Upload tokenizer
225b24a
verified
-
last-checkpoint
Training in progress, step 100000, checkpoint
-
runs
Initial version
-
trial-number=0-learning_rate=2.0e-05-warmup_ratio=0.060-min_lr=0.000-factor=0.910
Training in progress, step 10000
-
trial-number=1-learning_rate=2.5e-05-warmup_ratio=0.060-min_lr=0.000-factor=0.810
Training in progress, step 10000
-
trial-number=10-learning_rate=5.0e-05-warmup_ratio=0.030-min_lr=0.000-factor=0.970
Training in progress, step 10000
-
trial-number=11-learning_rate=1.9e-04-warmup_ratio=0.050-min_lr=0.000-factor=0.830
Training in progress, step 10000
-
trial-number=12-learning_rate=7.4e-06-warmup_ratio=0.030-min_lr=0.000-factor=0.930
Training in progress, step 10000
-
trial-number=13-learning_rate=9.3e-06-warmup_ratio=0.060-min_lr=0.000-factor=0.910
Training in progress, step 10000
-
trial-number=14-learning_rate=9.3e-05-warmup_ratio=0.020-min_lr=0.000-factor=0.820
Training in progress, step 10000
-
trial-number=15-learning_rate=4.0e-05-warmup_ratio=0.040-min_lr=0.000-factor=0.960
Training in progress, step 5000
-
trial-number=16-learning_rate=2.6e-05-warmup_ratio=0.040-min_lr=0.000-factor=0.860
Training in progress, step 10000
-
trial-number=17-learning_rate=3.0e-05-warmup_ratio=0.040-min_lr=0.000-factor=0.920
Training in progress, step 10000
-
trial-number=18-learning_rate=4.6e-05-warmup_ratio=0.040-min_lr=0.000-factor=0.820
Training in progress, step 10000
-
trial-number=19-learning_rate=8.0e-05-warmup_ratio=0.060-min_lr=0.000-factor=0.970
Training in progress, step 10000
-
trial-number=2-learning_rate=4.0e-05-warmup_ratio=0.020-min_lr=0.000-factor=0.890
Training in progress, step 10000
-
trial-number=20-learning_rate=8.1e-06-warmup_ratio=0.020-min_lr=0.000-factor=0.870
Training in progress, step 10000
-
trial-number=21-learning_rate=6.4e-06-warmup_ratio=0.050-min_lr=0.000-factor=0.850
Training in progress, step 10000
-
trial-number=22-learning_rate=1.6e-04-warmup_ratio=0.030-min_lr=0.000-factor=0.940
Training in progress, step 10000
-
trial-number=23-learning_rate=5.8e-05-warmup_ratio=0.050-min_lr=0.000-factor=0.800
Training in progress, step 10000
-
trial-number=24-learning_rate=1.5e-05-warmup_ratio=0.030-min_lr=0.000-factor=0.900
Training in progress, step 10000
-
trial-number=3-learning_rate=1.1e-04-warmup_ratio=0.050-min_lr=0.000-factor=0.850
Training in progress, step 10000
-
trial-number=4-learning_rate=1.1e-05-warmup_ratio=0.030-min_lr=0.000-factor=0.940
Training in progress, step 10000
-
trial-number=5-learning_rate=5.4e-06-warmup_ratio=0.050-min_lr=0.000-factor=0.970
Training in progress, step 10000
-
trial-number=6-learning_rate=1.4e-04-warmup_ratio=0.030-min_lr=0.000-factor=0.870
Training in progress, step 10000
-
trial-number=7-learning_rate=7.9e-05-warmup_ratio=0.060-min_lr=0.000-factor=0.920
Training in progress, step 10000
-
trial-number=8-learning_rate=2.0e-05-warmup_ratio=0.020-min_lr=0.000-factor=0.820
Training in progress, step 10000
-
trial-number=9-learning_rate=1.3e-05-warmup_ratio=0.050-min_lr=0.000-factor=0.890
Training in progress, step 10000
-
1.52 kB
initial commit
-
6.39 kB
Upload tokenizer
-
145 Bytes
Upload best_hyperparameters.json with huggingface_hub
-
1.74 kB
Upload best_hyperparameters.md with huggingface_hub
-
4.78 kB
Training in progress, step 5000
-
177 Bytes
Initial version
-
3.21 kB
Training in progress, step 5000
-
410 MB
Initial version
-
958 Bytes
Training in progress, step 5000
-
23.5 kB
Training in progress, step 5000
-
1.23 kB
Training in progress, step 5000
-
7.42 kB
Training in progress, step 20000
-
7.9 kB
Training in progress, step 5000
