Hugging Face's logo

Finnish-NLP
/
byt5-base-finnish

Text2Text Generation
Transformers
PyTorch
JAX
TensorBoard
Finnish
t5
finnish
byt5
t5x
seq2seq
text-generation-inference
Model card Files Metrics Community
aapot commited on
Commit
105a2e7
•
1 Parent(s): 3f8e7db

Add 10k train step

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. .gitignore +1 -0
  3. base_pretrain.gin +24 -0
  4. checkpoint_10000/checkpoint +3 -0
  5. checkpoint_10000/state.param_states.decoder.decoder_norm.scale.v/.zarray +3 -0
  6. checkpoint_10000/state.param_states.decoder.decoder_norm.scale.v/0 +3 -0
  7. checkpoint_10000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
  8. checkpoint_10000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  9. checkpoint_10000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +3 -0
  10. checkpoint_10000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0 +3 -0
  11. checkpoint_10000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
  12. checkpoint_10000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 +3 -0
  13. checkpoint_10000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
  14. checkpoint_10000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  15. checkpoint_10000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray +3 -0
  16. checkpoint_10000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0 +3 -0
  17. checkpoint_10000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
  18. checkpoint_10000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 +3 -0
  19. checkpoint_10000/state.param_states.decoder.layers_2.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
  20. checkpoint_10000/state.param_states.decoder.layers_2.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  21. checkpoint_10000/state.param_states.decoder.layers_2.pre_mlp_layer_norm.scale.v/.zarray +3 -0
  22. checkpoint_10000/state.param_states.decoder.layers_2.pre_mlp_layer_norm.scale.v/0 +3 -0
  23. checkpoint_10000/state.param_states.decoder.layers_2.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
  24. checkpoint_10000/state.param_states.decoder.layers_2.pre_self_attention_layer_norm.scale.v/0 +3 -0
  25. checkpoint_10000/state.param_states.decoder.layers_3.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
  26. checkpoint_10000/state.param_states.decoder.layers_3.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  27. checkpoint_10000/state.param_states.decoder.layers_3.pre_mlp_layer_norm.scale.v/.zarray +3 -0
  28. checkpoint_10000/state.param_states.decoder.layers_3.pre_mlp_layer_norm.scale.v/0 +3 -0
  29. checkpoint_10000/state.param_states.decoder.layers_3.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
  30. checkpoint_10000/state.param_states.decoder.layers_3.pre_self_attention_layer_norm.scale.v/0 +3 -0
  31. checkpoint_10000/state.param_states.decoder.layers_4.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
  32. checkpoint_10000/state.param_states.decoder.layers_4.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  33. checkpoint_10000/state.param_states.decoder.layers_4.pre_mlp_layer_norm.scale.v/.zarray +3 -0
  34. checkpoint_10000/state.param_states.decoder.layers_4.pre_mlp_layer_norm.scale.v/0 +3 -0
  35. checkpoint_10000/state.param_states.decoder.layers_4.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
  36. checkpoint_10000/state.param_states.decoder.layers_4.pre_self_attention_layer_norm.scale.v/0 +3 -0
  37. checkpoint_10000/state.param_states.decoder.layers_5.pre_cross_attention_layer_norm.scale.v/.zarray +3 -0
  38. checkpoint_10000/state.param_states.decoder.layers_5.pre_cross_attention_layer_norm.scale.v/0 +3 -0
  39. checkpoint_10000/state.param_states.decoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray +3 -0
  40. checkpoint_10000/state.param_states.decoder.layers_5.pre_mlp_layer_norm.scale.v/0 +3 -0
  41. checkpoint_10000/state.param_states.decoder.layers_5.pre_self_attention_layer_norm.scale.v/.zarray +3 -0
  42. checkpoint_10000/state.param_states.decoder.layers_5.pre_self_attention_layer_norm.scale.v/0 +3 -0
  43. checkpoint_10000/state.param_states.decoder.relpos_bias.rel_embedding.v/.zarray +3 -0
  44. checkpoint_10000/state.param_states.decoder.relpos_bias.rel_embedding.v/0.0 +3 -0
  45. checkpoint_10000/state.param_states.encoder.encoder_norm.scale.v/.zarray +3 -0
  46. checkpoint_10000/state.param_states.encoder.encoder_norm.scale.v/0 +3 -0
  47. checkpoint_10000/state.param_states.encoder.layers_0.pre_attention_layer_norm.scale.v/.zarray +3 -0
  48. checkpoint_10000/state.param_states.encoder.layers_0.pre_attention_layer_norm.scale.v/0 +3 -0
  49. checkpoint_10000/state.param_states.encoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray +3 -0
  50. checkpoint_10000/state.param_states.encoder.layers_0.pre_mlp_layer_norm.scale.v/0 +3 -0
.gitattributes CHANGED
@@ -1,6 +1,7 @@
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
 
