babylm-seqlen
/

mamba-512-warmup-v2

Model card Files Files and versions Community

mamba-512-warmup-v2

Ctrl+K

Ctrl+K

1 contributor

History: 29 commits

rdiehlmartinez's picture

Checkpoint step: 49,911 | Target words: 1,000,000,000 | Actual tokens: 1,635,483,648 | Actual words: 1,000,000,000.0000001 | Progress: 28/28

6f742e2 verified about 2 months ago

.gitattributes

1.52 kB

initial commit about 2 months ago
config.json

765 Bytes

Checkpoint step: 50 | Target words: 1,000,000 | Actual tokens: 1,638,400 | Actual words: 1,001,783.1740498088 | Progress: 1/28 about 2 months ago
model.safetensors

637 MB
LFS

Checkpoint step: 49,911 | Target words: 1,000,000,000 | Actual tokens: 1,635,483,648 | Actual words: 1,000,000,000.0000001 | Progress: 28/28 about 2 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.TrainingArguments",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType"
How to fix it?
5.84 kB
LFS

Checkpoint step: 50 | Target words: 1,000,000 | Actual tokens: 1,638,400 | Actual words: 1,001,783.1740498088 | Progress: 1/28 about 2 months ago