Hugging Face's logo

laohan
/
lau-3b-lora-full

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
laohan commited on
Commit
f837efe
•
1 Parent(s): 8eb84c7

laohan/lau-3b-lora-full

Browse files
Files changed (7) hide show
  1. README.md +3 -3
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Nov03_04-11-38_51b2cf5ead5c/events.out.tfevents.1730607126.51b2cf5ead5c.38099.0 +3 -0
  5. runs/Nov03_04-13-05_51b2cf5ead5c/events.out.tfevents.1730607201.51b2cf5ead5c.38099.1 +3 -0
  6. runs/Nov03_04-14-44_51b2cf5ead5c/events.out.tfevents.1730607286.51b2cf5ead5c.40639.0 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -34,11 +34,11 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.0005
37
- - train_batch_size: 1
38
  - eval_batch_size: 8
39
  - seed: 42
40
- - gradient_accumulation_steps: 4
41
- - total_train_batch_size: 4
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - num_epochs: 3
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.0005
37
+ - train_batch_size: 4
38
  - eval_batch_size: 8
39
  - seed: 42
40
+ - gradient_accumulation_steps: 2
41
+ - total_train_batch_size: 8
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - num_epochs: 3
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "o_proj",
24
- "q_proj",
25
  "v_proj",
26
- "k_proj"
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "k_proj",
 
24
  "v_proj",
25
+ "q_proj",
26
+ "o_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fec4283c5b1b767e8436e1204d11a9b4c643cc0c32a6da0407391fb0f32aa4c
3
  size 146830952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817b1f8e647086b3b94def02b0d18d1a171b839ee65cf969c1307db144dca06d
3
  size 146830952
runs/Nov03_04-11-38_51b2cf5ead5c/events.out.tfevents.1730607126.51b2cf5ead5c.38099.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa2e96b221af7dd1e53a0e7f22b3e9df9c11d9eb9a5b6db50179b35805ade4a
3
+ size 4184
runs/Nov03_04-13-05_51b2cf5ead5c/events.out.tfevents.1730607201.51b2cf5ead5c.38099.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa711d130d67ccec814f18d4096689eefff8add884768313855eece2615a6b3
3
+ size 4184
runs/Nov03_04-14-44_51b2cf5ead5c/events.out.tfevents.1730607286.51b2cf5ead5c.40639.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6307f4f19ea9e35038d6224ca1cfd6b5ca83b13f06d3854738e566768755e8f
3
+ size 190991
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:709ae5d89787a51e011b0291cdd18a8b80aeaf0a45e1c0d27760e28fa826bee6
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e2f1a510d8e4e4818a862b44724be3d2e85c24eff3e62f4194a23bd5bc45ec
3
  size 5176