4
  *.bz2 filter=lfs diff=lfs merge=lfs -text
5
  *.ftz filter=lfs diff=lfs merge=lfs -text
6
  *.gz filter=lfs diff=lfs merge=lfs -text
@@ -25,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
5
  *.bz2 filter=lfs diff=lfs merge=lfs -text
6
  *.ftz filter=lfs diff=lfs merge=lfs -text
7
  *.gz filter=lfs diff=lfs merge=lfs -text
 
26
  *.zip filter=lfs diff=lfs merge=lfs -text
27
  *.zstandard filter=lfs diff=lfs merge=lfs -text
28
  *tfevents* filter=lfs diff=lfs merge=lfs -text
29
+ checkpoint*/** filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ __pycache__/
base_pretrain.gin ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Register necessary SeqIO Tasks/Mixtures.
2
+ from __gin__ import dynamic_registration
3
+ from t5x import utils
4
+ import tasks
5
+ import __main__ as train_script
6
+
7
+ include 't5x/examples/t5/byt5/base.gin'
8
+ include 't5x/configs/runs/pretrain.gin'
9
+
10
+
11
+ # ------------------- Training specification overrides --------------------------
12
+ train_script.train:
13
+ eval_period = 10000
14
+
15
+ utils.SaveCheckpointConfig:
16
+ period = 10000
17
+ keep = 10
18
+
19
+ MIXTURE_OR_TASK_NAME = "byt5_pretrain_finnish"
20
+ USE_CACHED_TASKS = False
21
+ TASK_FEATURE_LENGTHS = {"inputs": 512, "targets": 512}
22
+ TRAIN_STEPS = 1000000
23
+ DROPOUT_RATE = 0.0
24
+ BATCH_SIZE = 256
checkpoint_10000/checkpoint ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f34bdb8f96c3559b2aa10df0336250ae19e3270a0e5f830a682a13469f252bb
3
+ size 2792047
checkpoint_10000/state.param_states.decoder.decoder_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.decoder_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b02e30ad784125e9ecc40ddf27786a86edbfb3bc8f46a51f668ee3b5c5b7af5
3
+ size 5546
checkpoint_10000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_0.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49d5808306f7001c8056a954c8a196fa69ec63ef873f816d8b8eae1f71fb898
3
+ size 5540
checkpoint_10000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_0.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d250f8cd70a199e4797f733a3b469a7e7eb0110b7c31835f2421db9dc3ecd3b7
3
+ size 5471
checkpoint_10000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_0.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139c78ca54e195479efa3da47e9e2a76d57e7e1d833cd7eec1cc0fee412242da
3
+ size 5591
checkpoint_10000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_1.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e7f913939f945cd1baf3a05ec2b26f2e69f0f24bd0e25c32a881aaa65d727f
3
+ size 5502
checkpoint_10000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_1.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3acae52d1597753f9b2f366627567acff7de0aaee8620109d0b73bbdfc4d789
3
+ size 5473
checkpoint_10000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_1.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca47bf50d898efde5d9b10fdb8b83b008ca24c693098c0cf26609f7b86d19c2
3
+ size 5555
checkpoint_10000/state.param_states.decoder.layers_2.pre_cross_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_2.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb56573b3bc10b358a676e511073f579b80d0d8563c015dd0ff8927ffcfb23b
3
+ size 5485
checkpoint_10000/state.param_states.decoder.layers_2.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_2.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a86495308631fe5372d96b05d2a3f9f2a860402ec111b4ad96322bd353df94b
3
+ size 5495
checkpoint_10000/state.param_states.decoder.layers_2.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_2.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa259d85404d2c6348dab818abfd2d22a87153fb0197bb42fda9d8b0e934850
