Commit
•
fb9e1b0
1
Parent(s):
8f56629
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 [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -44,23 +44,32 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 2
|
47 |
-
- num_epochs:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch
|
53 |
-
|
54 |
-
| 4.1739 | 0.9412
|
55 |
-
| 4.
|
56 |
-
| 3.
|
57 |
-
| 2.
|
58 |
-
| 2.
|
59 |
-
| 2.
|
60 |
-
|
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
|
66 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.8239
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 2
|
47 |
+
- num_epochs: 20
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
54 |
+
| 4.1739 | 0.9412 | 4 | 3.4659 |
|
55 |
+
| 4.0196 | 1.8824 | 8 | 3.3864 |
|
56 |
+
| 3.2283 | 2.8235 | 12 | 3.2071 |
|
57 |
+
| 2.0147 | 4.0 | 17 | 2.9738 |
|
58 |
+
| 2.2299 | 4.9412 | 21 | 2.7751 |
|
59 |
+
| 2.0711 | 5.8824 | 25 | 2.6203 |
|
60 |
+
| 1.946 | 6.8235 | 29 | 2.3797 |
|
61 |
+
| 1.4262 | 8.0 | 34 | 2.0694 |
|
62 |
+
| 1.6468 | 8.9412 | 38 | 1.8468 |
|
63 |
+
| 1.5549 | 9.8824 | 42 | 1.5932 |
|
64 |
+
| 1.4661 | 10.8235 | 46 | 1.3819 |
|
65 |
+
| 1.1079 | 12.0 | 51 | 1.2555 |
|
66 |
+
| 1.3114 | 12.9412 | 55 | 1.1306 |
|
67 |
+
| 1.2436 | 13.8824 | 59 | 1.0515 |
|
68 |
+
| 1.1965 | 14.8235 | 63 | 0.9581 |
|
69 |
+
| 0.9269 | 16.0 | 68 | 0.9277 |
|
70 |
+
| 1.1262 | 16.9412 | 72 | 0.8709 |
|
71 |
+
| 1.1054 | 17.8824 | 76 | 0.8343 |
|
72 |
+
| 0.8664 | 18.8235 | 80 | 0.8239 |
|
73 |
|
74 |
|
75 |
### Framework versions
|
runs/May10_12-00-23_186255fb755c/events.out.tfevents.1715343240.186255fb755c.10006.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:846cbb594d2e0b2a92355419c4361f89f2b7b936532ed7e646e88a5e90f8d2d9
|
3 |
+
size 354
|