End of training
Browse files- README.md +11 -11
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 5.
|
51 |
-
| 3.
|
52 |
-
| 1.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.3085
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 5.7293 | 1.0 | 30 | 4.6146 |
|
51 |
+
| 3.3709 | 2.0 | 60 | 2.0158 |
|
52 |
+
| 1.382 | 3.0 | 90 | 0.7932 |
|
53 |
+
| 0.8337 | 4.0 | 120 | 0.5675 |
|
54 |
+
| 0.6557 | 5.0 | 150 | 0.4715 |
|
55 |
+
| 0.5561 | 6.0 | 180 | 0.4106 |
|
56 |
+
| 0.5042 | 7.0 | 210 | 0.3627 |
|
57 |
+
| 0.4905 | 8.0 | 240 | 0.3346 |
|
58 |
+
| 0.4602 | 9.0 | 270 | 0.3145 |
|
59 |
+
| 0.39 | 10.0 | 300 | 0.3085 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -23,8 +23,8 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": "SEQ_2_SEQ_LM",
|
30 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"q",
|
27 |
+
"v"
|
28 |
],
|
29 |
"task_type": "SEQ_2_SEQ_LM",
|
30 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6655648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55df64e77ed208b2c2837230afa689a8fdf6b275ddd3e80b8ba86500d6188eb4
|
3 |
size 6655648
|