yiran-wang3
/

ds_chat_sppo_hard_new_iter0_constant_1e-6

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

ds_chat_sppo_hard_new_iter0_constant_1e-6

1 contributor

History: 2 commits

yiran-wang3's picture

Training in progress, epoch 1

773aca0 verified 18 days ago

.gitattributes

1.52 kB

initial commit 18 days ago
config.json

726 Bytes

Training in progress, epoch 1 18 days ago
special_tokens_map.json

482 Bytes

Training in progress, epoch 1 18 days ago
tokenizer.json

4.61 MB

Training in progress, epoch 1 18 days ago
tokenizer_config.json

3.54 kB

Training in progress, epoch 1 18 days ago
training_args.bin
Detected Pickle imports (15)
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "__builtin__.getattr",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DistributedType",
- "trl.trainer.dpo_config.FDivergenceType",
- "torch.device",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.HubStrategy",
- "alignment.configs.DPOConfig",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "accelerate.state.PartialState"
How to fix it?
7.61 kB
LFS

Training in progress, epoch 1 18 days ago