C2001ljy commited on
Commit
8ab3ebc
·
verified ·
1 Parent(s): 2aae262

Delete README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -68
README.md DELETED
@@ -1,68 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- tags:
4
- - generated_from_trainer
5
- base_model: facebook/rag-sequence-nq
6
- datasets:
7
- - cqa_v1
8
- model-index:
9
- - name: rag_sequence_nq_on_cqa
10
- results: []
11
- ---
12
-
13
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
- should probably proofread and complete it, then remove this comment. -->
15
-
16
- # rag_sequence_nq_on_cqa
17
-
18
- This model is a fine-tuned version of [facebook/rag-sequence-nq](https://huggingface.co/facebook/rag-sequence-nq) on the cqa_v1 dataset.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 31.3296
21
-
22
- ## Model description
23
-
24
- More information needed
25
-
26
- ## Intended uses & limitations
27
-
28
- More information needed
29
-
30
- ## Training and evaluation data
31
-
32
- More information needed
33
-
34
- ## Training procedure
35
-
36
- ### Training hyperparameters
37
-
38
- The following hyperparameters were used during training:
39
- - learning_rate: 3e-05
40
- - train_batch_size: 12
41
- - eval_batch_size: 12
42
- - seed: 47
43
- - gradient_accumulation_steps: 128
44
- - total_train_batch_size: 1536
45
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
- - lr_scheduler_type: polynomial
47
- - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 6
49
- - mixed_precision_training: Native AMP
50
-
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss |
54
- |:-------------:|:------:|:----:|:---------------:|
55
- | No log | 0.9968 | 17 | 41.6343 |
56
- | No log | 1.9936 | 34 | 36.0718 |
57
- | No log | 2.9968 | 51 | 33.7388 |
58
- | No log | 3.9936 | 68 | 32.4122 |
59
- | No log | 4.9904 | 85 | 31.6654 |
60
- | No log | 5.9872 | 102 | 31.3296 |
61
-
62
-
63
- ### Framework versions
64
-
65
- - Transformers 4.40.0
66
- - Pytorch 2.0.1+cu118
67
- - Datasets 2.14.5
68
- - Tokenizers 0.19.1