clement-cvll
commited on
Commit
•
ccd2639
1
Parent(s):
8ca6bff
End of training
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 [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,24 +39,26 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate: 0.
|
43 |
- train_batch_size: 4
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.3
|
49 |
-
- num_epochs:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
-
| No log | 1.0 |
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
|
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2368
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0005
|
43 |
- train_batch_size: 4
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: cosine
|
48 |
- lr_scheduler_warmup_ratio: 0.3
|
49 |
+
- num_epochs: 7
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| No log | 1.0 | 6 | 1.2601 |
|
56 |
+
| 1.906 | 2.0 | 12 | 0.7329 |
|
57 |
+
| 1.906 | 3.0 | 18 | 0.4273 |
|
58 |
+
| 0.9496 | 4.0 | 24 | 0.2872 |
|
59 |
+
| 0.7822 | 5.0 | 30 | 0.2423 |
|
60 |
+
| 0.7822 | 6.0 | 36 | 0.2370 |
|
61 |
+
| 0.6482 | 7.0 | 42 | 0.2368 |
|
62 |
|
63 |
|
64 |
### Framework versions
|