yalhessi
/

lemexp-task1-v3-template_full_nodefs-Llama-3.2-1B-8lr-12epochs-no-eos

Generated from Trainer

Model card Files Files and versions

lemexp-task1-v3-template_full_nodefs-Llama-3.2-1B-8lr-12epochs-no-eos

170 MB

1 contributor

History: 13 commits

yalhessi's picture

Training in progress, epoch 6, checkpoint

f6991b5 verified 27 days ago

checkpoint-15587
Training in progress, epoch 1, checkpoint 27 days ago
checkpoint-31174
Training in progress, epoch 2, checkpoint 27 days ago
checkpoint-46761
Training in progress, epoch 3, checkpoint 27 days ago
checkpoint-62348
Training in progress, epoch 4, checkpoint 27 days ago
checkpoint-77935
Training in progress, epoch 5, checkpoint 27 days ago
checkpoint-93522
Training in progress, epoch 6, checkpoint 27 days ago
.gitattributes

1.93 kB

Training in progress, epoch 6, checkpoint 27 days ago
adapter_config.json

778 Bytes

Training in progress, epoch 1 27 days ago
adapter_model.safetensors

3.42 MB
xet

Training in progress, epoch 6 27 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SaveStrategy",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "transformers.training_args.TrainingArguments",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.97 kB
xet

Training in progress, epoch 1 27 days ago