Update README.md
4ffac80
-
evals
Adding evaluations on val set
-
791 Bytes
Adding `safetensors` variant of this model (#1)
-
4.97 kB
Update README.md
-
762 Bytes
Model at 200k steps, mlm acc 0.5743
-
158 Bytes
Model at 200k steps, mlm acc 0.5743
-
904 Bytes
Model at 200k steps, mlm acc 0.5743
data_collator.joblib
Detected Pickle imports (4)
- "tokenizers.Tokenizer",
- "__main__.FlaxDataCollatorForLanguageModeling",
- "transformers.models.bert.tokenization_bert_fast.BertTokenizerFast",
- "tokenizers.models.Model"
How to fix it?
1.96 MB
Model at 200k steps, mlm acc 0.5743
-
712 MB
New flax model
-
712 MB
Adding `safetensors` variant of this model (#1)
-
712 MB
Model at 200k steps, mlm acc 0.5743
-
929 Bytes
New flax model
-
923 Bytes
Adding evaluations on val set
-
1.01 kB
Adding evaluations on val set
-
32.9 kB
Adding evaluations on val set
-
36.5 kB
Adding evaluations on val set
-
112 Bytes
Model at 200k steps, mlm acc 0.5743
-
1.96 MB
Model at 200k steps, mlm acc 0.5743
-
333 Bytes
Model at 200k steps, mlm acc 0.5743
training_args.joblib
Detected Pickle imports (4)
- "transformers.trainer_utils.SchedulerType",
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.TrainingArguments"
How to fix it?
1.86 kB
Model at 200k steps, mlm acc 0.5743
-
16 Bytes
Model at 200k steps, mlm acc 0.5743
-
996 kB
Model at 200k steps, mlm acc 0.5743