You can deploy this model and start earning money today!

contemmcm/
c09a9dd1b7e990470b75d194686baba4

Name: c09a9dd1b7e990470b75d194686baba4
Rating: 2.5 (8 reviews)

generated_from_trainer

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

finetune

mit

text-embeddings-inference

endpoints_compatible

Views

No views yet

c09a9dd1b7e990470b75d194686baba4

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Llama-8B on the nyu-mll/glue [qqp] dataset. It achieves the following results on the evaluation set:

Loss: 2.8762
Data Size: 1.0
Epoch Runtime: 11264.4107
Accuracy: 0.8190
F1 Macro: 0.8046
Rouge1: 0.8190
Rouge2: 0.0
Rougel: 0.8190
Rougelsum: 0.8190

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rougel	Rougelsum
No log	0	0	10.0422	0	113.7865	0.3795	0.3350	0.3797	0.3795	0.3797
10.4949	1	11370	2.5833	0.0078	202.4315	0.6326	0.3910	0.6325	0.6326	0.6324
2.5569	2	22740	2.4649	0.0156	292.7418	0.6603	0.6542	0.6604	0.6603	0.6602
2.476	3	34110	2.2693	0.0312	476.5734	0.7139	0.6949	0.7139	0.7136	0.7139
2.0929	4	45480	2.3753	0.0625	836.7690	0.7185	0.7073	0.7185	0.7185	0.7184
2.0421	5	56850	2.0027	0.125	1520.4541	0.7532	0.7077	0.7530	0.7531	0.7531
1.8042	6	68220	1.9093	0.25	2890.7774	0.7685	0.7344	0.7684	0.7684	0.7684
1.6518	7	79590	1.7930	0.5	5674.9903	0.7882	0.7746	0.7882	0.7882	0.7881
1.4975	8.0	90960	1.6496	1.0	11213.9877	0.8124	0.7989	0.8122	0.8125	0.8123
1.119	9.0	102330	1.6941	1.0	11253.7620	0.8182	0.8069	0.8182	0.8183	0.8181
0.7628	10.0	113700	1.9430	1.0	11269.5810	0.8185	0.8056	0.8184	0.8185	0.8185
0.5733	11.0	125070	2.4031	1.0	11298.2334	0.8184	0.8072	0.8184	0.8186	0.8183
0.3609	12.0	136440	2.8762	1.0	11264.4107	0.8190	0.8046	0.8190	0.8190	0.8190

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.22.1

contemmcm/c09a9dd1b7e990470b75d194686baba4

c09a9dd1b7e990470b75d194686baba4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
c09a9dd1b7e990470b75d194686baba4