versae commited on
Commit
8e64991
·
1 Parent(s): d9636e4

Saving weights and logs of step 60000 - epoch 51

Browse files
Files changed (3) hide show
  1. README.md +2 -1
  2. flax_model.msgpack +1 -1
  3. training_state.bin +2 -2
README.md CHANGED
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
48
  - num_train_dataset_workers: 32
49
  - num_hosts: 1
50
  - total_num_training_examples: 4,800,000
51
- - steps_per_epoch: 1985
52
  - num_beams: None
53
  - weight_decay: 0.01
54
  - adam_beta1: 0.9
@@ -68,6 +68,7 @@ The following hyperparameters were used during training:
68
  | 30000 | 1.2561 | 0.2111 | 14.6277 | 4.0617 | 17.9521 | 4.5011 |
69
  | 40000 | 33.1032 | 10.4733 | 100.0 | 100.0 | 100.0 | 98.0681 |
70
  | 50000 | 3.0192 | 2.5972 | 100.7979 | 80.9301 | 101.3298 | 79.8447 |
 
71
 
72
 
73
  ### Framework versions
 
48
  - num_train_dataset_workers: 32
49
  - num_hosts: 1
50
  - total_num_training_examples: 4,800,000
51
+ - steps_per_epoch: 1169
52
  - num_beams: None
53
  - weight_decay: 0.01
54
  - adam_beta1: 0.9
 
68
  | 30000 | 1.2561 | 0.2111 | 14.6277 | 4.0617 | 17.9521 | 4.5011 |
69
  | 40000 | 33.1032 | 10.4733 | 100.0 | 100.0 | 100.0 | 98.0681 |
70
  | 50000 | 3.0192 | 2.5972 | 100.7979 | 80.9301 | 101.3298 | 79.8447 |
71
+ | 60000 | 2.7909 | 2.0728 | 99.6011 | 79.8944 | 100.5319 | 78.8688 |
72
 
73
 
74
  ### Framework versions
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfb29f12b77d3746ed482c0b45d9941f076b1dffcff1c342c1411aaaff9c35f5
3
  size 3086611993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f866e787146e24c4500d40746f42d281d07c90796777332e227095249f4df3
3
  size 3086611993
training_state.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d1204e0389992a5325d159a0f7b7732bf6a4b2a84f7dab4ad200c129b9eb1cc
3
- size 1494
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd4aa3fe102d92fbff78f2fe68e0299155c085e4bea66874666465f600bfab3
3
+ size 1745