Hugging Face's logo

ncoder-incite
/
flan-t5-small-chat

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
ncoder-incite commited on
Commit
69018bc
•
1 Parent(s): f9c898f

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +2 -2
README.md CHANGED
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2367
21
- - Rouge1: 49.588
22
- - Rouge2: 44.597
23
- - Rougel: 46.6928
24
- - Rougelsum: 46.662
25
- - Gen Len: 19.0
26
 
27
  ## Model description
28
 
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
- | No log | 1.0 | 26 | 1.0858 | 4.9303 | 0.674 | 4.7306 | 4.7335 | 8.1731 |
57
- | No log | 2.0 | 52 | 0.5339 | 39.1598 | 30.9426 | 39.0844 | 39.1597 | 16.3462 |
58
- | No log | 3.0 | 78 | 0.2892 | 47.1834 | 41.288 | 45.1755 | 45.1471 | 19.0 |
59
- | No log | 4.0 | 104 | 0.2367 | 49.588 | 44.597 | 46.6928 | 46.662 | 19.0 |
60
 
61
 
62
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0455
21
+ - Rouge1: 93.7107
22
+ - Rouge2: 87.4214
23
+ - Rougel: 93.7107
24
+ - Rougelsum: 93.7107
25
+ - Gen Len: 3.0
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
+ | No log | 1.0 | 318 | 0.0494 | 93.5535 | 87.1069 | 93.5535 | 93.5535 | 3.0 |
57
+ | 0.0889 | 2.0 | 636 | 0.0468 | 93.5535 | 87.1069 | 93.5535 | 93.5535 | 3.0 |
58
+ | 0.0889 | 3.0 | 954 | 0.0447 | 94.4182 | 88.8365 | 94.4182 | 94.4182 | 3.0 |
59
+ | 0.0448 | 4.0 | 1272 | 0.0455 | 93.7107 | 87.4214 | 93.7107 | 93.7107 | 3.0 |
60
 
61
 
62
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76972e7e63fef9cfa4d748932e582684f1f3934a1f37ed524972f5ae64ff4154
3
  size 307907906
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67660aaf5e7a3b0a854848f0b9f012c0b7aab356dfc1112c4b7c12b3425e6b2
3
  size 307907906
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 88,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 88
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 4,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 4
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,