Training in progress, epoch 0
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -12,7 +12,7 @@
|
|
12 |
"layers_pattern": null,
|
13 |
"layers_to_transform": null,
|
14 |
"loftq_config": {},
|
15 |
-
"lora_alpha":
|
16 |
"lora_dropout": 0.1,
|
17 |
"megatron_config": null,
|
18 |
"megatron_core": "megatron.core",
|
@@ -20,16 +20,16 @@
|
|
20 |
"classifier"
|
21 |
],
|
22 |
"peft_type": "LORA",
|
23 |
-
"r":
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
-
"
|
28 |
-
"
|
29 |
],
|
30 |
"task_type": null,
|
31 |
"use_base_model": true,
|
32 |
-
"use_bias":
|
33 |
"use_dora": false,
|
34 |
"use_rslora": false
|
35 |
}
|
|
|
12 |
"layers_pattern": null,
|
13 |
"layers_to_transform": null,
|
14 |
"loftq_config": {},
|
15 |
+
"lora_alpha": 64,
|
16 |
"lora_dropout": 0.1,
|
17 |
"megatron_config": null,
|
18 |
"megatron_core": "megatron.core",
|
|
|
20 |
"classifier"
|
21 |
],
|
22 |
"peft_type": "LORA",
|
23 |
+
"r": 64,
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
+
"value",
|
28 |
+
"query"
|
29 |
],
|
30 |
"task_type": null,
|
31 |
"use_base_model": true,
|
32 |
+
"use_bias": true,
|
33 |
"use_dora": false,
|
34 |
"use_rslora": false
|
35 |
}
|
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 sha256:96275cd0dca76d30f72e057325cb25c7de8568d4fd814c844fe28384be504c16
|
3 |
+
size 9841620
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb3c050272040b71d23103452318228cc448d2a3f5ac8dda9e443e4b272d07b4
|
3 |
size 4984
|