DariaaaS/9test-ft
Browse files- README.md +6 -17
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,12 @@ 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 the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
-
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -47,22 +52,6 @@ The following hyperparameters were used during training:
|
|
47 |
- num_epochs: 10
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
-
### Training results
|
51 |
-
|
52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
-
|:-------------:|:------:|:----:|:---------------:|
|
54 |
-
| 1.9139 | 0.9991 | 794 | 1.8822 |
|
55 |
-
| 1.8456 | 1.9994 | 1589 | 1.8719 |
|
56 |
-
| 1.8174 | 2.9997 | 2384 | 1.8706 |
|
57 |
-
| 1.7946 | 4.0 | 3179 | 1.8729 |
|
58 |
-
| 1.7776 | 4.9991 | 3973 | 1.8769 |
|
59 |
-
| 1.7587 | 5.9994 | 4768 | 1.8817 |
|
60 |
-
| 1.7447 | 6.9997 | 5563 | 1.8872 |
|
61 |
-
| 1.733 | 8.0 | 6358 | 1.8913 |
|
62 |
-
| 1.7246 | 8.9991 | 7152 | 1.8959 |
|
63 |
-
| 1.714 | 9.9906 | 7940 | 1.8982 |
|
64 |
-
|
65 |
-
|
66 |
### Framework versions
|
67 |
|
68 |
- PEFT 0.10.0
|
|
|
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 the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- eval_loss: 2.2801
|
20 |
+
- eval_runtime: 2283.0172
|
21 |
+
- eval_samples_per_second: 4.671
|
22 |
+
- eval_steps_per_second: 1.168
|
23 |
+
- epoch: 1.9998
|
24 |
+
- step: 5332
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
52 |
- num_epochs: 10
|
53 |
- mixed_precision_training: Native AMP
|
54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
### Framework versions
|
56 |
|
57 |
- PEFT 0.10.0
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8397056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d4030cb64427de011fe577b46daf97ec11b9fa5451d2d8b749c3c6ae508f8f7
|
3 |
size 8397056
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e118e15ded9fcb6949ebe40d61d5783c7d620789190b6bb169d0ac7dc5fca1e5
|
3 |
size 4984
|