sayanbanerjee32
commited on
Commit
•
49cf445
1
Parent(s):
ce9b8ce
End of training
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:------:|:----:|:---------------:|
|
55 |
-
| 0.
|
56 |
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
-
- PEFT 0.13.
|
61 |
-
- Transformers 4.45.
|
62 |
- Pytorch 2.4.1+cu121
|
63 |
- Datasets 3.0.1
|
64 |
-
- Tokenizers 0.20.
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1606
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 0.1688 | 0.3704 | 50 | 0.1606 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
+
- PEFT 0.13.2
|
61 |
+
- Transformers 4.45.2
|
62 |
- Pytorch 2.4.1+cu121
|
63 |
- Datasets 3.0.1
|
64 |
+
- Tokenizers 0.20.1
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
"k_proj",
|
|
|
25 |
"v_proj",
|
|
|
26 |
"up_proj",
|
27 |
-
"
|
28 |
-
"gate_proj",
|
29 |
-
"q_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
"k_proj",
|
25 |
+
"gate_proj",
|
26 |
"v_proj",
|
27 |
+
"q_proj",
|
28 |
"up_proj",
|
29 |
+
"down_proj"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 35669232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b08bd427dd3b517563d30ef20f8780a6bbbc694d3367972912dc00863c0e8651
|
3 |
size 35669232
|
runs/Oct17_02-03-31_09c52a70180b/events.out.tfevents.1729130616.09c52a70180b.560.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec6eab9cb638974a8417148c74cadbdc1e66fca4e7816b1456b035fd53b8d52e
|
3 |
+
size 10390
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:304cd4f1a5efc0e934bfadb4e5545be57d68d0a473517f5bb74491ecd082399b
|
3 |
size 5560
|