Hugging Face's logo

gniemiec
/
mt5-small-finetuned-xsum

Text2Text Generation Transformers PyTorch TensorBoard
mt5 generated_from_trainer Eval Results Inference Endpoints text-generation-inference
Model card Files Metrics Community
2
gniemiec commited on
Commit
1b7410e
•
1 Parent(s): fc6f730

add model

Browse files
Files changed (4) hide show
  1. README.md +10 -10
  2. runs/Sep21_12-04-25_cadff6dd71cd/1632226261.0087423/events.out.tfevents.1632226261.cadff6dd71cd.90.1 +3 -0
  3. runs/Sep21_12-04-25_cadff6dd71cd/events.out.tfevents.1632226260.cadff6dd71cd.90.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Rouge1
21
  type: rouge
22
- value: 2.8314
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
30
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the xsum dataset.
31
  It achieves the following results on the evaluation set:
32
  - Loss: nan
33
- - Rouge1: 2.8314
34
- - Rouge2: 0.3142
35
- - Rougel: 2.6475
36
- - Rougelsum: 2.6485
37
  - Gen Len: 4.9416
38
 
39
  ## Model description
@@ -54,8 +54,8 @@ More information needed
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 2e-05
57
- - train_batch_size: 8
58
- - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
68
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
69
- | nan | 1.0 | 6377 | nan | 2.8314 | 0.3142 | 2.6475 | 2.6485 | 4.9416 |
70
 
71
 
72
  ### Framework versions
19
  metrics:
20
  - name: Rouge1
21
  type: rouge
22
+ value: 2.8351
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
  This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the xsum dataset.
31
  It achieves the following results on the evaluation set:
32
  - Loss: nan
33
+ - Rouge1: 2.8351
34
+ - Rouge2: 0.3143
35
+ - Rougel: 2.6488
36
+ - Rougelsum: 2.6463
37
  - Gen Len: 4.9416
38
 
39
  ## Model description
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 2e-05
57
+ - train_batch_size: 16
58
+ - eval_batch_size: 16
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
69
+ | nan | 1.0 | 12753 | nan | 2.8351 | 0.3143 | 2.6488 | 2.6463 | 4.9416 |
70
 
71
 
72
  ### Framework versions
runs/Sep21_12-04-25_cadff6dd71cd/1632226261.0087423/events.out.tfevents.1632226261.cadff6dd71cd.90.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70397e2e242259734c3f26b1d10ee53d54ca66cdb9e63faff0adf9934515334e
3
+ size 4450
runs/Sep21_12-04-25_cadff6dd71cd/events.out.tfevents.1632226260.cadff6dd71cd.90.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba4136f5b139d0be1de2821aa4837d4383243e42a39d83fa524e71bf4487996
3
+ size 7915
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2c4fc316d12e82918e897fb14271d4f2cf16d2fd193ddb5f481ea2e7082a6f0
3
  size 2799
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804275309efbc57096b328641731daaa2c05b66f35a20796e77d6de5c5ff371f
3
  size 2799