EvoLenTokenizer
/

base-200k

Generated from Trainer

Model card Files Files and versions

360 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

nancyH's picture

remove wandb console log (leaked .netrc path and run URLs)

d50f86a verified 1 day ago

.gitattributes

1.52 kB
initial commit 7 days ago
04.pretrain.sh

1.92 kB
final pretrained checkpoint at step 200000 7 days ago
04.pretrain_200k_base_5120.sh

1.78 kB
final pretrained checkpoint at step 200000 7 days ago
README.md

1.11 kB
final pretrained checkpoint at step 200000 7 days ago
all_results.json

472 Bytes
final pretrained checkpoint at step 200000 7 days ago
config.json

609 Bytes
final pretrained checkpoint at step 200000 7 days ago
eval_results.json

295 Bytes
final pretrained checkpoint at step 200000 7 days ago
generation_config.json

111 Bytes
final pretrained checkpoint at step 200000 7 days ago
model.safetensors

360 MB
xet

final pretrained checkpoint at step 200000 7 days ago
train_results.json

198 Bytes
final pretrained checkpoint at step 200000 7 days ago
trainer_state.json

25.2 kB
final pretrained checkpoint at step 200000 7 days ago
training_args.bin
Detected Pickle imports (8)
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.TrainingArguments",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "torch.device"
How to fix it?
5.14 kB
xet

final pretrained checkpoint at step 200000 7 days ago