Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: Qwen/Qwen1.5-4B
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3_Qwen_Qwen1.5-4B_5e-4_lora2
|
| 10 |
+
results: []
|
| 11 |
+
library_name: peft
|
| 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 |
+
# lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3_Qwen_Qwen1.5-4B_5e-4_lora2
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.8927
|
| 22 |
+
- Accuracy: 0.5834
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0005
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 8
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 8
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: constant
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 53 |
+
- num_epochs: 20.0
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 58 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 59 |
+
| 1.745 | 0.9973 | 187 | 1.6686 | 0.6096 |
|
| 60 |
+
| 1.4255 | 2.0 | 375 | 1.6989 | 0.6087 |
|
| 61 |
+
| 1.0295 | 2.9973 | 562 | 1.8159 | 0.6052 |
|
| 62 |
+
| 0.6982 | 4.0 | 750 | 1.9994 | 0.5996 |
|
| 63 |
+
| 0.4584 | 4.9973 | 937 | 2.2058 | 0.5949 |
|
| 64 |
+
| 0.3048 | 6.0 | 1125 | 2.3636 | 0.5928 |
|
| 65 |
+
| 0.2175 | 6.9973 | 1312 | 2.5218 | 0.5905 |
|
| 66 |
+
| 0.1719 | 8.0 | 1500 | 2.6292 | 0.5909 |
|
| 67 |
+
| 0.1355 | 8.9973 | 1687 | 2.7028 | 0.5892 |
|
| 68 |
+
| 0.1302 | 10.0 | 1875 | 2.7502 | 0.5876 |
|
| 69 |
+
| 0.1281 | 10.9973 | 2062 | 2.7715 | 0.5875 |
|
| 70 |
+
| 0.1331 | 12.0 | 2250 | 2.7947 | 0.5862 |
|
| 71 |
+
| 0.1435 | 12.9973 | 2437 | 2.7769 | 0.5867 |
|
| 72 |
+
| 0.1468 | 14.0 | 2625 | 2.7598 | 0.5862 |
|
| 73 |
+
| 0.1449 | 14.9973 | 2812 | 2.8147 | 0.5855 |
|
| 74 |
+
| 0.1404 | 16.0 | 3000 | 2.8564 | 0.5859 |
|
| 75 |
+
| 0.121 | 16.9973 | 3187 | 2.8381 | 0.5863 |
|
| 76 |
+
| 0.1198 | 18.0 | 3375 | 2.8844 | 0.5841 |
|
| 77 |
+
| 0.1198 | 18.9973 | 3562 | 2.9040 | 0.5834 |
|
| 78 |
+
| 0.1215 | 19.9467 | 3740 | 2.8927 | 0.5834 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- PEFT 0.5.0
|
| 84 |
+
- Transformers 4.40.2
|
| 85 |
+
- Pytorch 2.3.0
|
| 86 |
+
- Datasets 2.19.1
|
| 87 |
+
- Tokenizers 0.19.1
|