Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 9 |
+
model-index:
|
| 10 |
+
- name: ZeroShot-3.3.17-Mistral-7b-Multilanguage-3.2.0
|
| 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 |
+
# ZeroShot-3.3.17-Mistral-7b-Multilanguage-3.2.0
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2597
|
| 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: 0.0002
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 3
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 56 |
+
| 0.451 | 0.12 | 100 | 0.4237 |
|
| 57 |
+
| 0.4109 | 0.25 | 200 | 0.4063 |
|
| 58 |
+
| 0.3959 | 0.37 | 300 | 0.3975 |
|
| 59 |
+
| 0.388 | 0.5 | 400 | 0.3826 |
|
| 60 |
+
| 0.3727 | 0.62 | 500 | 0.3739 |
|
| 61 |
+
| 0.3743 | 0.74 | 600 | 0.3625 |
|
| 62 |
+
| 0.3631 | 0.87 | 700 | 0.3530 |
|
| 63 |
+
| 0.3491 | 0.99 | 800 | 0.3418 |
|
| 64 |
+
| 0.2781 | 1.12 | 900 | 0.3402 |
|
| 65 |
+
| 0.2831 | 1.24 | 1000 | 0.3284 |
|
| 66 |
+
| 0.2788 | 1.36 | 1100 | 0.3187 |
|
| 67 |
+
| 0.2727 | 1.49 | 1200 | 0.3078 |
|
| 68 |
+
| 0.2632 | 1.61 | 1300 | 0.2978 |
|
| 69 |
+
| 0.2568 | 1.74 | 1400 | 0.2882 |
|
| 70 |
+
| 0.2425 | 1.86 | 1500 | 0.2789 |
|
| 71 |
+
| 0.2388 | 1.98 | 1600 | 0.2694 |
|
| 72 |
+
| 0.1521 | 2.11 | 1700 | 0.2774 |
|
| 73 |
+
| 0.1523 | 2.23 | 1800 | 0.2732 |
|
| 74 |
+
| 0.147 | 2.36 | 1900 | 0.2692 |
|
| 75 |
+
| 0.1443 | 2.48 | 2000 | 0.2655 |
|
| 76 |
+
| 0.1427 | 2.6 | 2100 | 0.2618 |
|
| 77 |
+
| 0.1427 | 2.73 | 2200 | 0.2605 |
|
| 78 |
+
| 0.1422 | 2.85 | 2300 | 0.2599 |
|
| 79 |
+
| 0.1411 | 2.98 | 2400 | 0.2597 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- PEFT 0.9.0
|
| 85 |
+
- Transformers 4.38.1
|
| 86 |
+
- Pytorch 2.1.0+cu121
|
| 87 |
+
- Datasets 2.17.1
|
| 88 |
+
- Tokenizers 0.15.2
|