langgptai
/

llama3-8b_sa_v0.1

Generated from Trainer

Model card Files Files and versions Community

llama3-8b_sa_v0.1

1 contributor

History: 2 commits

sci-m-wang's picture

Upload 14 files

f232a59 verified 5 months ago

.gitattributes

1.52 kB

initial commit 5 months ago
README.md

1.83 kB

Upload 14 files 5 months ago
adapter_config.json

659 Bytes

Upload 14 files 5 months ago
adapter_model.safetensors

13.6 MB
LFS

Upload 14 files 5 months ago
all_results.json

349 Bytes

Upload 14 files 5 months ago
eval_results.json

161 Bytes

Upload 14 files 5 months ago
special_tokens_map.json

325 Bytes

Upload 14 files 5 months ago
tokenizer.json

9.09 MB

Upload 14 files 5 months ago
tokenizer_config.json

51.3 kB

Upload 14 files 5 months ago
train_results.json

208 Bytes

Upload 14 files 5 months ago
trainer_log.jsonl

21.5 kB

Upload 14 files 5 months ago
trainer_state.json

13.6 kB

Upload 14 files 5 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.18 kB
LFS

Upload 14 files 5 months ago
training_eval_loss.png

34.7 kB

Upload 14 files 5 months ago
training_loss.png

36.4 kB

Upload 14 files 5 months ago