Commit
•
2c529fc
1
Parent(s):
db00bfa
msahabudinov/code-finetuning
Browse files- README.md +16 -0
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- tokenizer.json +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 |
# finetuned
|
| 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 an unknown dataset.
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -46,6 +48,20 @@ The following hyperparameters were used during training:
|
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
- num_epochs: 3
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- PEFT 0.13.0
|
|
|
|
| 17 |
# finetuned
|
| 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 an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2803
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
- num_epochs: 3
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| 0.5282 | 0.3410 | 100 | 0.4418 |
|
| 56 |
+
| 0.3992 | 0.6820 | 200 | 0.3800 |
|
| 57 |
+
| 0.3324 | 1.0230 | 300 | 0.3341 |
|
| 58 |
+
| 0.3127 | 1.3640 | 400 | 0.3147 |
|
| 59 |
+
| 0.2591 | 1.7050 | 500 | 0.2895 |
|
| 60 |
+
| 0.2621 | 2.0460 | 600 | 0.2926 |
|
| 61 |
+
| 0.2195 | 2.3870 | 700 | 0.2826 |
|
| 62 |
+
| 0.2225 | 2.7280 | 800 | 0.2803 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
- PEFT 0.13.0
|
adapter_config.json
CHANGED
|
@@ -20,10 +20,10 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"qkv_proj",
|
| 24 |
"o_proj",
|
| 25 |
-
"
|
| 26 |
-
"
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"o_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"qkv_proj",
|
| 26 |
+
"gate_up_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 100697728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b523e890d7f5302eb870dbe1b02cbb5731d5484991a53e0bc5c490218d22e5a
|
| 3 |
size 100697728
|
tokenizer.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 4096,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7af4cc42e8b0584a851d5187bb443beb9126da174a17c0382267907794f6cff6
|
| 3 |
size 5432
|