Model save
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3__home_aiops_zhuty_lm_indexer_data_tyzhu_
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# lmind_nq_train6000_eval6489_v1_reciteonly_qa_v3__home_aiops_zhuty_lm_indexer_data_tyzhu_
|
15 |
+
|
16 |
+
This model was trained from scratch on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.8055
|
19 |
+
- Accuracy: 0.7597
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 2
|
41 |
+
- seed: 42
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- num_devices: 4
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 32
|
46 |
+
- total_eval_batch_size: 8
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: constant
|
49 |
+
- lr_scheduler_warmup_ratio: 0.05
|
50 |
+
- num_epochs: 20.0
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
56 |
+
| 0.5411 | 1.0 | 187 | 0.3938 | 0.7904 |
|
57 |
+
| 0.362 | 2.0 | 375 | 0.3804 | 0.7918 |
|
58 |
+
| 0.3047 | 3.0 | 562 | 0.3934 | 0.7891 |
|
59 |
+
| 0.2469 | 4.0 | 750 | 0.4226 | 0.7846 |
|
60 |
+
| 0.2022 | 5.0 | 937 | 0.4661 | 0.7803 |
|
61 |
+
| 0.1681 | 6.0 | 1125 | 0.5123 | 0.7761 |
|
62 |
+
| 0.1404 | 7.0 | 1312 | 0.5731 | 0.7721 |
|
63 |
+
| 0.1197 | 8.0 | 1500 | 0.6075 | 0.7701 |
|
64 |
+
| 0.1 | 9.0 | 1687 | 0.6317 | 0.7688 |
|
65 |
+
| 0.089 | 10.0 | 1875 | 0.6718 | 0.7664 |
|
66 |
+
| 0.0837 | 11.0 | 2062 | 0.6922 | 0.7653 |
|
67 |
+
| 0.0788 | 12.0 | 2250 | 0.7254 | 0.7632 |
|
68 |
+
| 0.0761 | 13.0 | 2437 | 0.7256 | 0.7629 |
|
69 |
+
| 0.0749 | 14.0 | 2625 | 0.7534 | 0.7621 |
|
70 |
+
| 0.0741 | 15.0 | 2812 | 0.7529 | 0.7620 |
|
71 |
+
| 0.0726 | 16.0 | 3000 | 0.7678 | 0.7611 |
|
72 |
+
| 0.0687 | 17.0 | 3187 | 0.7728 | 0.7610 |
|
73 |
+
| 0.0682 | 18.0 | 3375 | 0.7807 | 0.7603 |
|
74 |
+
| 0.0682 | 19.0 | 3562 | 0.7872 | 0.7610 |
|
75 |
+
| 0.0682 | 19.95 | 3740 | 0.8055 | 0.7597 |
|
76 |
+
|
77 |
+
|
78 |
+
### Framework versions
|
79 |
+
|
80 |
+
- Transformers 4.34.0
|
81 |
+
- Pytorch 2.1.0+cu121
|
82 |
+
- Datasets 2.18.0
|
83 |
+
- Tokenizers 0.14.1
|