Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
tinyllama-1.1b-mt-sft-qlora – AI Model by martimfasantos | AlphaNeural AI
You can deploy this model and start earning money today!
martimfasantos
/
tinyllama-1.1b-mt-sft-qlora
like
0
peft
tensorboard
safetensors
llama
alignment-handbook
trl
sft
generated_from_trainer
haoranxu/ALMA-Human-Parallel
TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
adapter
apache-2.0
4-bit
bitsandbytes
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
tinyllama-1.1b-mt-sft-qlora
This model is a fine-tuned version of
TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
on the haoranxu/ALMA-Human-Parallel dataset. It achieves the following results on the evaluation set:
Loss: 1.7228
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: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2
Training results
Training Loss
Epoch
Step
Validation Loss
1.639
1.0
739
1.7224
1.571
2.0
1478
1.7228
Framework versions
PEFT 0.7.1
Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2
