End of training
Browse files
README.md
CHANGED
@@ -7,14 +7,14 @@ tags:
|
|
7 |
- generated_from_trainer
|
8 |
base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
|
9 |
model-index:
|
10 |
-
- name: ROE_QA_Breeze-7B-Instruct-
|
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_QA_Breeze-7B-Instruct-
|
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 |
|
@@ -35,15 +35,15 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- learning_rate: 0.
|
39 |
- train_batch_size: 2
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
-
- gradient_accumulation_steps:
|
43 |
-
- total_train_batch_size:
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
-
- lr_scheduler_type:
|
46 |
-
- lr_scheduler_warmup_ratio: 0.
|
47 |
- num_epochs: 3
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
|
|
7 |
- generated_from_trainer
|
8 |
base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
|
9 |
model-index:
|
10 |
+
- name: ROE_QA_Breeze-7B-Instruct-v1_0_Q30_80_20_V2
|
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_QA_Breeze-7B-Instruct-v1_0_Q30_80_20_V2
|
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 |
|
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
- train_batch_size: 2
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 2
|
43 |
+
- total_train_batch_size: 4
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- lr_scheduler_warmup_ratio: 0.05
|
47 |
- num_epochs: 3
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|