Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
imelnyk
/
zephyr-7b-dpo-qlora-fsdp
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
e67ff0e
zephyr-7b-dpo-qlora-fsdp
1 contributor
History:
4 commits
imelnyk
Training in progress, step 1000
e67ff0e
verified
10 months ago
runs
Training in progress, step 1000
10 months ago
.gitattributes
Safe
1.52 kB
initial commit
10 months ago
special_tokens_map.json
Safe
551 Bytes
Training in progress, step 600
10 months ago
tokenizer.json
Safe
1.8 MB
Training in progress, step 600
10 months ago
tokenizer_config.json
Safe
1.39 kB
Training in progress, step 600
10 months ago
training_args.bin
pickle
Detected Pickle imports (9)
"transformers.trainer_utils.SchedulerType"
,
"torch.device"
,
"accelerate.utils.dataclasses.DistributedType"
,
"alignment.configs.DPOConfig"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.state.PartialState"
How to fix it?
5.05 kB
LFS
Training in progress, step 600
10 months ago