Model save
Browse files- README.md +2 -1
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -39,7 +39,8 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 8
|
41 |
- total_train_batch_size: 64
|
42 |
-
- optimizer: Use
|
|
|
43 |
- lr_scheduler_type: linear
|
44 |
- lr_scheduler_warmup_steps: 3
|
45 |
- num_epochs: 5
|
|
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 8
|
41 |
- total_train_batch_size: 64
|
42 |
+
- optimizer: Use adafactor and the args are:
|
43 |
+
No additional optimizer arguments
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 3
|
46 |
- num_epochs: 5
|
adapter_config.json
CHANGED
@@ -23,13 +23,13 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"up_proj",
|
27 |
"q_proj",
|
28 |
-
"gate_proj",
|
29 |
-
"v_proj",
|
30 |
"down_proj",
|
|
|
|
|
|
|
31 |
"k_proj",
|
32 |
-
"
|
33 |
],
|
34 |
"task_type": null,
|
35 |
"use_dora": true,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
|
|
26 |
"q_proj",
|
|
|
|
|
27 |
"down_proj",
|
28 |
+
"o_proj",
|
29 |
+
"up_proj",
|
30 |
+
"v_proj",
|
31 |
"k_proj",
|
32 |
+
"gate_proj"
|
33 |
],
|
34 |
"task_type": null,
|
35 |
"use_dora": true,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 51802928
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7604aa0809418cc069c50fd77a143bbb8c55a624d6216665ae4bad02ab8c9fe
|
3 |
size 51802928
|
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 sha256:8203a22f3e66520618cca01e78352bfd205178151b83a29535de51ce851622ed
|
3 |
size 5240
|