QinLiuNLP
/

llama3-sudo-dpo-10epochs-forget10mix400-1sft-2fullpara-1e-5

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

llama3-sudo-dpo-10epochs-forget10mix400-1sft-2fullpara-1e-5

Ctrl+K

Ctrl+K

2 contributors

History: 2 commits

QinLiuNLP's picture

Training in progress, step 250

3f8b62b verified 10 months ago

runs
Training in progress, step 250 10 months ago
.gitattributes

1.52 kB

initial commit 10 months ago
config.json

737 Bytes

Training in progress, step 250 10 months ago
model-00001-of-00004.safetensors

4.98 GB
LFS

Training in progress, step 250 10 months ago
model-00002-of-00004.safetensors

5 GB
LFS

Training in progress, step 250 10 months ago
model-00003-of-00004.safetensors

4.92 GB
LFS

Training in progress, step 250 10 months ago
model-00004-of-00004.safetensors

1.17 GB
LFS

Training in progress, step 250 10 months ago
model.safetensors.index.json

24 kB

Training in progress, step 250 10 months ago
special_tokens_map.json

439 Bytes

Training in progress, step 250 10 months ago
tokenizer.json

9.09 MB

Training in progress, step 250 10 months ago
tokenizer_config.json

51 kB

Training in progress, step 250 10 months ago
training_args.bin
Detected Pickle imports (14)
- "trl.trainer.dpo_config.FDivergenceType",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.HubStrategy",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames",
- "alignment.configs.DPOConfig"
How to fix it?
7.67 kB
LFS

Training in progress, step 250 10 months ago