mistralai/mistral-instruct-generation_tr
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [malhajar/Mistral-7B-Instruct-v0.2-turkish](https://huggingface.co/malhajar/Mistral-7B-Instruct-v0.2-turkish) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:------:|:----:|:---------------:|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [malhajar/Mistral-7B-Instruct-v0.2-turkish](https://huggingface.co/malhajar/Mistral-7B-Instruct-v0.2-turkish) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0125
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:------:|:----:|:---------------:|
|
56 |
+
| 0.3706 | 0.1198 | 20 | 0.1194 |
|
57 |
+
| 0.0327 | 0.2395 | 40 | 0.0267 |
|
58 |
+
| 0.0231 | 0.3593 | 60 | 0.0182 |
|
59 |
+
| 0.0167 | 0.4790 | 80 | 0.0147 |
|
60 |
+
| 0.0155 | 0.5988 | 100 | 0.0125 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"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 27280152
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9eae570dc07c93f0a89858ad1ddadfa1466597b779d3798034c98087f01bd315
|
3 |
size 27280152
|
runs/Jun04_08-26-57_ca1fc2d8e9cc/events.out.tfevents.1717489683.ca1fc2d8e9cc.207.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9faf06433c64a8741fb0a3bea787c252d9c721822796ce2e0dc2d4855c691343
|
3 |
+
size 9105
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6f231e99809c7209e33afc43c300a85993ec0dfad320ef774c3c841ba22afdb
|
3 |
size 5112
|