Training in progress, step 200
Browse files
adapter_config.json
CHANGED
@@ -16,17 +16,17 @@
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"v_proj",
|
25 |
"down_proj",
|
|
|
|
|
26 |
"up_proj",
|
27 |
"gate_proj",
|
28 |
-
"o_proj"
|
29 |
-
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 4,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"v_proj",
|
24 |
"down_proj",
|
25 |
+
"q_proj",
|
26 |
+
"k_proj",
|
27 |
"up_proj",
|
28 |
"gate_proj",
|
29 |
+
"o_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b07e46ceafc5ca884620b28184100a8cf5418324ebce9c8d025490676298790
|
3 |
+
size 20826816
|
runs/Nov05_17-06-45_bdc7b94c2463/events.out.tfevents.1730826425.bdc7b94c2463.911.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b883ebfaf136d32db21da2444709a136bf5d6febb3aee002b141ad4e67e1fd92
|
3 |
+
size 5732
|
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:fdff211728531e3c4c21de81cbf8ad6028b702e710cbd2d8ecd9c921a2cb3f1a
|
3 |
size 5240
|