Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
klcsp
/
mistral-7b-0.3-gpt4o_100k_classification-lora
like
0
PEFT
TensorBoard
Safetensors
llama-duo/synth_classification_dataset_dedup
mistral
alignment-handbook
trl
sft
Generated from Trainer
8-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
009fb31
mistral-7b-0.3-gpt4o_100k_classification-lora
1 contributor
History:
7 commits
chansung
Training in progress, step 200
009fb31
verified
about 11 hours ago
runs
Training in progress, step 200
about 11 hours ago
.gitattributes
1.52 kB
initial commit
about 13 hours ago
README.md
1.69 kB
End of training
about 13 hours ago
adapter_config.json
649 Bytes
Training in progress, step 100
about 12 hours ago
adapter_model.safetensors
1.09 GB
LFS
Training in progress, step 200
about 11 hours ago
added_tokens.json
51 Bytes
Training in progress, step 100
about 13 hours ago
all_results.json
396 Bytes
End of training
about 13 hours ago
config.json
1.15 kB
End of training
about 13 hours ago
eval_results.json
182 Bytes
End of training
about 13 hours ago
special_tokens_map.json
557 Bytes
Training in progress, step 100
about 13 hours ago
tokenizer.json
3.67 MB
Training in progress, step 100
about 13 hours ago
tokenizer.model
587 kB
LFS
Training in progress, step 100
about 13 hours ago
tokenizer_config.json
137 kB
Training in progress, step 100
about 13 hours ago
train_results.json
234 Bytes
Model save
about 13 hours ago
trainer_state.json
5.86 kB
Model save
about 13 hours ago
training_args.bin
pickle
Detected Pickle imports (9)
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.SchedulerType"
,
"alignment.configs.SFTConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.75 kB
LFS
Training in progress, step 100
about 12 hours ago