Commit
·
5323f0b
1
Parent(s):
aaf6b00
End of training
Browse files- README.md +74 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: openchat/openchat_3.5
|
| 6 |
+
tags:
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- amgadhasan/explicitai-scarch-0.1
|
| 10 |
+
model-index:
|
| 11 |
+
- name: Scarlet Chase Chatbot
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# Scarlet Chase Chatbot
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5) on the Scarch 0.2 dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.5505
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 2e-05
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_steps: 50
|
| 50 |
+
- num_epochs: 10
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.3688 | 0.99 | 23 | 1.2936 |
|
| 58 |
+
| 0.6937 | 1.99 | 46 | 0.7731 |
|
| 59 |
+
| 0.4616 | 2.98 | 69 | 0.5906 |
|
| 60 |
+
| 0.3754 | 3.98 | 92 | 0.5231 |
|
| 61 |
+
| 0.2555 | 4.97 | 115 | 0.5099 |
|
| 62 |
+
| 0.2235 | 5.97 | 138 | 0.5073 |
|
| 63 |
+
| 0.1517 | 6.96 | 161 | 0.5216 |
|
| 64 |
+
| 0.0767 | 8.0 | 185 | 0.5357 |
|
| 65 |
+
| 0.073 | 8.99 | 208 | 0.5503 |
|
| 66 |
+
| 0.0886 | 9.95 | 230 | 0.5505 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.35.0
|
| 72 |
+
- Pytorch 2.0.1+cu118
|
| 73 |
+
- Datasets 2.14.6
|
| 74 |
+
- Tokenizers 0.14.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1719857496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23f4c26d84c75c02f272d931fbf2ee06a99f6dfed8dd1185ac2d981adc3b7009
|
| 3 |
size 1719857496
|