You can deploy this model and start earning money today!

mariamoracrossitcr/
deepseek-llm-7b-base-INBioBHLv1

Name: deepseek-llm-7b-base-INBioBHLv1
Availability: InStock

generated_from_trainer

deepseek-ai/deepseek-llm-7b-base

adapter

other

Views

No views yet

deepseek-llm-7b-base-INBioBHLv1

This model is a fine-tuned version of deepseek-ai/deepseek-llm-7b-base on the INBioBHL dataset. It achieves the following results on the evaluation set:

Loss: 1.4008

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: 0.0001
train_batch_size: 20
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 12
total_train_batch_size: 240
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.7853	0.11	10	3.0280
4.0005	0.21	20	2.6052
2.6913	0.32	30	2.1521
2.0644	0.42	40	1.8928
1.6777	0.53	50	1.8519
1.6805	0.64	60	1.7077
1.286	0.74	70	1.7166
1.7723	0.85	80	1.6710
1.202	0.95	90	1.6233
1.5456	1.06	100	1.6451
1.3491	1.17	110	1.5835
1.2032	1.27	120	1.5820
1.5147	1.38	130	1.5587
0.9582	1.49	140	1.5458
1.627	1.59	150	1.5340
1.0827	1.7	160	1.5179
1.4403	1.8	170	1.5190
1.1859	1.91	180	1.4985
1.0517	2.02	190	1.5016
1.4674	2.12	200	1.4779
0.9293	2.23	210	1.4699
1.5128	2.33	220	1.4743
1.0257	2.44	230	1.4553
1.2647	2.55	240	1.4584
1.1809	2.65	250	1.4442
1.0357	2.76	260	1.4458
1.3411	2.86	270	1.4326
0.8416	2.97	280	1.4317
1.466	3.08	290	1.4271
1.0023	3.18	300	1.4167
1.1226	3.29	310	1.4200
1.1797	3.4	320	1.4075
0.8919	3.5	330	1.4105
1.3799	3.61	340	1.4008
0.8263	3.71	350	1.4014

Framework versions

PEFT 0.9.0
Transformers 4.39.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.6.0
Tokenizers 0.15.2

mariamoracrossitcr/deepseek-llm-7b-base-INBioBHLv1

deepseek-llm-7b-base-INBioBHLv1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mariamoracrossitcr/
deepseek-llm-7b-base-INBioBHLv1