Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
| 3 |
+
datasets:
|
| 4 |
+
- generator
|
| 5 |
+
library_name: peft
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
tags:
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Mistral-7B-text-to-sql-flash-attention-2-FAISS-NEWPOC
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# Mistral-7B-text-to-sql-flash-attention-2-FAISS-NEWPOC
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.5718
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 1.25e-05
|
| 43 |
+
- train_batch_size: 32
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 8
|
| 47 |
+
- total_train_batch_size: 256
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: constant
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 51 |
+
- lr_scheduler_warmup_steps: 15
|
| 52 |
+
- num_epochs: 50
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 58 |
+
| 1.6025 | 2.1053 | 10 | 1.3983 |
|
| 59 |
+
| 1.2594 | 4.2105 | 20 | 1.1677 |
|
| 60 |
+
| 1.1238 | 6.3158 | 30 | 1.0695 |
|
| 61 |
+
| 1.0331 | 8.4211 | 40 | 0.9917 |
|
| 62 |
+
| 0.9668 | 10.5263 | 50 | 0.9300 |
|
| 63 |
+
| 0.9064 | 12.6316 | 60 | 0.8783 |
|
| 64 |
+
| 0.8569 | 14.7368 | 70 | 0.8309 |
|
| 65 |
+
| 0.8099 | 16.8421 | 80 | 0.7842 |
|
| 66 |
+
| 0.7632 | 18.9474 | 90 | 0.7365 |
|
| 67 |
+
| 0.7188 | 21.0526 | 100 | 0.6991 |
|
| 68 |
+
| 0.6855 | 23.1579 | 110 | 0.6714 |
|
| 69 |
+
| 0.6587 | 25.2632 | 120 | 0.6492 |
|
| 70 |
+
| 0.6383 | 27.3684 | 130 | 0.6312 |
|
| 71 |
+
| 0.6206 | 29.4737 | 140 | 0.6171 |
|
| 72 |
+
| 0.6077 | 31.5789 | 150 | 0.6062 |
|
| 73 |
+
| 0.5964 | 33.6842 | 160 | 0.5973 |
|
| 74 |
+
| 0.5881 | 35.7895 | 170 | 0.5898 |
|
| 75 |
+
| 0.5805 | 37.8947 | 180 | 0.5831 |
|
| 76 |
+
| 0.5732 | 40.0 | 190 | 0.5771 |
|
| 77 |
+
| 0.5665 | 42.1053 | 200 | 0.5718 |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### Framework versions
|
| 81 |
+
|
| 82 |
+
- PEFT 0.11.1
|
| 83 |
+
- Transformers 4.42.3
|
| 84 |
+
- Pytorch 2.3.0+cu121
|
| 85 |
+
- Datasets 2.20.0
|
| 86 |
+
- Tokenizers 0.19.1
|