Model save
Browse files
README.md
CHANGED
|
@@ -1,3 +1,90 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: question-generator-v2
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# question-generator-v2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7497
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0005
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 3
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 1.0483 | 0.0967 | 50 | 0.9260 |
|
| 55 |
+
| 0.8577 | 0.1934 | 100 | 0.8202 |
|
| 56 |
+
| 0.7996 | 0.2901 | 150 | 0.7895 |
|
| 57 |
+
| 0.7802 | 0.3868 | 200 | 0.7784 |
|
| 58 |
+
| 0.7671 | 0.4836 | 250 | 0.7721 |
|
| 59 |
+
| 0.761 | 0.5803 | 300 | 0.7688 |
|
| 60 |
+
| 0.7587 | 0.6770 | 350 | 0.7663 |
|
| 61 |
+
| 0.7529 | 0.7737 | 400 | 0.7637 |
|
| 62 |
+
| 0.7562 | 0.8704 | 450 | 0.7616 |
|
| 63 |
+
| 0.7507 | 0.9671 | 500 | 0.7602 |
|
| 64 |
+
| 0.7274 | 1.0638 | 550 | 0.7589 |
|
| 65 |
+
| 0.7422 | 1.1605 | 600 | 0.7574 |
|
| 66 |
+
| 0.735 | 1.2573 | 650 | 0.7571 |
|
| 67 |
+
| 0.7367 | 1.3540 | 700 | 0.7555 |
|
| 68 |
+
| 0.7471 | 1.4507 | 750 | 0.7549 |
|
| 69 |
+
| 0.7404 | 1.5474 | 800 | 0.7541 |
|
| 70 |
+
| 0.742 | 1.6441 | 850 | 0.7533 |
|
| 71 |
+
| 0.7385 | 1.7408 | 900 | 0.7530 |
|
| 72 |
+
| 0.7352 | 1.8375 | 950 | 0.7525 |
|
| 73 |
+
| 0.7323 | 1.9342 | 1000 | 0.7516 |
|
| 74 |
+
| 0.7328 | 2.0309 | 1050 | 0.7515 |
|
| 75 |
+
| 0.7264 | 2.1277 | 1100 | 0.7510 |
|
| 76 |
+
| 0.704 | 2.2244 | 1150 | 0.7505 |
|
| 77 |
+
| 0.7242 | 2.3211 | 1200 | 0.7510 |
|
| 78 |
+
| 0.7203 | 2.4178 | 1250 | 0.7502 |
|
| 79 |
+
| 0.7285 | 2.5145 | 1300 | 0.7499 |
|
| 80 |
+
| 0.7192 | 2.6112 | 1350 | 0.7502 |
|
| 81 |
+
| 0.7204 | 2.7079 | 1400 | 0.7497 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- PEFT 0.12.0
|
| 87 |
+
- Transformers 4.42.3
|
| 88 |
+
- Pytorch 2.1.2
|
| 89 |
+
- Datasets 2.20.0
|
| 90 |
+
- Tokenizers 0.19.1
|