sv469/phi-2_finetuned
Browse files- README.md +6 -8
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- training_args.bin +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 [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -44,18 +44,16 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 2
|
47 |
-
- training_steps:
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-------:|:----:|:---------------:|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.0601 | 23.2558 | 250 | 0.1641 |
|
58 |
-
| 0.0483 | 27.9070 | 300 | 0.1627 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1810
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 2
|
47 |
+
- training_steps: 200
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-------:|:----:|:---------------:|
|
53 |
+
| 0.9443 | 4.6512 | 50 | 0.3824 |
|
54 |
+
| 0.2665 | 9.3023 | 100 | 0.2402 |
|
55 |
+
| 0.1542 | 13.9535 | 150 | 0.1915 |
|
56 |
+
| 0.1077 | 18.6047 | 200 | 0.1810 |
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
-
"k_proj",
|
25 |
"v_proj",
|
26 |
-
"
|
|
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"v_proj",
|
24 |
+
"k_proj",
|
25 |
+
"dense",
|
26 |
+
"q_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"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 83920464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8398c55eddd79fdfae52a476cc61b5da86fc9356fa61d771456a6e45aafa8f8
|
3 |
size 83920464
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daad53ab6a86dec224473c87f14c517588246fbec08b222e8294552c4709945c
|
3 |
size 5112
|