Hugging Face's logo

llavallava
/
smolvlm-instruct-trl-dpo-rlaif-v

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
dpo
Model card Files
xet
 Metrics Community
llavallava commited on
Commit
6e3a780
·
verified ·
1 Parent(s): 66d6a3a

Training in progress, step 10

Browse files
Files changed (4) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +1 -1
  3. runs/Jan26_12-43-04_csr-95830.utdallas.edu/events.out.tfevents.1737916985.csr-95830.utdallas.edu.3626339.0 +3 -0
  4. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -26,13 +26,13 @@
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
29
- "gate_proj",
30
  "q_proj",
 
 
31
  "up_proj",
32
- "o_proj",
33
- "k_proj",
34
  "v_proj",
35
- "down_proj"
36
  ],
37
  "task_type": null,
38
  "use_dora": true,
 
26
  "rank_pattern": {},
27
  "revision": null,
28
  "target_modules": [
29
+ "o_proj",
30
  "q_proj",
31
+ "down_proj",
32
+ "gate_proj",
33
  "up_proj",
 
 
34
  "v_proj",
35
+ "k_proj"
36
  ],
37
  "task_type": null,
38
  "use_dora": true,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf8e5b7a6ec6a89838a6f3a92180feb9e94d05caf304754eca51967c9b595198
3
  size 45187904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a4b7cc957893b034dd1965ab615a89a1eb51894783bff903d1bd9aaa2710c3
3
  size 45187904
runs/Jan26_12-43-04_csr-95830.utdallas.edu/events.out.tfevents.1737916985.csr-95830.utdallas.edu.3626339.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44066cc04cffc0560d296a7c26d28a21468155f341b72ae666a69e41d6e6d08e
3
+ size 11005
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2924a0b81bfff975a1fa886934e7ec1384d072f55ef3970600ed925711351103
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01d57a5481c61edbe6b7241ad406eee47dbfc5ffca497d9e4ec994f41b5f42e
3
  size 6200