Hugging Face's logo

SeanLee97
/
bellm-llama-7b-nli

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
SeanLee97 commited on
Commit
9ddce2f
•
1 Parent(s): 1ad1d30

Training in progress, step 100

Browse files
Files changed (7) hide show
  1. adapter_config.json +7 -4
  2. adapter_model.safetensors +1 -1
  3. angle.config +2 -11
  4. runs/Mar20_06-00-19_instance-20240226-074643/events.out.tfevents.1710914435.instance-20240226-074643.1717951.0 +3 -0
  5. runs/Mar20_06-08-17_instance-20240226-074643/events.out.tfevents.1710914902.instance-20240226-074643.1720334.0 +3 -0
  6. runs/Mar20_06-17-12_instance-20240226-074643/events.out.tfevents.1710915444.instance-20240226-074643.1721310.0 +3 -0
  7. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -13,19 +13,22 @@
13
  "lora_dropout": 0.1,
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
16
- "modules_to_save": null,
 
 
 
17
  "peft_type": "LORA",
18
  "r": 32,
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
  "o_proj",
23
- "up_proj",
24
  "q_proj",
25
- "gate_proj",
26
  "v_proj",
27
  "down_proj",
28
- "k_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
13
  "lora_dropout": 0.1,
14
  "megatron_config": null,
15
  "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "model.leaky_norm.weight",
18
+ "model.leaky_norm.bias"
19
+ ],
20
  "peft_type": "LORA",
21
  "r": 32,
22
  "rank_pattern": {},
23
  "revision": null,
24
  "target_modules": [
25
  "o_proj",
 
26
  "q_proj",
27
+ "up_proj",
28
  "v_proj",
29
  "down_proj",
30
+ "k_proj",
31
+ "gate_proj"
32
  ],
33
  "task_type": "CAUSAL_LM",
34
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dd4ab43d34335365c3d2c2da7338c2064353841b84384a4b88774ede36ed9d9
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97e91dac258a78f10a97fe127798224effeefb933e0e22269d7739939a2a4b5a
3
  size 319876032
angle.config CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "model_name_or_path": "NousResearch/Llama-2-7b-hf",
3
- "max_length": 75,
4
  "model_kwargs": {},
5
  "pooling_strategy": "cls",
6
  "lora_config_kwargs": {
@@ -8,16 +8,7 @@
8
  "r": 32,
9
  "lora_alpha": 32,
10
  "lora_dropout": 0.1,
11
- "bias": "none",
12
- "target_modules": [
13
- "up_proj",
14
- "down_proj",
15
- "o_proj",
16
- "k_proj",
17
- "q_proj",
18
- "gate_proj",
19
- "v_proj"
20
- ]
21
  },
22
  "apply_lora": 1
23
  }
 
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": {
 
8
  "r": 32,
9
  "lora_alpha": 32,
10
  "lora_dropout": 0.1,
11
+ "bias": "none"
 
 
 
 
 
 
 
 
 
12
  },
13
  "apply_lora": 1
14
  }
runs/Mar20_06-00-19_instance-20240226-074643/events.out.tfevents.1710914435.instance-20240226-074643.1717951.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147f4ee09782834b6ccdfc71476517a5b002bda534f6e7d0f59fa96e43ba9eab
3
+ size 5206
runs/Mar20_06-08-17_instance-20240226-074643/events.out.tfevents.1710914902.instance-20240226-074643.1720334.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84569d826fe0175ef3415048c14447df260baecf7ef582201b44e44f516c0fc
3
+ size 5206
runs/Mar20_06-17-12_instance-20240226-074643/events.out.tfevents.1710915444.instance-20240226-074643.1721310.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65073a830cca03025a6dce59bd9db4b73c85635fef8480e493aaa678154da56a
3
+ size 5413
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d1ec668db60c92c87a05e48fc9fe1710daf50d9e80e85d64642f142d395a524
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a17c613d3e0e22264379b569a7ef021e7162704a72661d8fc663d1e63e01d8e
3
  size 5048