Hugging Face's logo

AkshayPM
/
t5base-fine-tuned

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
spamacc commited on
Commit
b7cf15a
·
verified ·
1 Parent(s): 5df164e

End of training

Browse files
Files changed (5) hide show
  1. README.md +8 -46
  2. model.safetensors +1 -1
  3. runs/Feb24_14-19-34_803a7d951df0/events.out.tfevents.1708784376.803a7d951df0.186.0 +3 -0
  4. runs/Feb24_14-40-04_803a7d951df0/events.out.tfevents.1708785608.803a7d951df0.186.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.1159
19
 
20
  ## Model description
21
 
@@ -35,58 +35,20 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
- - train_batch_size: 4
39
- - eval_batch_size: 4
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 10
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:-----:|:----:|:---------------:|
50
- | 7.3659 | 0.25 | 50 | 1.9097 |
51
- | 1.9985 | 0.5 | 100 | 1.4844 |
52
- | 1.6183 | 0.75 | 150 | 1.3711 |
53
- | 1.5081 | 1.0 | 200 | 1.3077 |
54
- | 1.6322 | 1.25 | 250 | 1.2699 |
55
- | 1.3102 | 1.5 | 300 | 1.2420 |
56
- | 1.3373 | 1.75 | 350 | 1.2210 |
57
- | 1.394 | 2.0 | 400 | 1.2076 |
58
- | 1.307 | 2.25 | 450 | 1.1983 |
59
- | 1.3833 | 2.5 | 500 | 1.1872 |
60
- | 1.3781 | 2.75 | 550 | 1.1795 |
61
- | 1.2789 | 3.0 | 600 | 1.1735 |
62
- | 1.3799 | 3.25 | 650 | 1.1669 |
63
- | 1.2484 | 3.5 | 700 | 1.1608 |
64
- | 1.2521 | 3.75 | 750 | 1.1567 |
65
- | 1.2993 | 4.0 | 800 | 1.1518 |
66
- | 1.292 | 4.25 | 850 | 1.1488 |
67
- | 1.2883 | 4.5 | 900 | 1.1457 |
68
- | 1.2818 | 4.75 | 950 | 1.1419 |
69
- | 1.2097 | 5.0 | 1000 | 1.1384 |
70
- | 1.2208 | 5.25 | 1050 | 1.1365 |
71
- | 1.2032 | 5.5 | 1100 | 1.1340 |
72
- | 1.289 | 5.75 | 1150 | 1.1324 |
73
- | 1.2823 | 6.0 | 1200 | 1.1300 |
74
- | 1.2483 | 6.25 | 1250 | 1.1280 |
75
- | 1.2979 | 6.5 | 1300 | 1.1264 |
76
- | 1.2026 | 6.75 | 1350 | 1.1249 |
77
- | 1.1895 | 7.0 | 1400 | 1.1233 |
78
- | 1.2289 | 7.25 | 1450 | 1.1221 |
79
- | 1.2826 | 7.5 | 1500 | 1.1211 |
80
- | 1.1931 | 7.75 | 1550 | 1.1200 |
81
- | 1.1996 | 8.0 | 1600 | 1.1193 |
82
- | 1.2496 | 8.25 | 1650 | 1.1185 |
83
- | 1.2058 | 8.5 | 1700 | 1.1179 |
84
- | 1.2414 | 8.75 | 1750 | 1.1171 |
85
- | 1.1789 | 9.0 | 1800 | 1.1166 |
86
- | 1.3075 | 9.25 | 1850 | 1.1162 |
87
- | 1.1766 | 9.5 | 1900 | 1.1159 |
88
- | 1.1738 | 9.75 | 1950 | 1.1160 |
89
- | 1.2038 | 10.0 | 2000 | 1.1159 |
90
 
91
 
92
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.8941
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 2e-05
38
+ - train_batch_size: 6
39
+ - eval_batch_size: 6
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 2
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.7534 | 0.86 | 10000 | 0.6521 |
51
+ | 0.9127 | 1.72 | 20000 | 0.8941 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
 
53
 
54
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42ae200804d7e1bbdbe0841aa494b7cf377d9dd922c72a5f376de9a459fae1c1
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c743a9551de0d8498e60c57de9217b98e3a45f7af2c2ae696377d6616110e3
3
  size 891644712
runs/Feb24_14-19-34_803a7d951df0/events.out.tfevents.1708784376.803a7d951df0.186.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61e2a0e3c61eb3b892300c6d917eae5f2f98a169be39ecc34835394225c24c8d
3
+ size 5667
runs/Feb24_14-40-04_803a7d951df0/events.out.tfevents.1708785608.803a7d951df0.186.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f322821a880104135290089fdad044eea95bb29ac09a69ba23513492b76084b
3
+ size 6582
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:567e418bba0733a80eeb1eb02adab6b050b0eb19536dc85f07e2ad1335dc33d6
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e86fa45c23b1f841a99f409b1f0b7cdc6488be4fa7a84ff40fa0775ce20e33bb
3
  size 4856