cyberpole
/

Meta-Llama-3.1-8B-Instruct-mergedORPO

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Meta-Llama-3.1-8B-Instruct-mergedORPO

1 contributor

History: 127 commits

k-r-l's picture

Training in progress, step 63

5d5b06b verified 3 months ago

last-checkpoint
Training in progress, step 62, checkpoint 3 months ago
runs
Training in progress, step 63 3 months ago
.gitattributes

1.52 kB

initial commit 3 months ago
README.md

1.27 kB

Model save 3 months ago
adapter_config.json

661 Bytes

Training in progress, step 63 3 months ago
adapter_model.safetensors

13.6 MB
LFS

Training in progress, step 63 3 months ago
special_tokens_map.json

325 Bytes

Training in progress, step 1 3 months ago
tokenizer.json

9.09 MB

Training in progress, step 1 3 months ago
tokenizer_config.json

55.4 kB

Training in progress, step 1 3 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "trl.trainer.orpo_config.ORPOConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames"
How to fix it?
5.56 kB
LFS

Training in progress, step 63 3 months ago