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_hotpot_train8000_eval7405_v1_doc_qa_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_hotpot_train8000_eval7405_v1_doc_qa_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: 3.1631
|
22 |
+
- Accuracy: 0.5165
|
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 |
+
| 1.7567 | 0.9998 | 1089 | 2.2626 | 0.5190 |
|
60 |
+
| 1.5617 | 1.9995 | 2178 | 2.2436 | 0.5246 |
|
61 |
+
| 1.343 | 2.9993 | 3267 | 2.3385 | 0.5237 |
|
62 |
+
| 1.1682 | 4.0 | 4357 | 2.4995 | 0.5215 |
|
63 |
+
| 1.0141 | 4.9998 | 5446 | 2.6397 | 0.5182 |
|
64 |
+
| 0.9023 | 5.9995 | 6535 | 2.7929 | 0.5170 |
|
65 |
+
| 0.8008 | 6.9993 | 7624 | 2.8233 | 0.5162 |
|
66 |
+
| 0.7377 | 8.0 | 8714 | 2.8833 | 0.5180 |
|
67 |
+
| 0.6732 | 8.9998 | 9803 | 2.9550 | 0.5165 |
|
68 |
+
| 0.6225 | 9.9995 | 10892 | 2.9767 | 0.5165 |
|
69 |
+
| 0.5858 | 10.9993 | 11981 | 3.0117 | 0.5165 |
|
70 |
+
| 0.5618 | 12.0 | 13071 | 3.0317 | 0.5170 |
|
71 |
+
| 0.5464 | 12.9998 | 14160 | 3.0686 | 0.5167 |
|
72 |
+
| 0.5243 | 13.9995 | 15249 | 3.0829 | 0.5149 |
|
73 |
+
| 0.5066 | 14.9993 | 16338 | 3.0958 | 0.5127 |
|
74 |
+
| 0.4947 | 16.0 | 17428 | 3.0921 | 0.5153 |
|
75 |
+
| 0.4841 | 16.9998 | 18517 | 3.1170 | 0.5162 |
|
76 |
+
| 0.4727 | 17.9995 | 19606 | 3.1375 | 0.5172 |
|
77 |
+
| 0.4634 | 18.9993 | 20695 | 3.1323 | 0.5150 |
|
78 |
+
| 0.4468 | 19.9954 | 21780 | 3.1631 | 0.5165 |
|
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
|