Training in progress, step 100
Browse files
adapter_config.json
CHANGED
@@ -11,19 +11,21 @@
|
|
11 |
"loftq_config": {},
|
12 |
"lora_alpha": 256,
|
13 |
"lora_dropout": 0.1,
|
|
|
|
|
14 |
"modules_to_save": null,
|
15 |
"peft_type": "LORA",
|
16 |
"r": 64,
|
17 |
"rank_pattern": {},
|
18 |
"revision": null,
|
19 |
"target_modules": [
|
20 |
-
"
|
|
|
|
|
21 |
"up_proj",
|
22 |
"k_proj",
|
23 |
"gate_proj",
|
24 |
-
"
|
25 |
-
"o_proj",
|
26 |
-
"down_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM"
|
29 |
}
|
|
|
11 |
"loftq_config": {},
|
12 |
"lora_alpha": 256,
|
13 |
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"o_proj",
|
23 |
+
"q_proj",
|
24 |
+
"down_proj",
|
25 |
"up_proj",
|
26 |
"k_proj",
|
27 |
"gate_proj",
|
28 |
+
"v_proj"
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:714ab861b1da9a08669f6a2935a1259ef2fd0fd0e1f03b28101c6c84afb7a1da
|
3 |
size 671149168
|
runs/Dec01_04-04-25_a13ebef707de/events.out.tfevents.1701403511.a13ebef707de.26.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb2dcdc75fc8e788ac25e64dd006b281283ed662df40687e4886162a317f5217
|
3 |
+
size 20167
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ebf229ddba4252d671f8f8a0d00545c9d6a7a5fa05bd8853514efeaf8ef01a1
|
3 |
size 4283
|