Model save
Browse files- README.md +3 -3
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- tokenizer.json +6 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -34,15 +34,15 @@ More information needed
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 5e-05
|
37 |
-
- train_batch_size:
|
38 |
- eval_batch_size: 8
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 4
|
41 |
-
- total_train_batch_size:
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
- lr_scheduler_warmup_ratio: 0.3
|
45 |
-
- training_steps:
|
46 |
|
47 |
### Framework versions
|
48 |
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 5e-05
|
37 |
+
- train_batch_size: 1
|
38 |
- eval_batch_size: 8
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 4
|
41 |
+
- total_train_batch_size: 4
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
- lr_scheduler_warmup_ratio: 0.3
|
45 |
+
- training_steps: 3
|
46 |
|
47 |
### Framework versions
|
48 |
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"k_proj",
|
24 |
"down_proj",
|
25 |
-
"v_proj",
|
26 |
"q_proj",
|
27 |
-
"
|
28 |
-
"
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"o_proj",
|
|
|
23 |
"down_proj",
|
|
|
24 |
"q_proj",
|
25 |
+
"v_proj",
|
26 |
+
"up_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"k_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 50128536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d668afb71de6a1fd06fe8612ec0145bd1b1303631697f2507dc24393b2eafc3a
|
3 |
size 50128536
|
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 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b34b98b73ff1c6451c0e59f9268f354d99add9e59f3cf1166edf70ec5c5c6494
|
3 |
size 4792
|