Hugging Face's logo

fashxp
/
flan-t5-base-cars-descriptions

Text2Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
fashxp commited on
Commit
e5d4883
•
1 Parent(s): 3d85eb4

End of training

Browse files
Files changed (8) hide show
  1. README.md +13 -19
  2. logs/events.out.tfevents.1699954111.11ed68fc76de.295.0 +3 -0
  3. logs/events.out.tfevents.1699954904.11ed68fc76de.295.1 +3 -0
  4. logs/events.out.tfevents.1699954993.11ed68fc76de.295.2 +3 -0
  5. logs/events.out.tfevents.1699955218.11ed68fc76de.295.3 +3 -0
  6. logs/events.out.tfevents.1699955259.11ed68fc76de.295.4 +3 -0
  7. logs/events.out.tfevents.1699955359.11ed68fc76de.295.5 +3 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: nan
21
- - Rouge1: 17.8569
22
- - Rouge2: 9.8781
23
- - Rougel: 14.5368
24
- - Rougelsum: 17.194
25
- - Gen Len: 18.52
26
 
27
  ## Model description
28
 
@@ -47,23 +47,17 @@ The following hyperparameters were used during training:
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
- - num_epochs: 10
51
- - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
57
- | No log | 1.0 | 28 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
58
- | No log | 2.0 | 56 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
59
- | No log | 3.0 | 84 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
60
- | No log | 4.0 | 112 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
61
- | No log | 5.0 | 140 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
62
- | No log | 6.0 | 168 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
63
- | No log | 7.0 | 196 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
64
- | No log | 8.0 | 224 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
65
- | No log | 9.0 | 252 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
66
- | No log | 10.0 | 280 | nan | 17.8569 | 9.8781 | 14.5368 | 17.194 | 18.52 |
67
 
68
 
69
  ### Framework versions
 
18
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: nan
21
+ - Rouge1: 17.8813
22
+ - Rouge2: 10.4453
23
+ - Rougel: 15.9723
24
+ - Rougelsum: 17.3719
25
+ - Gen Len: 18.6
26
 
27
  ## Model description
28
 
 
47
  - seed: 42
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
+ - num_epochs: 5
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
+ | No log | 1.0 | 28 | nan | 17.8813 | 10.4453 | 15.9723 | 17.3719 | 18.6 |
57
+ | No log | 2.0 | 56 | nan | 17.8813 | 10.4453 | 15.9723 | 17.3719 | 18.6 |
58
+ | No log | 3.0 | 84 | nan | 17.8813 | 10.4453 | 15.9723 | 17.3719 | 18.6 |
59
+ | No log | 4.0 | 112 | nan | 17.8813 | 10.4453 | 15.9723 | 17.3719 | 18.6 |
60
+ | No log | 5.0 | 140 | nan | 17.8813 | 10.4453 | 15.9723 | 17.3719 | 18.6 |
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
logs/events.out.tfevents.1699954111.11ed68fc76de.295.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2d0602963b93f4786670690efa9bd663f65e0f8b3ea026febcdde15acf69bf
3
+ size 8229
logs/events.out.tfevents.1699954904.11ed68fc76de.295.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db12c1a4f5a3da6ff9a18d20e4ebfcf39e7a2e230d5fa02766c890927d40d2e
3
+ size 613
logs/events.out.tfevents.1699954993.11ed68fc76de.295.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b1dfea977b578b13ad2e020502f8ddbff16482d2988843013cf08e55b1c959
3
+ size 8228
logs/events.out.tfevents.1699955218.11ed68fc76de.295.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09844482a135b94d70ceaae30e72e08e446271d771555e8ce838833d120cecf
3
+ size 613
logs/events.out.tfevents.1699955259.11ed68fc76de.295.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99b92299a7fe7b32c39b7a9472d89d5d976477a791cc85381a79531ac7ecd6c
3
+ size 8229
logs/events.out.tfevents.1699955359.11ed68fc76de.295.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b21ea2b0ddf1d1bec6b30a013a160fbdeba459e9cfae24b563204083b2daf57
3
+ size 613
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e24582b723a0f434e11e89a8a3cb0978c63cb392cced979f802448fe8d460ab2
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ddca2f10a046bcbaa07b6c436ccba1a0d639aa59ebf2aef4ad7a9db6dda1f0
3
  size 4792