Mitrofazotron
commited on
Commit
•
4a60402
1
Parent(s):
0360d79
Model save
Browse files- README.md +80 -0
- generation_config.json +6 -0
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/flan-t5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- esnli
|
8 |
+
metrics:
|
9 |
+
- rouge
|
10 |
+
model-index:
|
11 |
+
- name: flan-t5-base-esnli
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Sequence-to-sequence Language Modeling
|
15 |
+
type: text2text-generation
|
16 |
+
dataset:
|
17 |
+
name: esnli
|
18 |
+
type: esnli
|
19 |
+
config: plain_text
|
20 |
+
split: validation
|
21 |
+
args: plain_text
|
22 |
+
metrics:
|
23 |
+
- name: Rouge1
|
24 |
+
type: rouge
|
25 |
+
value: 7.9134
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# flan-t5-base-esnli
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the esnli dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: nan
|
36 |
+
- Rouge1: 7.9134
|
37 |
+
- Rouge2: 2.5218
|
38 |
+
- Rougel: 6.6841
|
39 |
+
- Rougelsum: 6.8287
|
40 |
+
- Gen Len: 5.1981
|
41 |
+
|
42 |
+
## Model description
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Intended uses & limitations
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training and evaluation data
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training procedure
|
55 |
+
|
56 |
+
### Training hyperparameters
|
57 |
+
|
58 |
+
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 2e-05
|
60 |
+
- train_batch_size: 32
|
61 |
+
- eval_batch_size: 32
|
62 |
+
- seed: 42
|
63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
+
- lr_scheduler_type: linear
|
65 |
+
- num_epochs: 1
|
66 |
+
- mixed_precision_training: Native AMP
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
72 |
+
| 0.0 | 1.0 | 8584 | nan | 7.9134 | 2.5218 | 6.6841 | 6.8287 | 5.1981 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.36.0
|
78 |
+
- Pytorch 2.0.0
|
79 |
+
- Datasets 2.1.0
|
80 |
+
- Tokenizers 0.15.0
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.36.0"
|
6 |
+
}
|