Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
erbacher
/
pythia-1.0b-deduped-tldr-online-dpo
like
0
Safetensors
gpt_neox
Model card
Files
Files and versions
Community
main
pythia-1.0b-deduped-tldr-online-dpo
1 contributor
History:
2 commits
erbacher
Training in progress, step 1095
f13b754
verified
about 1 month ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
config.json
Safe
820 Bytes
Training in progress, step 1095
about 1 month ago
model.safetensors
Safe
2.02 GB
LFS
Training in progress, step 1095
about 1 month ago
special_tokens_map.json
Safe
579 Bytes
Training in progress, step 1095
about 1 month ago
tokenizer.json
Safe
3.56 MB
Training in progress, step 1095
about 1 month ago
tokenizer_config.json
Safe
5.33 kB
Training in progress, step 1095
about 1 month ago
training_args.bin
pickle
Detected Pickle imports (13)
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"trl.trainer.online_dpo_config.OnlineDPOConfig"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"torch.device"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"torch.bfloat16"
How to fix it?
6.78 kB
LFS
Training in progress, step 1095
about 1 month ago