Hugging Face's logo

distily
/
distily_test_attn_miles

TensorBoard
Safetensors
Distily
gpt2
bitnet
1.58b
Generated from Trainer
Model card Files Metrics Community
lapp0 commited on
Commit
6958d56
·
verified ·
1 Parent(s): f56b68f

Training in progress, step 61875

Browse files
Files changed (9) hide show
  1. logs/attn_layer_mapper=all, attn_loss_fn=logsum, attn_projector=miles/completed.flag +0 -0
  2. logs/attn_layer_mapper=all, attn_loss_fn=logsum_v2, attn_projector=miles/events.out.tfevents.1724550994.f383272e719b +3 -0
  3. logs/attn_layer_mapper=all, attn_loss_fn=logsum_v2, attn_projector=miles/events.out.tfevents.1724551424.f383272e719b +3 -0
  4. logs/attn_layer_mapper=all, attn_loss_fn=logsum_v2, attn_projector=miles/events.out.tfevents.1724554427.f383272e719b +3 -0
  5. logs/attn_layer_mapper=last_k_2, attn_loss_fn=raw_mse, attn_projector=miles/events.out.tfevents.1724550610.f383272e719b +3 -0
  6. logs/attn_layer_mapper=last_k_2, attn_loss_fn=raw_mse, attn_projector=miles/events.out.tfevents.1724550834.f383272e719b +3 -0
  7. model.safetensors +1 -1
  8. tokenizer.json +14 -2
  9. training_args.bin +1 -1
logs/attn_layer_mapper=all, attn_loss_fn=logsum, attn_projector=miles/completed.flag ADDED
File without changes
logs/attn_layer_mapper=all, attn_loss_fn=logsum_v2, attn_projector=miles/events.out.tfevents.1724550994.f383272e719b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9ecff1c083011b5b2e14460b7397e9022fc867a6a5e0f4c4b18038aebb9480
3
+ size 872199
logs/attn_layer_mapper=all, attn_loss_fn=logsum_v2, attn_projector=miles/events.out.tfevents.1724551424.f383272e719b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc91eaa1bcba47728e775523709495a3dd08e261863fb07409f08f53c91f171
3
+ size 9973874
logs/attn_layer_mapper=all, attn_loss_fn=logsum_v2, attn_projector=miles/events.out.tfevents.1724554427.f383272e719b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac72776f1a1a430d4c883b6c0699319007f7036b51f860211f0dd5563d9df36
3
+ size 29625287
logs/attn_layer_mapper=last_k_2, attn_loss_fn=raw_mse, attn_projector=miles/events.out.tfevents.1724550610.f383272e719b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b286e62b6c823cafb9b711fd99fb81df24ba6d268c6b5d886676489aecc28219
3
+ size 5374
logs/attn_layer_mapper=last_k_2, attn_loss_fn=raw_mse, attn_projector=miles/events.out.tfevents.1724550834.f383272e719b ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd1786c838cd77297340d2f1cceebbe9615d4a17435342eac731bd4ae77f03a
3
+ size 5374
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:424703a70c6de33f4ea2c85dd1f2be0add3d5c47fbb2f81a48da75dd8c22aeee
3
  size 248894656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a254fdfdee5ed159677fe2a217e4ff046f7b0172f7bda4d5d9d7c3f172a7821
3
  size 248894656
tokenizer.json CHANGED
@@ -1,7 +1,19 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 50256,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1023,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Right",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 50256,
14
+ "pad_type_id": 0,
15
+ "pad_token": "<|endoftext|>"
16
+ },
17
  "added_tokens": [
18
  {
19
  "id": 50256,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0206f9d17505ba45df67cf2279065f851a908ed967be6f43a621173ad6cc3b7
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aca42a1f0fbeaf1e34e36d51e7d555d781aa9da66028354384c4a5611ad64b5
3
  size 5432