Commit
•
f13d0e9
1
Parent(s):
db00304
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 |
|
|
@@ -36,25 +36,31 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.0002
|
| 39 |
-
- train_batch_size:
|
| 40 |
-
- eval_batch_size:
|
| 41 |
- seed: 42
|
| 42 |
- gradient_accumulation_steps: 4
|
| 43 |
-
- total_train_batch_size:
|
| 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.
|
| 55 |
-
| 4.
|
| 56 |
-
|
|
| 57 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
|
| 60 |
### 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: 2.3976
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
- seed: 42
|
| 42 |
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 4
|
| 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: 10
|
| 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 |
+
| 4.0195 | 1.8824 | 8 | 3.3893 |
|
| 56 |
+
| 3.2322 | 2.8235 | 12 | 3.2363 |
|
| 57 |
+
| 2.0625 | 4.0 | 17 | 3.0555 |
|
| 58 |
+
| 2.2884 | 4.9412 | 21 | 2.9109 |
|
| 59 |
+
| 2.1576 | 5.8824 | 25 | 2.7795 |
|
| 60 |
+
| 2.0546 | 6.8235 | 29 | 2.6220 |
|
| 61 |
+
| 1.5652 | 8.0 | 34 | 2.4955 |
|
| 62 |
+
| 1.8893 | 8.9412 | 38 | 2.4207 |
|
| 63 |
+
| 1.6427 | 9.4118 | 40 | 2.3976 |
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
runs/May10_11-40-33_186255fb755c/events.out.tfevents.1715341645.186255fb755c.885.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eb04415b8f93e26b2cf06f5ce9f98cdcb4297feb282ae5a01f759cb9660fc40
|
| 3 |
+
size 354
|