Commit
•
e0433cb
1
Parent(s):
2f9d976
chuonghoang/LoRA-public-service
Browse files- README.md +5 -1
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- tokenizer.json +6 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -42,7 +42,11 @@ The following hyperparameters were used during training:
|
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: constant
|
| 44 |
- lr_scheduler_warmup_ratio: 0.03
|
| 45 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
### Framework versions
|
| 48 |
|
|
|
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: constant
|
| 44 |
- lr_scheduler_warmup_ratio: 0.03
|
| 45 |
+
- num_epochs: 1
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
|
| 51 |
### Framework versions
|
| 52 |
|
adapter_config.json
CHANGED
|
@@ -19,11 +19,11 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"v_proj",
|
| 23 |
-
"
|
| 24 |
"o_proj",
|
| 25 |
-
"
|
| 26 |
-
"k_proj"
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM"
|
| 29 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"gate_proj",
|
| 23 |
"v_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
"o_proj",
|
| 26 |
+
"q_proj"
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM"
|
| 29 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369142184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b4295b891dbc49271959dbf0216fc582d6a022d9714e1c34c1efe139409883a
|
| 3 |
size 369142184
|
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 1024,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f53fef03aaa4dbc5228928ed1243cf2ee1cb6d9b7fed4a99d128bbc243f759f0
|
| 3 |
size 4664
|