Training in progress, step 200
Browse files- adapter_config.json +7 -7
- adapter_model.safetensors +2 -2
- angle.config +8 -8
- runs/Apr07_00-26-42_instance-20240226-074643/events.out.tfevents.1712449610.instance-20240226-074643.770748.0 +3 -0
- runs/Apr07_00-31-26_instance-20240226-074643/events.out.tfevents.1712449891.instance-20240226-074643.771883.0 +3 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -9,23 +9,23 @@
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
-
"lora_alpha":
|
13 |
-
"lora_dropout": 0.
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
-
"r":
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"v_proj",
|
23 |
"o_proj",
|
24 |
-
"up_proj",
|
25 |
-
"gate_proj",
|
26 |
"down_proj",
|
|
|
27 |
"q_proj",
|
28 |
-
"
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
+
"lora_alpha": 128,
|
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": 256,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"o_proj",
|
|
|
|
|
23 |
"down_proj",
|
24 |
+
"v_proj",
|
25 |
"q_proj",
|
26 |
+
"up_proj",
|
27 |
+
"k_proj",
|
28 |
+
"gate_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5035f7603660327c80afe44b8db0897e7246e56ef790ea3975a56ed11fcefe0
|
3 |
+
size 2558587064
|
angle.config
CHANGED
@@ -1,22 +1,22 @@
|
|
1 |
{
|
2 |
"model_name_or_path": "NousResearch/Llama-2-7b-hf",
|
3 |
-
"max_length":
|
4 |
"model_kwargs": {},
|
5 |
"pooling_strategy": "cls",
|
6 |
"lora_config_kwargs": {
|
7 |
"task_type": "CAUSAL_LM",
|
8 |
-
"r":
|
9 |
-
"lora_alpha":
|
10 |
-
"lora_dropout": 0.
|
11 |
"bias": "none",
|
12 |
"target_modules": [
|
13 |
-
"gate_proj",
|
14 |
-
"up_proj",
|
15 |
-
"v_proj",
|
16 |
"o_proj",
|
17 |
"down_proj",
|
|
|
18 |
"q_proj",
|
19 |
-
"
|
|
|
|
|
20 |
]
|
21 |
},
|
22 |
"apply_lora": 1
|
|
|
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": 256,
|
9 |
+
"lora_alpha": 128,
|
10 |
+
"lora_dropout": 0.1,
|
11 |
"bias": "none",
|
12 |
"target_modules": [
|
|
|
|
|
|
|
13 |
"o_proj",
|
14 |
"down_proj",
|
15 |
+
"v_proj",
|
16 |
"q_proj",
|
17 |
+
"up_proj",
|
18 |
+
"k_proj",
|
19 |
+
"gate_proj"
|
20 |
]
|
21 |
},
|
22 |
"apply_lora": 1
|
runs/Apr07_00-26-42_instance-20240226-074643/events.out.tfevents.1712449610.instance-20240226-074643.770748.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46138e74cb0a066e2363c8b26e178a84d17f0950f3ba77b376718ab6783862b3
|
3 |
+
size 5207
|
runs/Apr07_00-31-26_instance-20240226-074643/events.out.tfevents.1712449891.instance-20240226-074643.771883.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c0a0ba9d62751fb0d7f0cc2b1fc0f9d8072f7b3031d125f6c4598cdc9855413
|
3 |
+
size 5625
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c2577505af9b29b7012ddd9a76f62f9fe8eca926a717a53eb9a61213f3b8ce2
|
3 |
size 5048
|