Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: qlora-out
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
| 15 |
+
# qlora-out
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.3095
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 128
|
| 40 |
+
- eval_batch_size: 128
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_steps: 10
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 5.5317 | 0.07 | 1 | 5.2182 |
|
| 52 |
+
| 5.438 | 0.2 | 3 | 4.7897 |
|
| 53 |
+
| 4.1476 | 0.4 | 6 | 3.4313 |
|
| 54 |
+
| 3.2037 | 0.6 | 9 | 2.8663 |
|
| 55 |
+
| 2.7895 | 0.8 | 12 | 2.5112 |
|
| 56 |
+
| 2.3139 | 1.0 | 15 | 2.1467 |
|
| 57 |
+
| 2.1672 | 1.2 | 18 | 1.8620 |
|
| 58 |
+
| 1.9095 | 1.4 | 21 | 1.6519 |
|
| 59 |
+
| 1.5397 | 1.6 | 24 | 1.5429 |
|
| 60 |
+
| 1.6327 | 1.8 | 27 | 1.4518 |
|
| 61 |
+
| 1.3676 | 2.0 | 30 | 1.3892 |
|
| 62 |
+
| 1.3906 | 2.2 | 33 | 1.3531 |
|
| 63 |
+
| 1.4096 | 2.4 | 36 | 1.3314 |
|
| 64 |
+
| 1.3278 | 2.6 | 39 | 1.3165 |
|
| 65 |
+
| 1.3007 | 2.8 | 42 | 1.3107 |
|
| 66 |
+
| 1.2848 | 3.0 | 45 | 1.3095 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.35.2
|
| 72 |
+
- Pytorch 2.0.1+cu118
|
| 73 |
+
- Datasets 2.15.0
|
| 74 |
+
- Tokenizers 0.15.0
|