statking
/

Meta-Llama-3-8B-Instruct-DPO-QLoRA

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

Meta-Llama-3-8B-Instruct-DPO-QLoRA

1 contributor

History: 2 commits

statking's picture

Training in progress, step 100

fdbeed8 verified 4 months ago

.gitattributes

1.52 kB

initial commit 4 months ago
adapter_config.json

741 Bytes

Training in progress, step 100 4 months ago
adapter_model.safetensors

671 MB
LFS

Training in progress, step 100 4 months ago
special_tokens_map.json

509 Bytes

Training in progress, step 100 4 months ago
tokenizer.json

9.09 MB

Training in progress, step 100 4 months ago
tokenizer_config.json

51.2 kB

Training in progress, step 100 4 months ago
training_args.bin
Detected Pickle imports (13)
- "transformers.trainer_utils.HubStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "torch.device",
- "accelerate.state.PartialState",
- "torch.bfloat16",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "alignment.configs.DPOConfig"
How to fix it?
6.46 kB
LFS

Training in progress, step 100 4 months ago