Commit
•
ba3e928
1
Parent(s):
2da8c45
Training in progress, step 1000
Browse files
adapter_config.json
CHANGED
@@ -23,54 +23,54 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"model.decoder.layers.
|
|
|
27 |
"model.decoder.layers.1.self_attn.q_proj",
|
28 |
-
"model.decoder.layers.4.
|
29 |
-
"model.decoder.layers.
|
30 |
-
"model.decoder.layers.1.encoder_attn.v_proj",
|
31 |
-
"model.decoder.layers.9.encoder_attn.v_proj",
|
32 |
-
"model.decoder.layers.7.encoder_attn.v_proj",
|
33 |
"model.decoder.layers.10.self_attn.v_proj",
|
34 |
-
"model.decoder.layers.
|
35 |
-
"model.decoder.layers.0.self_attn.
|
36 |
-
"model.decoder.layers.5.self_attn.v_proj",
|
37 |
-
"model.decoder.layers.6.self_attn.v_proj",
|
38 |
-
"model.decoder.layers.6.encoder_attn.q_proj",
|
39 |
-
"model.decoder.layers.2.encoder_attn.v_proj",
|
40 |
"model.decoder.layers.8.self_attn.q_proj",
|
41 |
-
"model.decoder.layers.9.
|
|
|
|
|
42 |
"model.decoder.layers.3.self_attn.q_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
"model.decoder.layers.11.self_attn.v_proj",
|
44 |
-
"model.decoder.layers.1.self_attn.v_proj",
|
45 |
"model.decoder.layers.2.encoder_attn.q_proj",
|
46 |
-
"model.decoder.layers.11.self_attn.q_proj",
|
47 |
-
"model.decoder.layers.6.encoder_attn.v_proj",
|
48 |
-
"model.decoder.layers.2.self_attn.q_proj",
|
49 |
-
"model.decoder.layers.9.encoder_attn.q_proj",
|
50 |
-
"model.decoder.layers.10.encoder_attn.v_proj",
|
51 |
-
"model.decoder.layers.8.self_attn.v_proj",
|
52 |
-
"model.decoder.layers.11.encoder_attn.q_proj",
|
53 |
"model.decoder.layers.7.encoder_attn.q_proj",
|
54 |
-
"model.decoder.layers.5.self_attn.
|
|
|
|
|
55 |
"model.decoder.layers.8.encoder_attn.q_proj",
|
|
|
|
|
|
|
|
|
|
|
56 |
"model.decoder.layers.3.encoder_attn.q_proj",
|
57 |
-
"model.decoder.layers.
|
58 |
-
"model.decoder.layers.
|
|
|
|
|
|
|
|
|
59 |
"model.decoder.layers.2.self_attn.v_proj",
|
60 |
-
"model.decoder.layers.
|
61 |
-
"model.decoder.layers.5.encoder_attn.q_proj",
|
62 |
-
"model.decoder.layers.0.self_attn.q_proj",
|
63 |
-
"model.decoder.layers.10.self_attn.q_proj",
|
64 |
-
"model.decoder.layers.11.encoder_attn.v_proj",
|
65 |
-
"model.decoder.layers.10.encoder_attn.q_proj",
|
66 |
-
"model.decoder.layers.7.self_attn.q_proj",
|
67 |
-
"model.decoder.layers.3.encoder_attn.v_proj",
|
68 |
-
"model.decoder.layers.1.encoder_attn.q_proj",
|
69 |
-
"model.decoder.layers.4.self_attn.v_proj",
|
70 |
-
"model.decoder.layers.4.encoder_attn.q_proj",
|
71 |
"model.decoder.layers.5.encoder_attn.v_proj",
|
72 |
-
"model.decoder.layers.4.
|
73 |
-
"model.decoder.layers.
