Delete README.md
Browse files
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|