Training in progress, step 900
Browse files- adapter_config.json +1 -6
- adapter_model.safetensors +2 -2
- angle.config +2 -11
- runs/Apr06_09-00-14_instance-20240226-074643/events.out.tfevents.1712394019.instance-20240226-074643.346988.0 +3 -0
- runs/Apr06_09-03-57_instance-20240226-074643/events.out.tfevents.1712394241.instance-20240226-074643.348421.0 +3 -0
- runs/Apr06_09-05-03_instance-20240226-074643/events.out.tfevents.1712394307.instance-20240226-074643.349055.0 +3 -0
- runs/Apr06_09-11-54_instance-20240226-074643/events.out.tfevents.1712394722.instance-20240226-074643.349954.0 +3 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -20,12 +20,7 @@
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"q_proj",
|
23 |
-
"
|
24 |
-
"k_proj",
|
25 |
-
"up_proj",
|
26 |
-
"o_proj",
|
27 |
-
"v_proj",
|
28 |
-
"gate_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"q_proj",
|
23 |
+
"v_proj"
|
|
|
|
|
|
|
|
|
|
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"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 sha256:10734a8d0802bc17030ab4cef15c7956a05524b99aba77978557ed181c5e4ccd
|
3 |
+
size 67126104
|
angle.config
CHANGED
@@ -1,6 +1,6 @@
|
|
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": {
|
@@ -8,16 +8,7 @@
|
|
8 |
"r": 64,
|
9 |
"lora_alpha": 8,
|
10 |
"lora_dropout": 0.05,
|
11 |
-
"bias": "none"
|
12 |
-
"target_modules": [
|
13 |
-
"q_proj",
|
14 |
-
"k_proj",
|
15 |
-
"down_proj",
|
16 |
-
"up_proj",
|
17 |
-
"o_proj",
|
18 |
-
"v_proj",
|
19 |
-
"gate_proj"
|
20 |
-
]
|
21 |
},
|
22 |
"apply_lora": 1
|
23 |
}
|
|
|
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": {
|
|
|
8 |
"r": 64,
|
9 |
"lora_alpha": 8,
|
10 |
"lora_dropout": 0.05,
|
11 |
+
"bias": "none"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
},
|
13 |
"apply_lora": 1
|
14 |
}
|
runs/Apr06_09-00-14_instance-20240226-074643/events.out.tfevents.1712394019.instance-20240226-074643.346988.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d979bbb4d008c801b02c70bd9be223dabfbcc3de372794ff07e0594acd81c53
|
3 |
+
size 4765
|
runs/Apr06_09-03-57_instance-20240226-074643/events.out.tfevents.1712394241.instance-20240226-074643.348421.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd9f5f5b28616859881391d68e1e25932960d35892911685b069622ba83bf001
|
3 |
+
size 5114
|
runs/Apr06_09-05-03_instance-20240226-074643/events.out.tfevents.1712394307.instance-20240226-074643.349055.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1e7b761bd629f9b67b4a42fbbdc5f828db8c490b8c9109cddeded70e6035c16
|
3 |
+
size 4766
|
runs/Apr06_09-11-54_instance-20240226-074643/events.out.tfevents.1712394722.instance-20240226-074643.349954.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5e0a5a39c817c6071bae54bf500b0796762071f5fbb9b5fa0cd95d96a0235c4
|
3 |
+
size 6660
|
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 sha256:33924a2423a1885e38b3edb81fcbb96a6dbed772cf268f0f1bcbb0904cfd0602
|
3 |
size 5048
|