Shahradmz
/

Qwen2-0.5B-Instruct_continual_data_debug_PPO_1

Generated from Trainer

Model card Files Files and versions

Qwen2-0.5B-Instruct_continual_data_debug_PPO_1 / last

24.5 MB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

Shahradmz's picture

Training in progress, step 5

43438ca verified about 1 year ago

README.md

5.1 kB
Training in progress, step 5 about 1 year ago
adapter_config.json

721 Bytes
Training in progress, step 5 about 1 year ago
adapter_model.safetensors

8.66 MB
xet

Training in progress, step 5 about 1 year ago
added_tokens.json

80 Bytes
Training in progress, step 5 about 1 year ago
merges.txt

1.67 MB
Training in progress, step 5 about 1 year ago
special_tokens_map.json

367 Bytes
Training in progress, step 5 about 1 year ago
tokenizer.json

11.4 MB
xet

Training in progress, step 5 about 1 year ago
tokenizer_config.json

1.33 kB
Training in progress, step 5 about 1 year ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.SaveStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "torch.device",
- "continual_ppo_trainer.ContinualPPOConfig"
How to fix it?
6.39 kB
xet

Training in progress, step 5 about 1 year ago
vocab.json

2.78 MB
Training in progress, step 5 about 1 year ago