Commit
•
f02aca4
1
Parent(s):
7cade5b
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- zh
|
| 4 |
+
license: gemma
|
| 5 |
+
library_name: peft
|
| 6 |
+
tags:
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
- nycu-112-2-deeplearning-hw2
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
base_model: google/gemma-1.1-7b-it
|
| 12 |
+
datasets:
|
| 13 |
+
- DandinPower/ZH-Reading-Comprehension-gemma-it
|
| 14 |
+
model-index:
|
| 15 |
+
- name: gemma_7b_lora_completion_only
|
| 16 |
+
results: []
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 20 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 21 |
+
|
| 22 |
+
# gemma_7b_lora_completion_only
|
| 23 |
+
|
| 24 |
+
This model is a fine-tuned version of [google/gemma-1.1-7b-it](https://huggingface.co/google/gemma-1.1-7b-it) on the DandinPower/ZH-Reading-Comprehension-gemma-it dataset.
|
| 25 |
+
It achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 0.0885
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 0.0001
|
| 46 |
+
- train_batch_size: 1
|
| 47 |
+
- eval_batch_size: 1
|
| 48 |
+
- seed: 42
|
| 49 |
+
- distributed_type: multi-GPU
|
| 50 |
+
- num_devices: 2
|
| 51 |
+
- gradient_accumulation_steps: 8
|
| 52 |
+
- total_train_batch_size: 16
|
| 53 |
+
- total_eval_batch_size: 2
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- lr_scheduler_warmup_steps: 700
|
| 57 |
+
- num_epochs: 3.0
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 62 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 63 |
+
| 0.1172 | 0.3690 | 250 | 0.0932 |
|
| 64 |
+
| 0.1059 | 0.7380 | 500 | 0.0997 |
|
| 65 |
+
| 0.0913 | 1.1070 | 750 | 0.1225 |
|
| 66 |
+
| 0.074 | 1.4760 | 1000 | 0.1046 |
|
| 67 |
+
| 0.0619 | 1.8450 | 1250 | 0.1084 |
|
| 68 |
+
| 0.0375 | 2.2140 | 1500 | 0.1038 |
|
| 69 |
+
| 0.0128 | 2.5830 | 1750 | 0.0993 |
|
| 70 |
+
| 0.044 | 2.9520 | 2000 | 0.0885 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- PEFT 0.10.0
|
| 76 |
+
- Transformers 4.40.0
|
| 77 |
+
- Pytorch 2.2.2+cu121
|
| 78 |
+
- Datasets 2.19.0
|
| 79 |
+
- Tokenizers 0.19.1
|