Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
bertin-project
/
bertin-base-gaussian-exp-512seqlen
like
1
Follow
BERTIN Project
20
Fill-Mask
Transformers
PyTorch
JAX
TensorBoard
Joblib
Spanish
roberta
spanish
Inference Endpoints
License:
cc-by-4.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
bertin-base-gaussian-exp-512seqlen
/
outputs
3 contributors
History:
6 commits
versae
Step... (49001/50000 | Loss: 1.5274475812911987, Acc: 0.6873284578323364): 100%|ββββββββββββββββββββββββββββββ| 50000/50000 [9:53:39<00:00, 1.23s/it]
e17c43d
over 3 years ago
checkpoints
Step... (49001/50000 | Loss: 1.5274475812911987, Acc: 0.6873284578323364): 98%|ββββββββββββββββββββββββββββββ| 49024/50000 [9:31:53<21:29, 1.32s/it]
over 3 years ago
config.json
Safe
618 Bytes
Step... (24001/50000 | Loss: 1.617178201675415, Acc: 0.6729233860969543): 48%|ββββββββββββββ | 24176/50000 [9:23:11<10:03:40, 1.40s/it]
over 3 years ago
data_collator.joblib
pickle
Detected Pickle imports (5)
"tokenizers.AddedToken"
,
"__main__.FlaxDataCollatorForLanguageModeling"
,
"tokenizers.models.Model"
,
"transformers.models.roberta.tokenization_roberta_fast.RobertaTokenizerFast"
,
"tokenizers.Tokenizer"
How to fix it?
1.47 MB
LFS
Step... (42001/50000 | Loss: 1.5368554592132568, Acc: 0.6858981847763062): 86%|ββββββββββββββββββββββββ | 42934/50000 [7:12:02<3:21:33, 1.71s/it]
over 3 years ago
events.out.tfevents.1626606849.tablespoon.3622971.3.v2
Safe
3.62 MB
LFS
tfevents
over 3 years ago
events.out.tfevents.1626649897.tablespoon.3816803.3.v2
Safe
40 Bytes
LFS
Step... (42001/50000 | Loss: 1.5368554592132568, Acc: 0.6858981847763062): 86%|ββββββββββββββββββββββββ | 42934/50000 [7:12:02<3:21:33, 1.71s/it]
over 3 years ago
events.out.tfevents.1626650133.tablespoon.3825201.3.v2
Safe
3.81 MB
LFS
Step... (49001/50000 | Loss: 1.5274475812911987, Acc: 0.6873284578323364): 100%|ββββββββββββββββββββββββββββββ| 50000/50000 [9:53:39<00:00, 1.23s/it]
over 3 years ago
flax_model.msgpack
Safe
250 MB
LFS
Step... (49001/50000 | Loss: 1.5274475812911987, Acc: 0.6873284578323364): 98%|ββββββββββββββββββββββββββββββ| 49024/50000 [9:31:53<21:29, 1.32s/it]
over 3 years ago
optimizer_state.msgpack
Safe
500 MB
LFS
Step... (49001/50000 | Loss: 1.5274475812911987, Acc: 0.6873284578323364): 98%|ββββββββββββββββββββββββββββββ| 49024/50000 [9:31:53<21:29, 1.32s/it]
over 3 years ago
training_args.joblib
pickle
Detected Pickle imports (4)
"torch.device"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.training_args.TrainingArguments"
How to fix it?
1.87 kB
LFS
Step... (42001/50000 | Loss: 1.5368554592132568, Acc: 0.6858981847763062): 86%|ββββββββββββββββββββββββ | 42934/50000 [7:12:02<3:21:33, 1.71s/it]
over 3 years ago
training_state.json
Safe
15 Bytes
Step... (49001/50000 | Loss: 1.5274475812911987, Acc: 0.6873284578323364): 98%|ββββββββββββββββββββββββββββββ| 49024/50000 [9:31:53<21:29, 1.32s/it]
over 3 years ago