Hugging Face's logo

maxadmin
/
maximo-t5-chat

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
maxadmin commited on
Commit
683732c
•
1 Parent(s): 61d30cb

End of training

Browse files
Files changed (6) hide show
  1. README.md +16 -16
  2. model.safetensors +1 -1
  3. runs/Dec07_09-46-05_f973a9095c73/events.out.tfevents.1701942386.f973a9095c73.224.0 +3 -0
  4. runs/Dec07_09-46-05_f973a9095c73/events.out.tfevents.1701942512.f973a9095c73.224.1 +3 -0
  5. tokenizer.json +2 -2
  6. training_args.bin +1 -1
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: 0.7405
21
- - Rouge1: 52.8721
22
- - Rouge2: 36.7572
23
- - Rougel: 52.6723
24
- - Rougelsum: 52.7647
25
- - Gen Len: 14.9091
26
 
27
  ## Model description
28
 
@@ -53,16 +53,16 @@ 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 | 6 | 0.7775 | 45.4113 | 18.1818 | 45.3563 | 45.3447 | 14.2727 |
57
- | No log | 2.0 | 12 | 0.6883 | 47.2611 | 20.8343 | 47.2777 | 46.8606 | 14.2727 |
58
- | No log | 3.0 | 18 | 0.7010 | 54.3873 | 33.3491 | 54.1775 | 54.3223 | 14.0 |
59
- | No log | 4.0 | 24 | 0.7180 | 56.2604 | 35.7379 | 56.3303 | 56.0639 | 14.1818 |
60
- | No log | 5.0 | 30 | 0.7629 | 52.4292 | 33.3491 | 52.2935 | 52.3377 | 16.2727 |
61
- | No log | 6.0 | 36 | 0.7599 | 50.9191 | 32.3416 | 50.8317 | 50.979 | 14.8182 |
62
- | No log | 7.0 | 42 | 0.7521 | 52.2561 | 32.3416 | 51.8124 | 52.1745 | 13.3636 |
63
- | No log | 8.0 | 48 | 0.7503 | 54.2258 | 35.7576 | 54.4356 | 54.2957 | 13.4545 |
64
- | No log | 9.0 | 54 | 0.7429 | 52.8721 | 36.7572 | 52.6723 | 52.7647 | 14.9091 |
65
- | No log | 10.0 | 60 | 0.7405 | 52.8721 | 36.7572 | 52.6723 | 52.7647 | 14.9091 |
66
 
67
 
68
  ### 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: 2.3030
21
+ - Rouge1: 41.8615
22
+ - Rouge2: 34.5009
23
+ - Rougel: 42.1411
24
+ - Rougelsum: 41.8391
25
+ - Gen Len: 14.7857
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 | 7 | 1.9097 | 26.7567 | 11.5686 | 25.8411 | 25.338 | 15.7857 |
57
+ | No log | 2.0 | 14 | 2.0881 | 28.6356 | 20.3132 | 29.5342 | 28.913 | 15.9286 |
58
+ | No log | 3.0 | 21 | 2.0118 | 33.0671 | 16.081 | 33.7624 | 33.2398 | 16.6429 |
59
+ | No log | 4.0 | 28 | 2.1260 | 32.9158 | 16.7813 | 33.5121 | 32.7547 | 16.2143 |
60
+ | No log | 5.0 | 35 | 2.0860 | 38.3111 | 22.0194 | 38.8614 | 38.2719 | 14.4286 |
61
+ | No log | 6.0 | 42 | 2.2269 | 34.7021 | 21.9048 | 35.2641 | 34.7144 | 15.2143 |
62
+ | No log | 7.0 | 49 | 2.3382 | 40.1831 | 25.5322 | 40.7039 | 40.0726 | 15.5 |
63
+ | No log | 8.0 | 56 | 2.3151 | 38.6487 | 24.8332 | 39.0379 | 38.5125 | 15.5 |
64
+ | No log | 9.0 | 63 | 2.3079 | 41.8615 | 34.5009 | 42.1411 | 41.8391 | 14.7857 |
65
+ | No log | 10.0 | 70 | 2.3030 | 41.8615 | 34.5009 | 42.1411 | 41.8391 | 14.7857 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70445fd3cc0f4820b7d3ba99abc69512ab5a881e336a8666a9c100eebbb82468
3
  size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1232c4338c8e466fdffd2189bfd0a996fadbff594145105b9d3b49c33eb657f
3
  size 307867048
runs/Dec07_09-46-05_f973a9095c73/events.out.tfevents.1701942386.f973a9095c73.224.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2db8f8058a90a5739726725fa02a08331f2cd156962de22e70847ddb7001cd8c
3
+ size 10789
runs/Dec07_09-46-05_f973a9095c73/events.out.tfevents.1701942512.f973a9095c73.224.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbbe610a12b3abf039ed9ee8115817e01da3787f49bb343c5f26ba1c4763d59e
3
+ size 10817
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 48,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 48
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 339,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 339
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77eaf83fe48c9d90a02d9acf5caeecffcfcd0ef637f1c6ee56486ca2aac6cdee
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a09857ced197521626cf40f8d0fb9d965a5da9430a5b7fa8081f88d5a618347
3
  size 4728