End of training
Browse files- README.md +8 -1
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,6 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# ft-google-gemma-2b-it-qlora
|
18 |
|
19 |
This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -43,11 +45,16 @@ The following hyperparameters were used during training:
|
|
43 |
- total_train_batch_size: 128
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: constant
|
46 |
-
- num_epochs:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
17 |
# ft-google-gemma-2b-it-qlora
|
18 |
|
19 |
This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 2.7355
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
45 |
- total_train_batch_size: 128
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: constant
|
48 |
+
- num_epochs: 10
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 0.1332 | 3.0 | 3 | 2.5378 |
|
56 |
+
| 0.0683 | 6.0 | 6 | 2.5858 |
|
57 |
+
| 0.0236 | 9.0 | 9 | 2.7355 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -22,13 +22,13 @@
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
-
"q_proj",
|
26 |
-
"gate_proj",
|
27 |
-
"v_proj",
|
28 |
"o_proj",
|
|
|
29 |
"down_proj",
|
|
|
30 |
"k_proj",
|
31 |
-
"
|
|
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
34 |
"use_dora": false,
|
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
|
|
|
|
|
|
25 |
"o_proj",
|
26 |
+
"up_proj",
|
27 |
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
"k_proj",
|
30 |
+
"v_proj",
|
31 |
+
"q_proj"
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
34 |
"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 4272785368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1306fc825bd6b4779454a9c73f3b63a6ec5b4c832cf30bb173fa1849e5b3e3e4
|
3 |
size 4272785368
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2387bc0ec1e091240f40e33e26537876055316d5030ebd4f152ea413ca6d9d0
|
3 |
size 4920
|