Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Hand_off_DS_Llama8B_100steps_1e6rate_SFT – AI Model by tsavage68 | AlphaNeural AI
You can deploy this model and start earning money today!
tsavage68
/
Hand_off_DS_Llama8B_100steps_1e6rate_SFT
like
0
transformers
safetensors
llama
text-generation
trl
sft
generated_from_trainer
conversational
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
finetune
mit
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Hand_off_DS_Llama8B_100steps_1e6rate_SFT
This model is a fine-tuned version of
deepseek-ai/DeepSeek-R1-Distill-Llama-8B
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.7178
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: 1e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Use adafactor and the args are: No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 100
Training results
Training Loss
Epoch
Step
Validation Loss
2.6767
0.0464
50
2.4451
0.7309
0.0929
100
0.7178
Framework versions
Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.3.1
Tokenizers 0.21.0
