You can deploy this model and start earning money today!

7siwek/
llama381binstruct_summarize_short

Name: llama381binstruct_summarize_short
Availability: InStock

generated_from_trainer

generator

NousResearch/Meta-Llama-3.1-8B-Instruct

adapter

llama3.1

Views

No views yet

llama381binstruct_summarize_short

This model is a fine-tuned version of NousResearch/Meta-Llama-3.1-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

Loss: 2.9125

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: 0.0002
train_batch_size: 1
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 30
training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
1.7217	1.3158	25	1.7570
0.6773	2.6316	50	1.7855
0.3713	3.9474	75	1.8944
0.1498	5.2632	100	2.2601
0.0738	6.5789	125	2.3539
0.0395	7.8947	150	2.4572
0.03	9.2105	175	2.4119
0.0179	10.5263	200	2.4960
0.0154	11.8421	225	2.5468
0.0054	13.1579	250	2.6392
0.0041	14.4737	275	2.7146
0.0027	15.7895	300	2.8038
0.003	17.1053	325	2.8446
0.0024	18.4211	350	2.8672
0.0019	19.7368	375	2.8810
0.0021	21.0526	400	2.8946
0.0021	22.3684	425	2.9023
0.0019	23.6842	450	2.9083
0.0018	25.0	475	2.9117
0.0017	26.3158	500	2.9125

Framework versions

PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 3.0.0
Tokenizers 0.19.1

7siwek/llama381binstruct_summarize_short

llama381binstruct_summarize_short

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

7siwek/
llama381binstruct_summarize_short