babylm-seqlen
/

mamba-2048-warmup-v2

Model card Files Files and versions

mamba-2048-warmup-v2

Ctrl+K

Ctrl+K

1 contributor

History: 29 commits

rdiehlmartinez's picture

Checkpoint step: 12463 | Target words: 1,000,000,000 | Actual tokens: 1,633,419,264 | Actual words: 1,000,000,000 | Progress: 28/28

f74513d 2 months ago

.gitattributes

1.52 kB

initial commit 2 months ago
config.json

765 Bytes

Checkpoint step: 13 | Target words: 1,000,000 | Actual tokens: 1,703,936 | Actual words: 1,043,171.2405713368 | Progress: 1/28 2 months ago
model.safetensors

637 MB
xet

Checkpoint step: 12463 | Target words: 1,000,000,000 | Actual tokens: 1,633,419,264 | Actual words: 1,000,000,000 | Progress: 28/28 2 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.training_args.TrainingArguments",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.84 kB
xet

Checkpoint step: 13 | Target words: 1,000,000 | Actual tokens: 1,703,936 | Actual words: 1,043,171.2405713368 | Progress: 1/28 2 months ago