TaiGary commited on
Commit
cc5ff31
·
verified ·
1 Parent(s): 51e2305

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -99
README.md CHANGED
@@ -1,99 +0,0 @@
1
- ---
2
- library_name: transformers
3
- license: other
4
- base_model: Qwen/Qwen2.5-7B-Instruct
5
- tags:
6
- - llama-factory
7
- - full
8
- - generated_from_trainer
9
- model-index:
10
- - name: agenttuning_v4_15k_tag4
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
- # agenttuning_v4_15k_tag4
18
-
19
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the agenttuning_v4_15k_tag4 dataset.
20
- It achieves the following results on the evaluation set:
21
- - Loss: 0.3463
22
-
23
- ## Model description
24
-
25
- More information needed
26
-
27
- ## Intended uses & limitations
28
-
29
- More information needed
30
-
31
- ## Training and evaluation data
32
-
33
- More information needed
34
-
35
- ## Training procedure
36
-
37
- ### Training hyperparameters
38
-
39
- The following hyperparameters were used during training:
40
- - learning_rate: 5e-06
41
- - train_batch_size: 1
42
- - eval_batch_size: 1
43
- - seed: 42
44
- - distributed_type: multi-GPU
45
- - num_devices: 4
46
- - total_train_batch_size: 4
47
- - total_eval_batch_size: 4
48
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
- - lr_scheduler_type: cosine
50
- - num_epochs: 1
51
-
52
- ### Training results
53
-
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:------:|:----:|:---------------:|
56
- | 0.411 | 0.0272 | 100 | 0.4573 |
57
- | 0.4154 | 0.0544 | 200 | 0.4534 |
58
- | 0.45 | 0.0816 | 300 | 0.4339 |
59
- | 0.4442 | 0.1088 | 400 | 0.4359 |
60
- | 0.5011 | 0.1361 | 500 | 0.4093 |
61
- | 0.4743 | 0.1633 | 600 | 0.4134 |
62
- | 0.2855 | 0.1905 | 700 | 0.4042 |
63
- | 0.3281 | 0.2177 | 800 | 0.4117 |
64
- | 0.3854 | 0.2449 | 900 | 0.4114 |
65
- | 0.5613 | 0.2721 | 1000 | 0.4117 |
66
- | 0.5624 | 0.2993 | 1100 | 0.4049 |
67
- | 0.4616 | 0.3265 | 1200 | 0.3989 |
68
- | 0.373 | 0.3537 | 1300 | 0.3982 |
69
- | 0.5473 | 0.3810 | 1400 | 0.3963 |
70
- | 0.5104 | 0.4082 | 1500 | 0.3924 |
71
- | 0.4531 | 0.4354 | 1600 | 0.3852 |
72
- | 0.3872 | 0.4626 | 1700 | 0.3814 |
73
- | 0.4966 | 0.4898 | 1800 | 0.3819 |
74
- | 0.5067 | 0.5170 | 1900 | 0.3738 |
75
- | 0.4067 | 0.5442 | 2000 | 0.3749 |
76
- | 0.3464 | 0.5714 | 2100 | 0.3786 |
77
- | 0.353 | 0.5986 | 2200 | 0.3678 |
78
- | 0.4483 | 0.6259 | 2300 | 0.3640 |
79
- | 0.3288 | 0.6531 | 2400 | 0.3594 |
80
- | 0.4155 | 0.6803 | 2500 | 0.3576 |
81
- | 0.3656 | 0.7075 | 2600 | 0.3538 |
82
- | 0.303 | 0.7347 | 2700 | 0.3544 |
83
- | 0.4023 | 0.7619 | 2800 | 0.3527 |
84
- | 0.3726 | 0.7891 | 2900 | 0.3503 |
85
- | 0.3333 | 0.8163 | 3000 | 0.3487 |
86
- | 0.4189 | 0.8435 | 3100 | 0.3462 |
87
- | 0.3927 | 0.8707 | 3200 | 0.3452 |
88
- | 0.3778 | 0.8980 | 3300 | 0.3466 |
89
- | 0.3443 | 0.9252 | 3400 | 0.3466 |
90
- | 0.3868 | 0.9524 | 3500 | 0.3470 |
91
- | 0.382 | 0.9796 | 3600 | 0.3463 |
92
-
93
-
94
- ### Framework versions
95
-
96
- - Transformers 4.46.1
97
- - Pytorch 2.6.0+cu124
98
- - Datasets 3.1.0
99
- - Tokenizers 0.20.3