SleepyGorilla
commited on
Commit
•
c782460
1
Parent(s):
bcb7b63
SleepyGorilla/Mistral_7B
Browse files
README.md
CHANGED
@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen: 0.
|
23 |
-
- Rewards/rejected: -
|
24 |
-
- Rewards/accuracies: 0.
|
25 |
-
- Rewards/margins:
|
26 |
-
- Logps/rejected: -
|
27 |
-
- Logps/chosen: -
|
28 |
-
- Logits/rejected: -
|
29 |
-
- Logits/chosen: -2.
|
30 |
|
31 |
## Model description
|
32 |
|
@@ -59,11 +59,11 @@ The following hyperparameters were used during training:
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
61 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
|
68 |
|
69 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [TheBloke/OpenHermes-2-Mistral-7B-GPTQ](https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GPTQ) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4618
|
22 |
+
- Rewards/chosen: -0.7871
|
23 |
+
- Rewards/rejected: -6.6095
|
24 |
+
- Rewards/accuracies: 0.9375
|
25 |
+
- Rewards/margins: 5.8223
|
26 |
+
- Logps/rejected: -220.7533
|
27 |
+
- Logps/chosen: -104.2417
|
28 |
+
- Logits/rejected: -1.9929
|
29 |
+
- Logits/chosen: -2.4654
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
61 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
62 |
+
| 0.5633 | 0.0 | 10 | 0.5184 | 0.0815 | -0.3179 | 1.0 | 0.3995 | -157.8381 | -95.5550 | -2.1002 | -2.5591 |
|
63 |
+
| 0.3936 | 0.0 | 20 | 0.2875 | 0.2689 | -1.1716 | 1.0 | 1.4404 | -166.3746 | -93.6817 | -2.0675 | -2.5604 |
|
64 |
+
| 0.2132 | 0.0 | 30 | 0.2000 | 0.0966 | -2.8012 | 0.9375 | 2.8977 | -182.6702 | -95.4047 | -2.0286 | -2.5520 |
|
65 |
+
| 0.034 | 0.0 | 40 | 0.4078 | -0.5324 | -5.2327 | 0.9375 | 4.7003 | -206.9856 | -101.6947 | -2.0143 | -2.4945 |
|
66 |
+
| 0.0665 | 0.0 | 50 | 0.4618 | -0.7871 | -6.6095 | 0.9375 | 5.8223 | -220.7533 | -104.2417 | -1.9929 | -2.4654 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13648432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ed8c23e952bf13275720438d5d8d1c6a13442e0255a60ba3d8d314d209927e0
|
3 |
size 13648432
|
runs/Mar16_18-59-36_f0843e752b6c/events.out.tfevents.1710615755.f0843e752b6c.971.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0d94056905effb0affb7732cd532de2a1f24b99e4217269ca04772ba8aad093
|
3 |
+
size 13334
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4475
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b990e32d43a9f3ad091100b93ca5b758b676985de0fb98bd08c011f72e533bc
|
3 |
size 4475
|