3
+ size 5536
checkpoint_10000/state.param_states.decoder.layers_3.pre_cross_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_3.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a89715c7324274863f7983995ff8945c639c2be07648214651796e987c2815a
3
+ size 5506
checkpoint_10000/state.param_states.decoder.layers_3.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_3.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c5a77f7158105215a9509ba57a0369b033e11f752c902d5b77bd5d1beaaeac
3
+ size 5503
checkpoint_10000/state.param_states.decoder.layers_3.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_3.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:162c30ff3d061438785dac40e5d6cb8a6e3f844a2616d2049719086ff42181f5
3
+ size 5547
checkpoint_10000/state.param_states.decoder.layers_4.pre_cross_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_4.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0613f2003d094908c3faf2875b5ca9680991ab912772224f169d0701b6278685
3
+ size 5519
checkpoint_10000/state.param_states.decoder.layers_4.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_4.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ab5fa4ac6b702e9e97e14f437c7e52b832b2706a73467d1c40db33996b84be
3
+ size 5570
checkpoint_10000/state.param_states.decoder.layers_4.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_4.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b19d46610a38c8edbb56dd6263a1798dff8027238c4a16e8e6983b3033d929
3
+ size 5576
checkpoint_10000/state.param_states.decoder.layers_5.pre_cross_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_5.pre_cross_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a517e404b1a6df3abe86ac685c1b4de20f848ffdd10bb3b12a57c61f7b0946c
3
+ size 5519
checkpoint_10000/state.param_states.decoder.layers_5.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_5.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6cf26d2e6e6708e7e2c13c6f84a57acbb46fbbd3493b2df94e563c3637ecf84
3
+ size 5549
checkpoint_10000/state.param_states.decoder.layers_5.pre_self_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.decoder.layers_5.pre_self_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeaf0ab88e801024c13a0052c0c3e8073369c859e28a72dca19868806dbd6005
3
+ size 5665
checkpoint_10000/state.param_states.decoder.relpos_bias.rel_embedding.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7028b3f2007ef72746d64487314ca6723cab7f9713ecb30bd30b73a22418e831
3
+ size 172
checkpoint_10000/state.param_states.decoder.relpos_bias.rel_embedding.v/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65284ef7b0de15a72da6fcca4a522092b8d4301a5aafea385486e85988ad0b85
3
+ size 1445
checkpoint_10000/state.param_states.encoder.encoder_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.encoder.encoder_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b58a73db9acb2ae71f77eb4c6753399fed91531c45ee86df63123339242683a
3
+ size 5543
checkpoint_10000/state.param_states.encoder.layers_0.pre_attention_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.encoder.layers_0.pre_attention_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eac16a2916d7d8082fa87fc236150b4cf77a5f8e4c8802cd530015cabdf199b
3
+ size 5614
checkpoint_10000/state.param_states.encoder.layers_0.pre_mlp_layer_norm.scale.v/.zarray ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15454ca58ace9d64cc661f694fa3a5c43479ab9e9298e3f5d36932e899b8ecc
3
+ size 170
checkpoint_10000/state.param_states.encoder.layers_0.pre_mlp_layer_norm.scale.v/0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149e9f6c7a89621bdf03c0abc8ef305ae9ac74d6a9408d3ee8b0ce8c0971314e
3
+ size 5437