adapter / B-2k-lora-rank256-lr0.00005-med2k

6.64 GB

Ctrl+K

1 contributor

History: 1 commit

poppuppy

Upload folder using huggingface_hub

31afb15 verified 15 days ago

README.md

1.5 kB
Upload folder using huggingface_hub 15 days ago
adapter_config.json

802 Bytes
Upload folder using huggingface_hub 15 days ago
adapter_model.safetensors

6.63 GB
xet

Upload folder using huggingface_hub 15 days ago
all_results.json

338 Bytes
Upload folder using huggingface_hub 15 days ago
chat_template.jinja

656 Bytes
Upload folder using huggingface_hub 15 days ago
eval_results.json

159 Bytes
Upload folder using huggingface_hub 15 days ago
special_tokens_map.json

506 Bytes
Upload folder using huggingface_hub 15 days ago
tokenizer.json

17.2 MB
xet

Upload folder using huggingface_hub 15 days ago
tokenizer_config.json

50.9 kB
Upload folder using huggingface_hub 15 days ago
train_results.json

199 Bytes
Upload folder using huggingface_hub 15 days ago
trainer_log.jsonl

1.6 kB
Upload folder using huggingface_hub 15 days ago
trainer_state.json

2.33 kB
Upload folder using huggingface_hub 15 days ago
training_args.bin
Detected Pickle imports (14)
- "llamafactory.hparams.training_args.TrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.SchedulerType",
- "torch.device",
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.bfloat16",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
8.34 kB
xet

Upload folder using huggingface_hub 15 days ago
training_loss.png

38.5 kB
Upload folder using huggingface_hub 15 days ago

Detected Pickle imports (14)