Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Prathyusha101
/
reset_value_head
like
0
Transformers
Safetensors
trl-internal-testing/tldr-preference-sft-trl-style
Generated from Trainer
arxiv:
1909.08593
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
355f456
reset_value_head
3.63 MB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
Prathyusha101
Training in progress, step 1250
355f456
verified
9 months ago
policy
Training in progress, step 1250
9 months ago
.gitattributes
Safe
1.52 kB
initial commit
9 months ago
chat_template.jinja
Safe
167 Bytes
Training in progress, step 500
9 months ago
completions.csv
Safe
54.4 kB
Training in progress, step 1250
9 months ago
special_tokens_map.json
Safe
579 Bytes
Training in progress, step 500
9 months ago
tokenizer.json
Safe
3.56 MB
Training in progress, step 500
9 months ago
tokenizer_config.json
Safe
5.07 kB
Training in progress, step 500
9 months ago
training_args.bin
pickle
Detected Pickle imports (12)
"transformers.training_args.OptimizerNames"
,
"torch.device"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.deepspeed.HfDeepSpeedConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"trl.trainer.ppo_config.PPOConfig"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.SaveStrategy"
How to fix it?
7.29 kB
xet
Training in progress, step 500
9 months ago