caijinyue
/

medgemma-4b-it-sft-lora-fp_o3_195

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

medgemma-4b-it-sft-lora-fp_o3_195

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

caijinyue's picture

Training in progress, epoch 1

1f09b8e verified 3 months ago

runs
Training in progress, epoch 1 3 months ago
.gitattributes

1.57 kB

Training in progress, epoch 1 3 months ago
README.md

1.51 kB

Model save 3 months ago
adapter_config.json

927 Bytes

Training in progress, epoch 1 3 months ago
adapter_model.safetensors

2.84 GB
xet

Training in progress, epoch 1 3 months ago
chat_template.jinja

1.53 kB

Training in progress, epoch 1 3 months ago
preprocessor_config.json

570 Bytes

Training in progress, epoch 1 3 months ago
processor_config.json

70 Bytes

Training in progress, epoch 1 3 months ago
special_tokens_map.json

662 Bytes

Training in progress, epoch 1 3 months ago
tokenizer.json

33.4 MB
xet

Training in progress, epoch 1 3 months ago
tokenizer_config.json

1.16 MB

Training in progress, epoch 1 3 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "trl.trainer.sft_config.SFTConfig",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState"
How to fix it?
5.75 kB
xet

Training in progress, epoch 1 3 months ago