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_3e-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_3e-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: 3.0184
|
22 |
+
- Accuracy: 0.5886
|
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: 0.0003
|
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 |
+
| 1.7516 | 0.9973 | 187 | 1.6714 | 0.6086 |
|
60 |
+
| 1.5219 | 2.0 | 375 | 1.6736 | 0.6104 |
|
61 |
+
| 1.2037 | 2.9973 | 562 | 1.7561 | 0.6081 |
|
62 |
+
| 0.8815 | 4.0 | 750 | 1.8875 | 0.6033 |
|
63 |
+
| 0.6016 | 4.9973 | 937 | 2.0768 | 0.5980 |
|
64 |
+
| 0.3979 | 6.0 | 1125 | 2.2606 | 0.5953 |
|
65 |
+
| 0.2591 | 6.9973 | 1312 | 2.4670 | 0.5933 |
|
66 |
+
| 0.1821 | 8.0 | 1500 | 2.6145 | 0.5922 |
|
67 |
+
| 0.1338 | 8.9973 | 1687 | 2.7399 | 0.5911 |
|
68 |
+
| 0.1172 | 10.0 | 1875 | 2.8330 | 0.5915 |
|
69 |
+
| 0.1102 | 10.9973 | 2062 | 2.8674 | 0.5914 |
|
70 |
+
| 0.1079 | 12.0 | 2250 | 2.8947 | 0.5903 |
|
71 |
+
| 0.11 | 12.9973 | 2437 | 2.9230 | 0.5894 |
|
72 |
+
| 0.1136 | 14.0 | 2625 | 2.9049 | 0.5888 |
|
73 |
+
| 0.1173 | 14.9973 | 2812 | 2.8788 | 0.5883 |
|
74 |
+
| 0.1163 | 16.0 | 3000 | 2.9582 | 0.5892 |
|
75 |
+
| 0.1047 | 16.9973 | 3187 | 2.9485 | 0.5886 |
|
76 |
+
| 0.1044 | 18.0 | 3375 | 2.9815 | 0.5894 |
|
77 |
+
| 0.105 | 18.9973 | 3562 | 2.9880 | 0.5881 |
|
78 |
+
| 0.1036 | 19.9467 | 3740 | 3.0184 | 0.5886 |
|
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
|