Hugging Face's logo

SeanLee97
/
bellm-llama-7b-nli

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
SeanLee97 commited on
Commit
c8e1582
•
1 Parent(s): 6831fe5

Training in progress, step 200

Browse files
Files changed (7) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +2 -2
  3. angle.config +3 -3
  4. runs/Apr07_09-45-24_instance-20240226-074643/events.out.tfevents.1712483135.instance-20240226-074643.1028754.0 +2 -2
  5. runs/Apr07_10-49-45_instance-20240226-074643/events.out.tfevents.1712487001.instance-20240226-074643.1056587.0 +3 -0
  6. runs/Apr07_10-54-47_instance-20240226-074643/events.out.tfevents.1712487297.instance-20240226-074643.1068449.0 +3 -0
  7. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -9,13 +9,13 @@
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
12
- "lora_alpha": 16,
13
  "lora_dropout": 0.05,
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
- "r": 8,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
  "loftq_config": {},
12
+ "lora_alpha": 32,
13
  "lora_dropout": 0.05,
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
+ "r": 16,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:219ec5f4314d4b3a5aecfdaffc318888edf58a347fd1f4d32025dabf899ee152
3
- size 8405600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c38c2abdfca3b929c12ab474d22007c5a8dbc1e39d0928966714fdc36feeadfd
3
+ size 16794456
angle.config CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "model_name_or_path": "NousResearch/Llama-2-7b-hf",
3
- "max_length": 85,
4
  "model_kwargs": {},
5
  "pooling_strategy": "cls",
6
  "lora_config_kwargs": {
7
  "task_type": "CAUSAL_LM",
8
- "r": 8,
9
- "lora_alpha": 16,
10
  "lora_dropout": 0.05,
11
  "bias": "none"
12
  },
 
1
  {
2
  "model_name_or_path": "NousResearch/Llama-2-7b-hf",
3
+ "max_length": 80,
4
  "model_kwargs": {},
5
  "pooling_strategy": "cls",
6
  "lora_config_kwargs": {
7
  "task_type": "CAUSAL_LM",
8
+ "r": 16,
9
+ "lora_alpha": 32,
10
  "lora_dropout": 0.05,
11
  "bias": "none"
12
  },
runs/Apr07_09-45-24_instance-20240226-074643/events.out.tfevents.1712483135.instance-20240226-074643.1028754.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c570271218c3ae829306367fa885f08352af334ed3fcd519601e892638d1ba6a
3
- size 14954
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42a2d055594d758a3e5fc29a06091c71406f518af7f6859aeb1b852bc35b2f4
3
+ size 15308
runs/Apr07_10-49-45_instance-20240226-074643/events.out.tfevents.1712487001.instance-20240226-074643.1056587.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbafd3541014df5974b521b3a0a4db8dcdcb172c176decc0ce5ec744668e9620
3
+ size 5459
runs/Apr07_10-54-47_instance-20240226-074643/events.out.tfevents.1712487297.instance-20240226-074643.1068449.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:593ffb26a222b94912356903b05541a021da32f74a2a3a43c45b4ab39262d899
3
+ size 5248
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6db33d706f52b48b673761422b942d830dcc688166c0018b7e5be347b77c25d6
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf217563738fa69d3a9c66dcdbd1f1b153e692ca31ae94436a1183ca3c5553f
3
  size 5048