End of training
Browse files- README.md +23 -22
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Accuracy: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -46,32 +46,33 @@ The following hyperparameters were used during training:
|
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
|
|
49 |
- training_steps: 200
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4238
|
24 |
+
- Accuracy: 0.7778
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
46 |
- seed: 42
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
+
- lr_scheduler_warmup_steps: 20
|
50 |
- training_steps: 200
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
56 |
+
| 0.7031 | 0.1087 | 10 | 0.6740 | 0.5752 |
|
57 |
+
| 0.6719 | 0.2174 | 20 | 0.6701 | 0.6046 |
|
58 |
+
| 0.6602 | 0.3261 | 30 | 0.6497 | 0.6601 |
|
59 |
+
| 0.6367 | 0.4348 | 40 | 0.6113 | 0.7059 |
|
60 |
+
| 0.6172 | 0.5435 | 50 | 0.5686 | 0.7320 |
|
61 |
+
| 0.5625 | 0.6522 | 60 | 0.5276 | 0.7451 |
|
62 |
+
| 0.5664 | 0.7609 | 70 | 0.4938 | 0.7451 |
|
63 |
+
| 0.5859 | 0.8696 | 80 | 0.4651 | 0.7712 |
|
64 |
+
| 0.5 | 0.9783 | 90 | 0.4560 | 0.7647 |
|
65 |
+
| 0.5898 | 1.0870 | 100 | 0.4560 | 0.7582 |
|
66 |
+
| 0.5664 | 1.1957 | 110 | 0.4459 | 0.7516 |
|
67 |
+
| 0.4648 | 1.3043 | 120 | 0.4387 | 0.7745 |
|
68 |
+
| 0.5117 | 1.4130 | 130 | 0.4306 | 0.7712 |
|
69 |
+
| 0.4219 | 1.5217 | 140 | 0.4239 | 0.7680 |
|
70 |
+
| 0.3828 | 1.6304 | 150 | 0.4314 | 0.7680 |
|
71 |
+
| 0.3789 | 1.7391 | 160 | 0.4319 | 0.7647 |
|
72 |
+
| 0.3828 | 1.8478 | 170 | 0.4291 | 0.7680 |
|
73 |
+
| 0.3438 | 1.9565 | 180 | 0.4279 | 0.7745 |
|
74 |
+
| 0.3496 | 2.0652 | 190 | 0.4274 | 0.7712 |
|
75 |
+
| 0.3945 | 2.1739 | 200 | 0.4238 | 0.7778 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -25,13 +25,13 @@
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
-
"gate_proj",
|
29 |
-
"k_proj",
|
30 |
"o_proj",
|
31 |
-
"
|
32 |
-
"v_proj",
|
33 |
"q_proj",
|
34 |
-
"up_proj"
|
|
|
|
|
|
|
35 |
],
|
36 |
"task_type": "SEQ_CLS",
|
37 |
"use_dora": false,
|
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
|
|
|
|
28 |
"o_proj",
|
29 |
+
"k_proj",
|
|
|
30 |
"q_proj",
|
31 |
+
"up_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"v_proj",
|
34 |
+
"down_proj"
|
35 |
],
|
36 |
"task_type": "SEQ_CLS",
|
37 |
"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 39260648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1830e519b9fb4dfa4e4c42a3a24e90246f11070dd81e5207fe8bb2b6b993a858
|
3 |
size 39260648
|
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 sha256:9d5fe4c47db0ef08955bd7d9219f1ad59a76a9ba1728b459dff4c3c272321f78
|
3 |
size 5240
|