Training in progress, epoch 1
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"layers_pattern": null,
|
| 15 |
"layers_to_transform": null,
|
| 16 |
"loftq_config": {},
|
| 17 |
-
"lora_alpha":
|
| 18 |
"lora_dropout": 0.1,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
|
@@ -30,9 +30,9 @@
|
|
| 30 |
"scheduler_verbose": true,
|
| 31 |
"scheduler_verbose_interval": 100,
|
| 32 |
"target_modules": [
|
| 33 |
-
"query",
|
| 34 |
"value",
|
| 35 |
"key",
|
|
|
|
| 36 |
"dense"
|
| 37 |
],
|
| 38 |
"task_type": null,
|
|
|
|
| 14 |
"layers_pattern": null,
|
| 15 |
"layers_to_transform": null,
|
| 16 |
"loftq_config": {},
|
| 17 |
+
"lora_alpha": 32,
|
| 18 |
"lora_dropout": 0.1,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
|
|
|
| 30 |
"scheduler_verbose": true,
|
| 31 |
"scheduler_verbose_interval": 100,
|
| 32 |
"target_modules": [
|
|
|
|
| 33 |
"value",
|
| 34 |
"key",
|
| 35 |
+
"query",
|
| 36 |
"dense"
|
| 37 |
],
|
| 38 |
"task_type": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 33056140
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de989e660372e26a9c11dcdf729cb66192373e8df5bc9b4a3a68b114c09abe3f
|
| 3 |
size 33056140
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:923470c4af94bef989d54ed0720230ceb355ed87a0f08e560e43df41cde63c4f
|
| 3 |
size 5304
|