Commit
•
264f1ec
1
Parent(s):
5c83fab
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: filipealmeida/Mistral-7B-Instruct-v0.1-sharded
|
| 7 |
+
model-index:
|
| 8 |
+
- name: mistral7b-finetune-10k
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# mistral7b-finetune-10k
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [filipealmeida/Mistral-7B-Instruct-v0.1-sharded](https://huggingface.co/filipealmeida/Mistral-7B-Instruct-v0.1-sharded) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0138
|
| 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: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- training_steps: 2500
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 1.8342 | 0.08 | 100 | 1.4509 |
|
| 52 |
+
| 1.3118 | 0.16 | 200 | 1.2525 |
|
| 53 |
+
| 1.2008 | 0.24 | 300 | 1.2086 |
|
| 54 |
+
| 1.1544 | 0.33 | 400 | 1.1871 |
|
| 55 |
+
| 1.1421 | 0.41 | 500 | 1.1651 |
|
| 56 |
+
| 1.1222 | 0.49 | 600 | 1.1497 |
|
| 57 |
+
| 1.1234 | 0.57 | 700 | 1.1232 |
|
| 58 |
+
| 1.0913 | 0.65 | 800 | 1.1089 |
|
| 59 |
+
| 1.0872 | 0.73 | 900 | 1.0906 |
|
| 60 |
+
| 1.0396 | 0.82 | 1000 | 1.0784 |
|
| 61 |
+
| 1.0634 | 0.9 | 1100 | 1.0701 |
|
| 62 |
+
| 1.007 | 0.98 | 1200 | 1.0616 |
|
| 63 |
+
| 0.9981 | 1.06 | 1300 | 1.0545 |
|
| 64 |
+
| 0.9518 | 1.14 | 1400 | 1.0453 |
|
| 65 |
+
| 0.939 | 1.22 | 1500 | 1.0386 |
|
| 66 |
+
| 0.9791 | 1.31 | 1600 | 1.0356 |
|
| 67 |
+
| 0.977 | 1.39 | 1700 | 1.0302 |
|
| 68 |
+
| 0.9287 | 1.47 | 1800 | 1.0233 |
|
| 69 |
+
| 0.9393 | 1.55 | 1900 | 1.0209 |
|
| 70 |
+
| 0.915 | 1.63 | 2000 | 1.0184 |
|
| 71 |
+
| 0.95 | 1.71 | 2100 | 1.0155 |
|
| 72 |
+
| 0.9542 | 1.8 | 2200 | 1.0150 |
|
| 73 |
+
| 0.9272 | 1.88 | 2300 | 1.0146 |
|
| 74 |
+
| 0.9381 | 1.96 | 2400 | 1.0142 |
|
| 75 |
+
| 0.9358 | 2.04 | 2500 | 1.0138 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- PEFT 0.7.1
|
| 81 |
+
- Transformers 4.36.0.dev0
|
| 82 |
+
- Pytorch 2.0.0
|
| 83 |
+
- Datasets 2.1.0
|
| 84 |
+
- Tokenizers 0.15.0
|