Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
bertin-project
/
bertin-base-stepwise-exp-512seqlen
like
0
Follow
BERTIN Project
32
Fill-Mask
Transformers
PyTorch
JAX
TensorBoard
Joblib
Safetensors
Spanish
roberta
spanish
License:
cc-by-4.0
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
1
Deploy
Use this model
main
bertin-base-stepwise-exp-512seqlen
/
outputs
5.26 GB
3 contributors
History:
23 commits
versae
Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 64%|ββββββββββββββββββ | 31806/50000 [12:45:50<7:10:54, 1.42s/it]
a135ed0
over 4 years ago
checkpoints
Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 64%|ββββββββββββββββββ | 31806/50000 [12:45:50<7:10:54, 1.42s/it]
over 4 years ago
config.json
618 Bytes
Step... (1000/50000 | Loss: 1.7686773538589478, Acc: 0.6487793326377869): 3%|β | 1286/50000 [29:40<20:20:20, 1.50s/it]
over 4 years ago
data_collator.joblib
1.47 MB
xet
Step... (1000/50000 | Loss: 1.7686773538589478, Acc: 0.6487793326377869): 3%|β | 1286/50000 [29:40<20:20:20, 1.50s/it]
over 4 years ago
events.out.tfevents.1627258355.tablespoon.3000110.3.v2
7.36 MB
xet
Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 64%|ββββββββββββββββββ | 31806/50000 [12:45:50<7:10:54, 1.42s/it]
over 4 years ago
flax_model.msgpack
250 MB
xet
Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 64%|ββββββββββββββββββ | 31806/50000 [12:45:50<7:10:54, 1.42s/it]
over 4 years ago
optimizer_state.msgpack
500 MB
xet
Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 64%|ββββββββββββββββββ | 31806/50000 [12:45:50<7:10:54, 1.42s/it]
over 4 years ago
training_args.joblib
1.87 kB
xet
Step... (1000/50000 | Loss: 1.7686773538589478, Acc: 0.6487793326377869): 3%|β | 1286/50000 [29:40<20:20:20, 1.50s/it]
over 4 years ago
training_state.json
15 Bytes
Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 64%|ββββββββββββββββββ | 31806/50000 [12:45:50<7:10:54, 1.42s/it]
over 4 years ago