End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: TheBloke/Tess-M-v1.3-GPTQ
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: Tess34-fans
|
| 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 |
+
# Tess34-fans
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [TheBloke/Tess-M-v1.3-GPTQ](https://huggingface.co/TheBloke/Tess-M-v1.3-GPTQ) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.7360
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0004
|
| 38 |
+
- train_batch_size: 2
|
| 39 |
+
- eval_batch_size: 2
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 2
|
| 44 |
+
- training_steps: 1000
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 1.2094 | 0.02 | 50 | 0.9702 |
|
| 52 |
+
| 0.9633 | 0.04 | 100 | 0.9093 |
|
| 53 |
+
| 0.91 | 0.06 | 150 | 0.8754 |
|
| 54 |
+
| 0.8928 | 0.08 | 200 | 0.8588 |
|
| 55 |
+
| 0.8768 | 0.1 | 250 | 0.8428 |
|
| 56 |
+
| 0.8344 | 0.12 | 300 | 0.8235 |
|
| 57 |
+
| 0.8345 | 0.14 | 350 | 0.8160 |
|
| 58 |
+
| 0.812 | 0.16 | 400 | 0.8125 |
|
| 59 |
+
| 0.8605 | 0.18 | 450 | 0.8079 |
|
| 60 |
+
| 0.8263 | 0.21 | 500 | 0.7884 |
|
| 61 |
+
| 0.7863 | 0.23 | 550 | 0.7849 |
|
| 62 |
+
| 0.7751 | 0.25 | 600 | 0.7798 |
|
| 63 |
+
| 0.7976 | 0.27 | 650 | 0.7695 |
|
| 64 |
+
| 0.7584 | 0.29 | 700 | 0.7631 |
|
| 65 |
+
| 0.8019 | 0.31 | 750 | 0.7552 |
|
| 66 |
+
| 0.7626 | 0.33 | 800 | 0.7501 |
|
| 67 |
+
| 0.7566 | 0.35 | 850 | 0.7472 |
|
| 68 |
+
| 0.7261 | 0.37 | 900 | 0.7424 |
|
| 69 |
+
| 0.7613 | 0.39 | 950 | 0.7379 |
|
| 70 |
+
| 0.7274 | 0.41 | 1000 | 0.7360 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.35.2
|
| 76 |
+
- Pytorch 2.1.0+cu118
|
| 77 |
+
- Datasets 2.15.0
|
| 78 |
+
- Tokenizers 0.15.0
|