jiazhengli
/

Mixtral-8x7B-Instruct-v0.1-QLoRA-Assessment-Rationale-sft

Generated from Trainer

Model card Files Files and versions Community

Mixtral-8x7B-Instruct-v0.1-QLoRA-Assessment-Rationale-sft

2 contributors

History: 3 commits

jiazhengli's picture

Update README.md

2fb28ff verified 2 months ago

.gitattributes

1.52 kB

initial commit 6 months ago
README.md

3.2 kB

Update README.md 2 months ago
adapter_config.json

730 Bytes

init push 6 months ago
adapter_model.safetensors

485 MB
LFS

init push 6 months ago
all_results.json

307 Bytes

init push 6 months ago
eval_results.json

160 Bytes

init push 6 months ago
special_tokens_map.json

437 Bytes

init push 6 months ago
tokenizer.json

1.8 MB

init push 6 months ago
tokenizer.model

493 kB
LFS

init push 6 months ago
tokenizer_config.json

1.41 kB

init push 6 months ago
train_results.json

168 Bytes

init push 6 months ago
trainer_log.jsonl

7.08 kB

init push 6 months ago
trainer_state.json

6.88 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

35.3 kB

init push 6 months ago
training_loss.png

35.6 kB

init push 6 months ago