lora_phi-1_5
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: microsoft/phi-1_5
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: lora_phi-1_5
|
| 11 |
results: []
|
|
@@ -16,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# lora_phi-1_5
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -46,6 +50,17 @@ The following hyperparameters were used during training:
|
|
| 46 |
- lr_scheduler_warmup_ratio: 0.05
|
| 47 |
- training_steps: 593
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- PEFT 0.11.1
|
|
|
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: microsoft/phi-1_5
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
model-index:
|
| 12 |
- name: lora_phi-1_5
|
| 13 |
results: []
|
|
|
|
| 18 |
|
| 19 |
# lora_phi-1_5
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.3998
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 50 |
- lr_scheduler_warmup_ratio: 0.05
|
| 51 |
- training_steps: 593
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 2.7756 | 0.8065 | 100 | 2.5791 |
|
| 58 |
+
| 2.558 | 1.6129 | 200 | 2.4656 |
|
| 59 |
+
| 2.4521 | 2.4194 | 300 | 2.4294 |
|
| 60 |
+
| 2.4589 | 3.2258 | 400 | 2.4103 |
|
| 61 |
+
| 2.4248 | 4.0323 | 500 | 2.3998 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
### Framework versions
|
| 65 |
|
| 66 |
- PEFT 0.11.1
|