Model save
Browse files- README.md +5 -16
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -6,8 +6,6 @@ tags:
|
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: microsoft/phi-1_5
|
| 9 |
-
datasets:
|
| 10 |
-
- generator
|
| 11 |
model-index:
|
| 12 |
- name: phi-1.5-lora-tuned-Ondolly
|
| 13 |
results: []
|
|
@@ -18,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# phi-1.5-lora-tuned-Ondolly
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 2.5945
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -40,22 +36,15 @@ More information needed
|
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
- learning_rate: 1e-05
|
| 43 |
-
- train_batch_size:
|
| 44 |
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
| 46 |
-
- gradient_accumulation_steps:
|
| 47 |
-
- total_train_batch_size:
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- lr_scheduler_warmup_ratio: 0.05
|
| 51 |
-
- training_steps:
|
| 52 |
-
|
| 53 |
-
### Training results
|
| 54 |
-
|
| 55 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
-
|:-------------:|:-------:|:----:|:---------------:|
|
| 57 |
-
| 2.7652 | 12.9032 | 100 | 2.5945 |
|
| 58 |
-
|
| 59 |
|
| 60 |
### Framework versions
|
| 61 |
|
|
|
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: microsoft/phi-1_5
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: phi-1.5-lora-tuned-Ondolly
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# phi-1.5-lora-tuned-Ondolly
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on an unknown dataset.
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 1e-05
|
| 39 |
+
- train_batch_size: 10
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 40
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_ratio: 0.05
|
| 47 |
+
- training_steps: 590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9456136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3d6828718cf7f3950b57cc177755a4522d520923e46fec1495ded3be0300e13
|
| 3 |
size 9456136
|