minimini99
commited on
Commit
•
9d5c1be
1
Parent(s):
e125d7c
minimini99/phi3-lora-test
Browse files- README.md +8 -2
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -14,10 +14,12 @@ model-index:
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jongmin4422/Phi3-mini-ft-python-code/runs/
|
18 |
# phi-3-mini-LoRA
|
19 |
|
20 |
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -45,10 +47,14 @@ The following hyperparameters were used during training:
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_ratio: 0.1
|
48 |
-
- num_epochs:
|
49 |
|
50 |
### Training results
|
51 |
|
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jongmin4422/Phi3-mini-ft-python-code/runs/zwsclld3)
|
18 |
# phi-3-mini-LoRA
|
19 |
|
20 |
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.2828
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 100
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
56 |
+
| 1.8947 | 36.3636 | 100 | 1.3447 |
|
57 |
+
| 1.2021 | 72.7273 | 200 | 1.2828 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,12 +20,12 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
-
"k_proj",
|
25 |
"o_proj",
|
26 |
"gate_proj",
|
27 |
-
"down_proj",
|
28 |
"up_proj",
|
|
|
|
|
|
|
29 |
"v_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"o_proj",
|
24 |
"gate_proj",
|
|
|
25 |
"up_proj",
|
26 |
+
"k_proj",
|
27 |
+
"down_proj",
|
28 |
+
"q_proj",
|
29 |
"v_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17842848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b56250c1d445672e33739f90290fe3313d10728e8e71bd17e19af78b4e4d9dde
|
3 |
size 17842848
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63201426a51d343157d04f71be0c65aa11fe8df67638436bed9ff0f6ec6ddf2e
|
3 |
size 5368
|