DUAL-GPO
/

phi-2-gpo-iter-1

alignment-handbook

generated_from_trainer

Model card Files Files and versions Community

phi-2-gpo-iter-1

1 contributor

History: 4 commits

lole25's picture

End of training

dd5eeed verified 2 months ago

.gitattributes

1.52 kB

initial commit 2 months ago
README.md

2.22 kB

End of training 2 months ago
adapter_config.json

595 Bytes

Training in progress, step 100 2 months ago
adapter_model.safetensors
42 MB
LFS

Model save 2 months ago
added_tokens.json

1.08 kB

Training in progress, step 100 2 months ago
all_results.json

751 Bytes

Model save 2 months ago
config.json

898 Bytes

End of training 2 months ago
eval_results.json

575 Bytes

Model save 2 months ago
merges.txt

456 kB

Training in progress, step 100 2 months ago
special_tokens_map.json

587 Bytes

Training in progress, step 100 2 months ago
tokenizer.json

2.11 MB

Training in progress, step 100 2 months ago
tokenizer_config.json

7.82 kB

Training in progress, step 100 2 months ago
train_results.json

197 Bytes

Model save 2 months ago
trainer_state.json

7.55 kB

Model save 2 months ago
training_args.bin
Detected Pickle imports (11)
- "torch.device",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "alignment.configs.DPOConfig",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.training_args.OptimizerNames",
- "torch.bfloat16"
How to fix it?
5.82 kB
LFS

Training in progress, step 100 2 months ago
vocab.json

798 kB

Training in progress, step 100 2 months ago