jiazhengli
/

Meta-Llama-3-8B-QLoRA-Assessment-Rationale-sft

Generated from Trainer

Model card Files Files and versions Community

Meta-Llama-3-8B-QLoRA-Assessment-Rationale-sft

2 contributors

History: 4 commits

jiazhengli's picture

Update README.md

40da4a1 verified about 1 month ago

.gitattributes

1.52 kB

initial commit 4 months ago
README.md

3.18 kB

Update README.md about 1 month ago
adapter_config.json

727 Bytes

init push 4 months ago
adapter_model.safetensors

83.9 MB
LFS

init push 4 months ago
all_results.json

310 Bytes

init push 4 months ago
eval_results.json

163 Bytes

init push 4 months ago
special_tokens_map.json

325 Bytes

init push 4 months ago
tokenizer.json

9.09 MB

init push 4 months ago
tokenizer_config.json

51.3 kB

init push 4 months ago
train_results.json

168 Bytes

init push 4 months ago
trainer_log.jsonl

7.06 kB

init push 4 months ago
trainer_state.json

6.87 kB

init push 4 months ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
How to fix it?
5.11 kB
LFS

init push 4 months ago
training_eval_loss.png

39.9 kB

init push 4 months ago
training_loss.png

34.1 kB

init push 4 months ago