Commit
·
cb66580
1
Parent(s):
e9a0158
End of training
Browse files- README.md +72 -0
- adapter_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: tiiuae/falcon-7b
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- spider
|
| 8 |
+
model-index:
|
| 9 |
+
- name: falcon-7b_spider
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# falcon-7b_spider
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the spider dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1858
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0001
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 43.7
|
| 46 |
+
- num_epochs: 3
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 0.3145 | 0.23 | 100 | 0.2930 |
|
| 53 |
+
| 0.7216 | 0.46 | 200 | 0.2351 |
|
| 54 |
+
| 0.1483 | 0.68 | 300 | 0.2174 |
|
| 55 |
+
| 0.1186 | 0.91 | 400 | 0.2108 |
|
| 56 |
+
| 0.1887 | 1.14 | 500 | 0.2134 |
|
| 57 |
+
| 0.2358 | 1.37 | 600 | 0.2017 |
|
| 58 |
+
| 0.1678 | 1.6 | 700 | 0.1901 |
|
| 59 |
+
| 0.1771 | 1.83 | 800 | 0.1989 |
|
| 60 |
+
| 0.0394 | 2.05 | 900 | 0.1869 |
|
| 61 |
+
| 0.0916 | 2.28 | 1000 | 0.1845 |
|
| 62 |
+
| 0.1701 | 2.51 | 1100 | 0.1868 |
|
| 63 |
+
| 0.2159 | 2.74 | 1200 | 0.1899 |
|
| 64 |
+
| 0.1933 | 2.97 | 1300 | 0.1969 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.32.0.dev0
|
| 70 |
+
- Pytorch 2.0.1+cu117
|
| 71 |
+
- Datasets 2.14.4
|
| 72 |
+
- Tokenizers 0.13.3
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9460849
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de7280ffad288b5b38f44520d9cda943a4f0ea40ea3905166f271b7cc0470045
|
| 3 |
size 9460849
|