Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
zephyr-34b-sft-full_epoch1 – AI Model by dlibf | AlphaNeural AI
You can deploy this model and start earning money today!
dlibf
/
zephyr-34b-sft-full_epoch1
like
0
transformers
tensorboard
safetensors
llama
text-generation
trl
sft
generated_from_trainer
conversational
generator
01-ai/Yi-34B-200K
finetune
other
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
zephyr-34b-sft-full_epoch1
This model is a fine-tuned version of
01-ai/Yi-34B-200K
on the generator dataset. It achieves the following results on the evaluation set:
Loss: 0.9533
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: 2e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
0.9435
1.0
1026
0.9533
Framework versions
Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.15.1
