End of training
Browse files
README.md
CHANGED
|
@@ -20,13 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
-
|
| 24 |
-
-
|
| 25 |
-
- eval_runtime: 21.3878
|
| 26 |
-
- eval_samples_per_second: 18.375
|
| 27 |
-
- eval_steps_per_second: 4.629
|
| 28 |
-
- epoch: 1.2974
|
| 29 |
-
- step: 3209
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
|
@@ -45,7 +40,7 @@ More information needed
|
|
| 45 |
### Training hyperparameters
|
| 46 |
|
| 47 |
The following hyperparameters were used during training:
|
| 48 |
-
- learning_rate:
|
| 49 |
- train_batch_size: 4
|
| 50 |
- eval_batch_size: 4
|
| 51 |
- seed: 42
|
|
@@ -53,10 +48,27 @@ The following hyperparameters were used during training:
|
|
| 53 |
- total_train_batch_size: 16
|
| 54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
- lr_scheduler_type: linear
|
| 56 |
-
-
|
| 57 |
-
- num_epochs: 2
|
| 58 |
- mixed_precision_training: Native AMP
|
| 59 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
### Framework versions
|
| 61 |
|
| 62 |
- PEFT 0.12.0
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.0663
|
| 24 |
+
- Model Preparation Time: 0.0259
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 1.5e-05
|
| 44 |
- train_batch_size: 4
|
| 45 |
- eval_batch_size: 4
|
| 46 |
- seed: 42
|
|
|
|
| 48 |
- total_train_batch_size: 16
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 1
|
|
|
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|:----------------------:|
|
| 58 |
+
| 1.0842 | 0.0809 | 200 | 1.0744 | 0.0259 |
|
| 59 |
+
| 1.0767 | 0.1617 | 400 | 1.0724 | 0.0259 |
|
| 60 |
+
| 1.0997 | 0.2426 | 600 | 1.0716 | 0.0259 |
|
| 61 |
+
| 1.0758 | 0.3234 | 800 | 1.0707 | 0.0259 |
|
| 62 |
+
| 1.0949 | 0.4043 | 1000 | 1.0697 | 0.0259 |
|
| 63 |
+
| 1.0892 | 0.4851 | 1200 | 1.0687 | 0.0259 |
|
| 64 |
+
| 1.0876 | 0.5660 | 1400 | 1.0682 | 0.0259 |
|
| 65 |
+
| 1.0873 | 0.6469 | 1600 | 1.0676 | 0.0259 |
|
| 66 |
+
| 1.0679 | 0.7277 | 1800 | 1.0671 | 0.0259 |
|
| 67 |
+
| 1.0802 | 0.8086 | 2000 | 1.0669 | 0.0259 |
|
| 68 |
+
| 1.0823 | 0.8894 | 2200 | 1.0667 | 0.0259 |
|
| 69 |
+
| 1.0812 | 0.9703 | 2400 | 1.0663 | 0.0259 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
### Framework versions
|
| 73 |
|
| 74 |
- PEFT 0.12.0
|
runs/Aug08_01-18-18_3c395c9c27fe/events.out.tfevents.1723085753.3c395c9c27fe.5947.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34613c4b99d302b78508cd2f32321f4f6cf83c874c3d4fdaf0aaa07ba8140798
|
| 3 |
+
size 425
|