jiazhengli
/

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

Generated from Trainer

Model card Files Files and versions Community

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

2 contributors

History: 3 commits

jiazhengli's picture

Update README.md

50e66b0 verified 2 months ago

.gitattributes

1.52 kB

initial commit 6 months ago
README.md

4.79 kB

Update README.md 2 months ago
adapter_config.json

727 Bytes

init push 6 months ago
adapter_model.safetensors

83.9 MB
LFS

init push 6 months ago
all_results.json

691 Bytes

init push 6 months ago
eval_results.json

544 Bytes

init push 6 months ago
special_tokens_map.json

325 Bytes

init push 6 months ago
tokenizer.json

9.09 MB

init push 6 months ago
tokenizer_config.json

51.3 kB

init push 6 months ago
train_results.json

167 Bytes

init push 6 months ago
trainer_log.jsonl

40.9 kB

init push 6 months ago
trainer_state.json

97.1 kB

init push 6 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 6 months ago
training_eval_loss.png

43.6 kB

init push 6 months ago
training_loss.png

51.5 kB

init push 6 months ago
training_rewards_accuracies.png

52.2 kB

init push 6 months ago