RedaAlami
/

zephyr-7b-dpo-qlora

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-qlora

1 contributor

History: 9 commits

RedaAlami's picture

Training in progress, step 100

01aecfc verified 3 months ago

runs
Training in progress, step 100 3 months ago
.gitattributes

1.52 kB

initial commit 5 months ago
README.md

1.32 kB

Model save 4 months ago
adapter_config.json

742 Bytes

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

646 MB
LFS

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

232 Bytes

Model save 4 months ago
special_tokens_map.json

977 Bytes

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

9.78 MB

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

363 kB

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

232 Bytes

Model save 4 months ago
trainer_state.json

3.05 kB

Model save 4 months ago
training_args.bin
Detected Pickle imports (10)
- "trl.trainer.dpo_config.FDivergenceType",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames",
- "alignment.configs.DPOConfig"
How to fix it?
6.14 kB
LFS

Training in progress, step 100 3 months ago