9459	1.62	15000	2.0307	0.5235
1.9205	1.95	18000	2.0189	0.5279
1.9039	2.27	21000	2.0024	0.5313
1.9033	2.6	24000	1.9890	0.5337
1.8621	2.92	27000	1.9509	0.5401
1.8252	3.25	30000	1.9420	0.5439
1.813	3.57	33000	1.9208	0.5493
1.8085	3.9	36000	1.9157	0.5497
1.7984	4.22	39000	1.9157	0.5497
1.8008	4.55	42000	1.9157	0.5497
1.7967	4.87	45000	1.9157	0.5497
1.7972	5.2	48000	1.9157	0.5497
1.7967	5.52	51000	1.9157	0.5497

Framework versions

Transformers 4.31.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.13.1
Tokenizers 0.13.3