Medxa
/

donut-paper-ktp

vision-encoder-decoder

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

donut-paper-ktp

Ctrl+K

Ctrl+K

1 contributor

History: 360 commits

aryaadhi's picture

Best model with eval_loss 0.4990

5fd4a18 verified about 1 month ago

runs
End of training about 1 month ago
.gitattributes

1.52 kB

initial commit about 1 month ago
README.md

1.18 kB

End of training about 1 month ago
added_tokens.json

910 Bytes

Best processor with eval_loss 4.6618 about 1 month ago
config.json

1.76 kB

Best model with eval_loss 8.3023 about 1 month ago
generation_config.json

160 Bytes

Model save about 1 month ago
model.safetensors

809 MB
xet

Best model with eval_loss 0.4990 about 1 month ago
preprocessor_config.json

420 Bytes

Best processor with eval_loss 8.3023 about 1 month ago
sentencepiece.bpe.model

1.3 MB
xet

End of training about 1 month ago
special_tokens_map.json

6.23 kB

Best processor with eval_loss 4.6618 about 1 month ago
tokenizer.json

4.02 MB

Best processor with eval_loss 8.3023 about 1 month ago
tokenizer_config.json

8.57 kB

Best processor with eval_loss 4.6618 about 1 month ago
training_args.bin
Detected Pickle imports (10)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
5.5 kB
xet

Training in progress, epoch 1 about 1 month ago