update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: EnabledChat-v2-lora
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# EnabledChat-v2-lora
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [0x70DA/EnabledChat](https://huggingface.co/0x70DA/EnabledChat) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.2828
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0002
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_steps: 100
|
| 43 |
+
- num_epochs: 2
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 1.3247 | 0.07 | 200 | 1.3711 |
|
| 51 |
+
| 1.4053 | 0.14 | 400 | 1.3470 |
|
| 52 |
+
| 1.3431 | 0.21 | 600 | 1.3355 |
|
| 53 |
+
| 1.4012 | 0.27 | 800 | 1.3278 |
|
| 54 |
+
| 1.3189 | 0.34 | 1000 | 1.3235 |
|
| 55 |
+
| 1.3581 | 0.41 | 1200 | 1.3181 |
|
| 56 |
+
| 1.3417 | 0.48 | 1400 | 1.3138 |
|
| 57 |
+
| 1.3111 | 0.55 | 1600 | 1.3110 |
|
| 58 |
+
| 1.3547 | 0.62 | 1800 | 1.3068 |
|
| 59 |
+
| 1.3725 | 0.68 | 2000 | 1.3058 |
|
| 60 |
+
| 1.3574 | 0.75 | 2200 | 1.3028 |
|
| 61 |
+
| 1.3773 | 0.82 | 2400 | 1.2999 |
|
| 62 |
+
| 1.2944 | 0.89 | 2600 | 1.2979 |
|
| 63 |
+
| 1.2433 | 0.96 | 2800 | 1.2962 |
|
| 64 |
+
| 1.2349 | 1.03 | 3000 | 1.2952 |
|
| 65 |
+
| 1.3126 | 1.1 | 3200 | 1.2934 |
|
| 66 |
+
| 1.284 | 1.16 | 3400 | 1.2925 |
|
| 67 |
+
| 1.2194 | 1.23 | 3600 | 1.2912 |
|
| 68 |
+
| 1.2885 | 1.3 | 3800 | 1.2902 |
|
| 69 |
+
| 1.2159 | 1.37 | 4000 | 1.2888 |
|
| 70 |
+
| 1.2832 | 1.44 | 4200 | 1.2881 |
|
| 71 |
+
| 1.2233 | 1.51 | 4400 | 1.2868 |
|
| 72 |
+
| 1.2565 | 1.57 | 4600 | 1.2857 |
|
| 73 |
+
| 1.2618 | 1.64 | 4800 | 1.2855 |
|
| 74 |
+
| 1.3954 | 1.71 | 5000 | 1.2846 |
|
| 75 |
+
| 1.3082 | 1.78 | 5200 | 1.2840 |
|
| 76 |
+
| 1.3149 | 1.85 | 5400 | 1.2834 |
|
| 77 |
+
| 1.2558 | 1.92 | 5600 | 1.2830 |
|
| 78 |
+
| 1.2299 | 1.98 | 5800 | 1.2828 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.29.2
|
| 84 |
+
- Pytorch 2.0.0
|
| 85 |
+
- Datasets 2.11.0
|
| 86 |
+
- Tokenizers 0.13.3
|