Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
AdversarialRLHF
/
ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_propprefix
like
0
Follow
Adversarial Goodhart RLHF
3
Safetensors
gpt_neox
Model card
Files
Files and versions
xet
Community
main
ppo_pythia410m_tldr6.9b_rm410mdata_mergedsft_propprefix
32.4 GB
1 contributor
History:
10 commits
Muqeeth
Training in progress, step 256
bd2f220
verified
5 months ago
checkpoint-104
Training in progress, step 104, checkpoint
5 months ago
checkpoint-156
Training in progress, step 156, checkpoint
5 months ago
checkpoint-208
Training in progress, step 208, checkpoint
5 months ago
checkpoint-52
Training in progress, step 52, checkpoint
5 months ago
.gitattributes
Safe
1.52 kB
initial commit
5 months ago
config.json
Safe
758 Bytes
Training in progress, step 52
5 months ago
model.safetensors
1.62 GB
xet
Training in progress, step 256
5 months ago
special_tokens_map.json
Safe
585 Bytes
Training in progress, step 52
5 months ago
tokenizer.json
Safe
3.56 MB
Training in progress, step 52
5 months ago
tokenizer_config.json
Safe
5.01 kB
Training in progress, step 52
5 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"accelerate.state.PartialState"
,
"trl.trainer.ppo_config.PPOConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"torch.device"
,
"transformers.training_args.OptimizerNames"
How to fix it?
6.58 kB
xet
Training in progress, step 52
5 months ago