End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: ROE_Patent_Breeze7B_V1
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# ROE_Patent_Breeze7B_V1
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [MediaTek-Research/Breeze-7B-Instruct-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7530
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: constant
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
+
- num_epochs: 11
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
+
| 0.9896 | 0.9697 | 12 | 0.9971 |
|
| 57 |
+
| 0.9038 | 1.9394 | 24 | 0.9124 |
|
| 58 |
+
| 0.812 | 2.9899 | 37 | 0.8596 |
|
| 59 |
+
| 0.8009 | 3.9596 | 49 | 0.8248 |
|
| 60 |
+
| 0.7401 | 4.9293 | 61 | 0.8017 |
|
| 61 |
+
| 0.6997 | 5.9798 | 74 | 0.7835 |
|
| 62 |
+
| 0.6831 | 6.9495 | 86 | 0.7715 |
|
| 63 |
+
| 0.656 | 8.0 | 99 | 0.7635 |
|
| 64 |
+
| 0.6389 | 8.9697 | 111 | 0.7558 |
|
| 65 |
+
| 0.6094 | 9.9394 | 123 | 0.7550 |
|
| 66 |
+
| 0.5967 | 10.6667 | 132 | 0.7530 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- PEFT 0.13.3.dev0
|
| 72 |
+
- Transformers 4.45.2
|
| 73 |
+
- Pytorch 2.4.1+cu121
|
| 74 |
+
- Datasets 3.0.1
|
| 75 |
+
- Tokenizers 0.20.1
|
runs/Oct14_14-22-51_4fee8626f477/events.out.tfevents.1728915773.4fee8626f477.21682.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97c056bf33644b7a0d018e3c21161c230215d3c12cd84ccc4942891a4e2bf458
|
| 3 |
+
size 11801
|