TARARARAK
/

HGU_rulebook-Llama3.2-Bllossom-5B_fine-tuning-QLoRA-32_128_2

Generated from Trainer

Model card Files Files and versions Community

HGU_rulebook-Llama3.2-Bllossom-5B_fine-tuning-QLoRA-32_128_2

Ctrl+K

Ctrl+K

1 contributor

History: 23 commits

TARARARAK's picture

Best model with eval_loss: 0.6642413139343262

8dd9d04 verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

2.69 kB

Best model with eval_loss: 0.6642413139343262 3 months ago
adapter_config.json

668 Bytes

Training in progress, step 31 3 months ago
adapter_model.safetensors

72.1 MB
LFS

Best model with eval_loss: 0.6642413139343262 3 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.TrainingArguments",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy"
How to fix it?
4.99 kB
LFS

Training in progress, step 31 3 months ago