DUAL-GPO
/

zephyr-7b-gpo-iter1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-gpo-iter1

1 contributor

History: 11 commits

lole25's picture

Training in progress, step 1000

71cdc77 verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
adapter_config.json

657 Bytes

Training in progress, step 100 3 months ago
adapter_model.safetensors
671 MB
LFS

Training in progress, step 1000 3 months ago
special_tokens_map.json

551 Bytes

Training in progress, step 100 3 months ago
tokenizer.json

1.8 MB

Training in progress, step 100 3 months ago
tokenizer_config.json

1.39 kB

Training in progress, step 100 3 months ago
training_args.bin
Detected Pickle imports (11)
- "torch.device",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "alignment.configs.DPOConfig",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.training_args.OptimizerNames",
- "torch.bfloat16"
How to fix it?
5.82 kB
LFS

Training in progress, step 100 3 months ago