heloisy/zephyr-7b-beta-cosmosqa-ptbr-text-v3
Browse files- README.md +76 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: HuggingFaceH4/zephyr-7b-beta
|
| 7 |
+
model-index:
|
| 8 |
+
- name: zephyr-7b-b-cosmosqa-ptbr-text-v3
|
| 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 |
+
# zephyr-7b-b-cosmosqa-ptbr-text-v3
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0961
|
| 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: 4e-05
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 100
|
| 47 |
+
- num_epochs: 2
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 1.4897 | 0.13 | 100 | 1.1561 |
|
| 54 |
+
| 1.1452 | 0.25 | 200 | 1.1251 |
|
| 55 |
+
| 1.1185 | 0.38 | 300 | 1.1146 |
|
| 56 |
+
| 1.1079 | 0.51 | 400 | 1.1038 |
|
| 57 |
+
| 1.0906 | 0.63 | 500 | 1.0998 |
|
| 58 |
+
| 1.0849 | 0.76 | 600 | 1.0967 |
|
| 59 |
+
| 1.0721 | 0.89 | 700 | 1.0959 |
|
| 60 |
+
| 1.0623 | 1.01 | 800 | 1.0941 |
|
| 61 |
+
| 1.0217 | 1.14 | 900 | 1.0987 |
|
| 62 |
+
| 1.0122 | 1.27 | 1000 | 1.0977 |
|
| 63 |
+
| 1.0095 | 1.39 | 1100 | 1.0980 |
|
| 64 |
+
| 1.0088 | 1.52 | 1200 | 1.0966 |
|
| 65 |
+
| 0.9952 | 1.65 | 1300 | 1.0964 |
|
| 66 |
+
| 1.0018 | 1.77 | 1400 | 1.0967 |
|
| 67 |
+
| 0.9991 | 1.9 | 1500 | 1.0961 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- PEFT 0.7.1.dev0
|
| 73 |
+
- Transformers 4.36.0.dev0
|
| 74 |
+
- Pytorch 2.0.1+cu117
|
| 75 |
+
- Datasets 2.14.7
|
| 76 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 130074856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2317c6716201dce11553888ebdc9b160a1a9c5a2da669f4505228f405d42be14
|
| 3 |
size 130074856
|