|
74 |
],
|
75 |
"task_type": null,
|
76 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"model.decoder.layers.10.self_attn.q_proj",
|
27 |
+
"model.decoder.layers.1.encoder_attn.q_proj",
|
28 |
"model.decoder.layers.1.self_attn.q_proj",
|
29 |
+
"model.decoder.layers.4.self_attn.v_proj",
|
30 |
+
"model.decoder.layers.3.encoder_attn.v_proj",
|
|
|
|
|
|
|
31 |
"model.decoder.layers.10.self_attn.v_proj",
|
32 |
+
"model.decoder.layers.10.encoder_attn.v_proj",
|
33 |
+
"model.decoder.layers.0.self_attn.q_proj",
|
|
|
|
|
|
|
|
|
34 |
"model.decoder.layers.8.self_attn.q_proj",
|
35 |
+
"model.decoder.layers.9.encoder_attn.v_proj",
|
36 |
+
"model.decoder.layers.8.encoder_attn.v_proj",
|
37 |
+
"model.decoder.layers.9.self_attn.v_proj",
|
38 |
"model.decoder.layers.3.self_attn.q_proj",
|
39 |
+
"model.decoder.layers.9.encoder_attn.q_proj",
|
40 |
+
"model.decoder.layers.0.encoder_attn.q_proj",
|
41 |
+
"model.decoder.layers.11.self_attn.q_proj",
|
42 |
+
"model.decoder.layers.4.self_attn.q_proj",
|
43 |
+
"model.decoder.layers.7.self_attn.v_proj",
|
44 |
+
"model.decoder.layers.0.self_attn.v_proj",
|
45 |
+
"model.decoder.layers.2.encoder_attn.v_proj",
|
46 |
+
"model.decoder.layers.6.encoder_attn.q_proj",
|
47 |
+
"model.decoder.layers.11.encoder_attn.v_proj",
|
48 |
+
"model.decoder.layers.10.encoder_attn.q_proj",
|
49 |
+
"model.decoder.layers.5.encoder_attn.q_proj",
|
50 |
"model.decoder.layers.11.self_attn.v_proj",
|
|
|
51 |
"model.decoder.layers.2.encoder_attn.q_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
"model.decoder.layers.7.encoder_attn.q_proj",
|
53 |
+
"model.decoder.layers.5.self_attn.v_proj",
|
54 |
+
"model.decoder.layers.6.self_attn.q_proj",
|
55 |
+
"model.decoder.layers.6.self_attn.v_proj",
|
56 |
"model.decoder.layers.8.encoder_attn.q_proj",
|
57 |
+
"model.decoder.layers.11.encoder_attn.q_proj",
|
58 |
+
"model.decoder.layers.7.self_attn.q_proj",
|
59 |
+
"model.decoder.layers.4.encoder_attn.v_proj",
|
60 |
+
"model.decoder.layers.0.encoder_attn.v_proj",
|
61 |
+
"model.decoder.layers.1.self_attn.v_proj",
|
62 |
"model.decoder.layers.3.encoder_attn.q_proj",
|
63 |
+
"model.decoder.layers.2.self_attn.q_proj",
|
64 |
+
"model.decoder.layers.5.self_attn.q_proj",
|
65 |
+
"model.decoder.layers.7.encoder_attn.v_proj",
|
66 |
+
"model.decoder.layers.8.self_attn.v_proj",
|
67 |
+
"model.decoder.layers.9.self_attn.q_proj",
|
68 |
+
"model.decoder.layers.6.encoder_attn.v_proj",
|
69 |
"model.decoder.layers.2.self_attn.v_proj",
|
70 |
+
"model.decoder.layers.1.encoder_attn.v_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
"model.decoder.layers.5.encoder_attn.v_proj",
|
72 |
+
"model.decoder.layers.4.encoder_attn.q_proj",
|
73 |
+
"model.decoder.layers.3.self_attn.v_proj"
|
74 |
],
|
75 |
"task_type": null,
|
76 |
"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 2372656
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:685233a349ad7a6cf1730a6653b290be929c8ffe220770019a1bbf4f4e9b2319
|
3 |
size 2372656
|
runs/Jul13_14-11-46_dc5a3487e29b/events.out.tfevents.1720879919.dc5a3487e29b.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f6652d6eaa1a27dd954324fb9caf5e9c7499aff4ae3331700264dfa8f18141d
|
3 |
+
size 15800
|
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 sha256:00b31526909fdcfa15f7feb9ab54e77748affe3723a4a1735cf9546f96668f00
|
3 |
size 5240
|