LLMsForHepth
/

s1-L-3.1-8B-qkv_v2

Generated from Trainer

Model card Files Files and versions

s1-L-3.1-8B-qkv_v2

111 MB

1 contributor

History: 3 commits

paulrichmond's picture

Training in progress, step 2048, checkpoint

5c58e9d verified 8 months ago

last-checkpoint
Training in progress, step 2048, checkpoint 8 months ago
.gitattributes

1.57 kB

Training in progress, step 2048 8 months ago
adapter_config.json

667 Bytes

Training in progress, step 2048 8 months ago
adapter_model.safetensors

18.9 MB
xet

Training in progress, step 2048 8 months ago
special_tokens_map.json

335 Bytes

Training in progress, step 2048 8 months ago
tokenizer.json

17.2 MB
xet

Training in progress, step 2048 8 months ago
tokenizer_config.json

50.5 kB

Training in progress, step 2048 8 months ago
training_args.bin
Detected Pickle imports (16)
- "__builtin__.dict",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "omegaconf.dictconfig.DictConfig",
- "collections.defaultdict",
- "omegaconf.base.ContainerMetadata",
- "omegaconf.nodes.AnyNode",
- "accelerate.state.PartialState",
- "torch.device",
- "typing.Any",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "omegaconf.base.Metadata",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.82 kB
xet

Training in progress, step 2048 8 months ago