JoseBambora
commited on
Commit
•
92d809b
1
Parent(s):
5021994
End of training
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 2.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 2.
|
55 |
-
|
|
56 |
-
| 1.
|
57 |
-
| 1.
|
58 |
|
59 |
|
60 |
### Framework versions
|
@@ -62,5 +62,5 @@ The following hyperparameters were used during training:
|
|
62 |
- PEFT 0.7.1
|
63 |
- Transformers 4.36.1
|
64 |
- Pytorch 2.0.0+cu117
|
65 |
-
- Datasets 2.
|
66 |
- Tokenizers 0.15.2
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 2.1395
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 2.0547 | 1.0 | 50 | 2.1017 |
|
55 |
+
| 2.0079 | 2.0 | 100 | 2.1056 |
|
56 |
+
| 1.8627 | 3.0 | 150 | 2.1294 |
|
57 |
+
| 1.7794 | 4.0 | 200 | 2.1395 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
62 |
- PEFT 0.7.1
|
63 |
- Transformers 4.36.1
|
64 |
- Pytorch 2.0.0+cu117
|
65 |
+
- Datasets 2.18.0
|
66 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb2eec4e61233f706b90b06d59b367cf4d593dfc5fb515bbbd23d66849b4b5a1
|
3 |
size 109069176
|
runs/May05_15-46-05_18121608d80e/events.out.tfevents.1714923967.18121608d80e.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9469140027301082ec006f7245fd63860bea0c4925b90f155672d7cbc25edbcb
|
3 |
+
size 7447
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d76bd84bef0a03b050a80b036cc627d9396212fe707f91463fb1b7abba6fed16
|
3 |
size 4283
|