Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
frankmorales2020
/
Meta-Llama-3-8B-MEDAL-flash-attention-2-cosine
like
0
PEFT
TensorBoard
Safetensors
generator
trl
sft
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
3961e2d
Meta-Llama-3-8B-MEDAL-flash-attention-2-cosine
1 contributor
History:
2 commits
frankmorales2020
Training in progress, epoch 0
3961e2d
verified
6 months ago
runs
Training in progress, epoch 0
6 months ago
.gitattributes
1.52 kB
initial commit
6 months ago
adapter_config.json
731 Bytes
Training in progress, epoch 0
6 months ago
adapter_model.safetensors
1.34 GB
LFS
Training in progress, epoch 0
6 months ago
special_tokens_map.json
439 Bytes
Training in progress, epoch 0
6 months ago
tokenizer.json
9.09 MB
Training in progress, epoch 0
6 months ago
tokenizer_config.json
50.8 kB
Training in progress, epoch 0
6 months ago
training_args.bin
pickle
Detected Pickle imports (9)
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.training_args.TrainingArguments"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.state.PartialState"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"torch.device"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.HubStrategy"
How to fix it?
5.24 kB
LFS
Training in progress, epoch 0
6 months ago