Hugging Face's logo

bertrand-fournel
/
mt5-small-finetuned-summary

Summarization
Transformers
TensorBoard
Safetensors
mt5
text2text-generation
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bertrand-fournel commited on
Commit
749315e
•
1 Parent(s): 293a4eb

Training complete

Browse files
Files changed (5) hide show
  1. README.md +18 -18
  2. model.safetensors +1 -1
  3. runs/Dec21_13-19-52_933636919b14/events.out.tfevents.1703164807.933636919b14.2341.0 +3 -0
  4. runs/Dec21_13-19-52_933636919b14/events.out.tfevents.1703169591.933636919b14.2341.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Rouge1
25
  type: rouge
26
- value: 22.1761
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,11 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the xlsum dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 2.2770
37
- - Rouge1: 22.1761
38
- - Rouge2: 8.0115
39
- - Rougel: 18.8245
40
- - Rougelsum: 18.8574
41
 
42
  ## Model description
43
 
@@ -57,8 +57,8 @@ More information needed
57
 
58
  The following hyperparameters were used during training:
59
  - learning_rate: 5.6e-05
60
- - train_batch_size: 8
61
- - eval_batch_size: 8
62
  - seed: 42
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
@@ -66,16 +66,16 @@ The following hyperparameters were used during training:
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
70
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
71
- | 4.7862 | 1.0 | 1085 | 2.5085 | 21.2935 | 7.4006 | 18.0791 | 18.0868 |
72
- | 3.2212 | 2.0 | 2170 | 2.4069 | 21.968 | 7.9139 | 18.5785 | 18.6248 |
73
- | 3.0201 | 3.0 | 3255 | 2.3489 | 21.8529 | 7.9865 | 18.6842 | 18.7074 |
74
- | 2.9085 | 4.0 | 4340 | 2.3173 | 22.1605 | 8.2646 | 18.8284 | 18.838 |
75
- | 2.8285 | 5.0 | 5425 | 2.2965 | 22.0612 | 8.0447 | 18.7454 | 18.7784 |
76
- | 2.7727 | 6.0 | 6510 | 2.2899 | 22.1416 | 7.9747 | 18.7622 | 18.8029 |
77
- | 2.7311 | 7.0 | 7595 | 2.2797 | 22.2979 | 8.1382 | 18.9798 | 19.035 |
78
- | 2.7171 | 8.0 | 8680 | 2.2770 | 22.1761 | 8.0115 | 18.8245 | 18.8574 |
79
 
80
 
81
  ### Framework versions
 
23
  metrics:
24
  - name: Rouge1
25
  type: rouge
26
+ value: 21.6196
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the xlsum dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 2.1466
37
+ - Rouge1: 21.6196
38
+ - Rouge2: 7.7979
39
+ - Rougel: 17.5683
40
+ - Rougelsum: 17.6757
41
 
42
  ## Model description
43
 
 
57
 
58
  The following hyperparameters were used during training:
59
  - learning_rate: 5.6e-05
60
+ - train_batch_size: 4
61
+ - eval_batch_size: 4
62
  - seed: 42
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
 
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
70
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|
71
+ | 3.9629 | 1.0 | 2170 | 2.3132 | 20.7316 | 7.3431 | 16.9157 | 17.0149 |
72
+ | 2.9704 | 2.0 | 4340 | 2.2299 | 21.3148 | 7.8529 | 17.2968 | 17.3873 |
73
+ | 2.8026 | 3.0 | 6510 | 2.2092 | 21.3313 | 7.8526 | 17.3679 | 17.4773 |
74
+ | 2.7054 | 4.0 | 8680 | 2.1876 | 21.6909 | 7.9841 | 17.6881 | 17.7839 |
75
+ | 2.6453 | 5.0 | 10850 | 2.1743 | 21.7372 | 7.7546 | 17.6551 | 17.7575 |
76
+ | 2.5925 | 6.0 | 13020 | 2.1602 | 21.5715 | 7.7879 | 17.5943 | 17.6994 |
77
+ | 2.5619 | 7.0 | 15190 | 2.1482 | 21.5888 | 7.8789 | 17.6519 | 17.752 |
78
+ | 2.5415 | 8.0 | 17360 | 2.1466 | 21.6196 | 7.7979 | 17.5683 | 17.6757 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:895e88046a0ded0e59d0e4d1080048bb2816086f6d58e5b0bc58da522e8e4c13
3
  size 1200729512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848e7e6ae64c96fe695152910d63cb939d0911271f4c49dc3d1c399c2cb91498
3
  size 1200729512
runs/Dec21_13-19-52_933636919b14/events.out.tfevents.1703164807.933636919b14.2341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd511ed3187a9c38b9a8cb5f456ab36530055435e77ed2d66e1ad5e9183eeb5a
3
+ size 9948
runs/Dec21_13-19-52_933636919b14/events.out.tfevents.1703169591.933636919b14.2341.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782f2d86645f7acadfe052576c3a65ef30c91d2f0f82cafccb49a290112f9f1e
3
+ size 571
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:175ca495b9738068bf62e3e2a7951706e7865bcd427ea69948f90f546d54d82c
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b92679873c2bb0dfae3d7905ad0b6ba1ef6bfca04e3c4608770797a8fa262fd8
3
  size 4728