Training in progress, step 48
Browse files
adapter_config.json
CHANGED
@@ -23,40 +23,40 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"38.self_attn.q_proj",
|
28 |
-
"36.self_attn.v_proj",
|
29 |
-
"model.layers.26.self_attn.q_proj",
|
30 |
-
"34.self_attn.v_proj",
|
31 |
-
"model.layers.28.self_attn.q_proj",
|
32 |
-
"model.layers.31.self_attn.q_proj",
|
33 |
-
"36.self_attn.q_proj",
|
34 |
-
"37.self_attn.q_proj",
|
35 |
"38.self_attn.v_proj",
|
36 |
"cross_attn.q_proj",
|
|
|
|
|
37 |
"39.self_attn.v_proj",
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
"model.layers.30.self_attn.q_proj",
|
42 |
-
"
|
|
|
43 |
"model.layers.27.self_attn.v_proj",
|
44 |
-
"37.self_attn.v_proj",
|
45 |
-
"model.layers.25.self_attn.v_proj",
|
46 |
"model.layers.28.self_attn.v_proj",
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"33.self_attn.v_proj",
|
50 |
"35.self_attn.q_proj",
|
51 |
-
"
|
52 |
-
"model.layers.24.self_attn.v_proj",
|
53 |
-
"34.self_attn.q_proj",
|
54 |
-
"33.self_attn.q_proj",
|
55 |
"model.layers.30.self_attn.v_proj",
|
56 |
-
"model.layers.
|
57 |
-
"
|
|
|
|
|
|
|
|
|
|
|
58 |
"model.layers.26.self_attn.v_proj",
|
59 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
],
|
61 |
"task_type": null,
|
62 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"model.layers.25.self_attn.q_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"38.self_attn.v_proj",
|
28 |
"cross_attn.q_proj",
|
29 |
+
"34.self_attn.q_proj",
|
30 |
+
"model.layers.25.self_attn.v_proj",
|
31 |
"39.self_attn.v_proj",
|
32 |
+
"32.self_attn.q_proj",
|
33 |
+
"33.self_attn.v_proj",
|
34 |
+
"37.self_attn.q_proj",
|
35 |
"model.layers.30.self_attn.q_proj",
|
36 |
+
"33.self_attn.q_proj",
|
37 |
+
"model.layers.24.self_attn.q_proj",
|
38 |
"model.layers.27.self_attn.v_proj",
|
|
|
|
|
39 |
"model.layers.28.self_attn.v_proj",
|
40 |
+
"36.self_attn.v_proj",
|
41 |
+
"38.self_attn.q_proj",
|
|
|
42 |
"35.self_attn.q_proj",
|
43 |
+
"cross_attn.v_proj",
|
|
|
|
|
|
|
44 |
"model.layers.30.self_attn.v_proj",
|
45 |
+
"model.layers.27.self_attn.q_proj",
|
46 |
+
"39.self_attn.q_proj",
|
47 |
+
"36.self_attn.q_proj",
|
48 |
+
"model.layers.31.self_attn.v_proj",
|
49 |
+
"model.layers.24.self_attn.v_proj",
|
50 |
+
"model.layers.28.self_attn.q_proj",
|
51 |
+
"model.layers.29.self_attn.q_proj",
|
52 |
"model.layers.26.self_attn.v_proj",
|
53 |
+
"35.self_attn.v_proj",
|
54 |
+
"model.layers.31.self_attn.q_proj",
|
55 |
+
"model.layers.26.self_attn.q_proj",
|
56 |
+
"37.self_attn.v_proj",
|
57 |
+
"32.self_attn.v_proj",
|
58 |
+
"34.self_attn.v_proj",
|
59 |
+
"model.layers.29.self_attn.v_proj"
|
60 |
],
|
61 |
"task_type": null,
|
62 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 143143408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d988ef7481766f3d91995cca8055b4a57f24ae49aca1abffa6c447dd8aeebc55
|
3 |
size 143143408
|
runs/Oct07_17-20-11_c091326edbce/events.out.tfevents.1728321626.c091326edbce.7104.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d539c385e901f82b7f048f2edb75c53ead2bb8f79bea070ddc66c8a0b9963e34
|
3 |
+
size 8280
|
runs/Oct07_17-22-02_c091326edbce/events.out.tfevents.1728321729.c091326edbce.8492.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aa66ce3dd6a75d16d7c86b2eb1d944feb29157e354b852d454e244c8d074fd9
|
3 |
+
size 9935
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f34115798420517404ffd523653f8b8275fbaffe2fc75273a436c9985943e71b
|
3 |
size 5240
|