dball
/

zephyr-7b-dpo-qlora-no-sft

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions

Metrics Training metrics Community

zephyr-7b-dpo-qlora-no-sft

Ctrl+K

Ctrl+K

1 contributor

History: 75 commits

leaderboard-pr-bot's picture

leaderboard-pr-bot

Adding Evaluation Results

10a5c4c verified over 1 year ago

runs
Model save over 1 year ago
.gitattributes

1.52 kB

initial commit over 1 year ago
README.md

17.3 kB

Adding Evaluation Results over 1 year ago
adapter_config.json

655 Bytes

Training in progress, step 200 over 1 year ago
adapter_model.safetensors

83.9 MB
xet

Model save over 1 year ago
all_results.json

745 Bytes

Model save over 1 year ago
config.json

1.03 kB

End of training over 1 year ago
eval_results.json

569 Bytes

Model save over 1 year ago
special_tokens_map.json

437 Bytes

Training in progress, step 200 over 1 year ago
tokenizer.json

1.8 MB

Training in progress, step 200 over 1 year ago
tokenizer.model

493 kB
xet

Training in progress, step 200 over 1 year ago
tokenizer_config.json

942 Bytes

Training in progress, step 200 over 1 year ago
train_results.json

196 Bytes

Model save over 1 year ago
trainer_state.json

412 kB

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

Training in progress, step 200 over 1 year ago