DUAL-GPO
/

zephyr-7b-gpo-v3-4-i2

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-gpo-v3-4-i2

1 contributor

History: 41 commits

This model has 1 file scanned as suspicious.

lole25's picture

End of training

346051e verified 5 months ago

runs
Model save 5 months ago
.gitattributes

1.52 kB

initial commit 5 months ago
README.md

1.37 kB

End of training 5 months ago
adapter_config.json

657 Bytes

Training in progress, step 500 5 months ago
adapter_model.safetensors

671 MB
LFS

Model save 5 months ago
all_results.json

195 Bytes

Model save 5 months ago
config.json

642 Bytes

End of training 5 months ago
special_tokens_map.json

551 Bytes

Training in progress, step 500 5 months ago
tokenizer.json

1.8 MB

Training in progress, step 500 5 months ago
tokenizer_config.json

1.39 kB

Training in progress, step 500 5 months ago
train_results.json

195 Bytes

Model save 5 months ago
trainer_state.json

253 kB

Model save 5 months ago
training_args.bin
Detected Pickle imports (11)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "torch.bfloat16",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "alignment.configs.DPOConfig"
How to fix it?
5.82 kB
LFS

Training in progress, step 500 5 months ago