DUAL-GPO
/

zephyr-7b-ipo-10k-40k-0.001-i1

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-ipo-10k-40k-0.001-i1

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

BraylonDash's picture

Training in progress, step 20

dd307e6 verified 11 months ago

runs
Training in progress, step 20 11 months ago
.gitattributes

1.52 kB

initial commit 11 months ago
adapter_config.json

670 Bytes

Training in progress, step 20 11 months ago
adapter_model.safetensors

671 MB
LFS

Training in progress, step 20 11 months ago
special_tokens_map.json

437 Bytes

Training in progress, step 20 11 months ago
tokenizer.json

1.8 MB

Training in progress, step 20 11 months ago
tokenizer.model

493 kB
LFS

Training in progress, step 20 11 months ago
tokenizer_config.json

1.19 kB

Training in progress, step 20 11 months ago
training_args.bin
Detected Pickle imports (11)
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "torch.device",
- "alignment.configs.DPOConfig",
- "torch.bfloat16"
How to fix it?
5.88 kB
LFS

Training in progress, step 20 11 months ago