dball
/

zephyr-7b-sft-qlora

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-sft-qlora

1 contributor

History: 146 commits

dball's picture

Manually fix minor details in README.md

ffcebba verified about 1 year ago

runs
Model save about 1 year ago
.gitattributes

1.52 kB

initial commit about 1 year ago
README.md

2.51 kB

Manually fix minor details in README.md about 1 year ago
adapter_config.json

655 Bytes

Training in progress, step 300 about 1 year ago
adapter_model.safetensors

83.9 MB
LFS

Model save about 1 year ago
all_results.json

360 Bytes

Model save about 1 year ago
config.json

1.03 kB

End of training about 1 year ago
eval_results.json

184 Bytes

Model save about 1 year ago
special_tokens_map.json

437 Bytes

Training in progress, step 100 about 1 year ago
tokenizer.json

1.8 MB

Training in progress, step 100 about 1 year ago
tokenizer.model

493 kB
LFS

Training in progress, step 100 about 1 year ago
tokenizer_config.json

1.39 kB

Training in progress, step 100 about 1 year ago
train_results.json

196 Bytes

Model save about 1 year ago
trainer_state.json

425 kB

Model save about 1 year ago
training_args.bin
Detected Pickle imports (8)
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "alignment.configs.SFTConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState"
How to fix it?
4.79 kB
LFS

Training in progress, step 300 about 1 year ago