Hugging Face's logo

distily
/
distily_test_attn_ortho_whiteners

TensorBoard
Safetensors
Distily
gpt2
bitnet
1.58b
Generated from Trainer
Model card Files Metrics Community
lapp0 commited on
Commit
f48f5a5
•
1 Parent(s): 4be8769

Training in progress, step 61875

Browse files
Files changed (9) hide show
  1. logs/attn_layer_mapper=layer-2, attn_loss_fn=cos, attn_projector=orthogonal_layernorm/events.out.tfevents.1724896607.d9703cfffc0c +3 -0
  2. logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm, max_grad_norm=100/events.out.tfevents.1724896080.d9703cfffc0c +3 -0
  3. logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm/completed.flag +0 -0
  4. logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm, max_grad_norm=100/events.out.tfevents.1724896546.d9703cfffc0c +3 -0
  5. logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm/events.out.tfevents.1724896484.d9703cfffc0c +3 -0
  6. logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm/events.out.tfevents.1724896782.d9703cfffc0c +3 -0
  7. logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm/events.out.tfevents.1724897735.d9703cfffc0c +3 -0
  8. model.safetensors +1 -1
  9. training_args.bin +1 -1
logs/attn_layer_mapper=layer-2, attn_loss_fn=cos, attn_projector=orthogonal_layernorm/events.out.tfevents.1724896607.d9703cfffc0c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cffd2a486dbbaa7c7a44d8529b6bae2bc7ba29b6d7ba91619e4ccfe90db143
3
+ size 5621
logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm, max_grad_norm=100/events.out.tfevents.1724896080.d9703cfffc0c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab68387b95cf0570ec9dc1109a1a26665e5a6a64021605fb5edeee5af29744cf
3
+ size 788285
logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_batchnorm/completed.flag ADDED
File without changes
logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm, max_grad_norm=100/events.out.tfevents.1724896546.d9703cfffc0c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35286fc1e59d82c86d823cb716b948948fd1fad503c61057df2df1673be273f1
3
+ size 5667
logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm/events.out.tfevents.1724896484.d9703cfffc0c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ea84cda6972cee8451034266326027384c890be9882b22d40d3c95c9caba4c
3
+ size 5629
logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm/events.out.tfevents.1724896782.d9703cfffc0c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec56fb28bea64d85091a13ec062483fc2261b9bc04bbaeee8d84e889fc07553
3
+ size 2338556
logs/attn_layer_mapper=layer-2, attn_loss_fn=raw_mse, attn_projector=orthogonal_layernorm/events.out.tfevents.1724897735.d9703cfffc0c ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3410140b424aded7c6760d33dcdc2c62b0f80dd3b1f796d128addaec8e9d49
3
+ size 29625351
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6cf0df0a59fbf4feec70697b022087bbb7d0006f8855a74e4bc64a8012575fe
3
  size 248894656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73513c9efe702364131b6b90cea0cc01e8c9e75e60a93b032e63c93431c103d
3
  size 248894656
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:146fd7de077926ff060437708ca8699049b38a4be7b4e1e7c63e77c3f2079889
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37943b711deef9d5bc1213080af2d5434cc9346f7852c83e0233aa42a47f71d6
3
  size 5496