Hugging Face's logo

Shakhovak
/
flan-t5-base-absa-multitask-joint

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
Shakhovak commited on
Commit
5473921
•
1 Parent(s): 2e75d9e

End of training

Browse files
Files changed (3) hide show
  1. README.md +26 -26
  2. model.safetensors +1 -1
  3. 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 [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1154
19
 
20
  ## Model description
21
 
@@ -47,31 +47,31 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 2.5623 | 0.16 | 200 | 0.4999 |
51
- | 0.524 | 0.32 | 400 | 0.3094 |
52
- | 0.3811 | 0.47 | 600 | 0.2566 |
53
- | 0.3097 | 0.63 | 800 | 0.2226 |
54
- | 0.2869 | 0.79 | 1000 | 0.1973 |
55
- | 0.2654 | 0.95 | 1200 | 0.1903 |
56
- | 0.2221 | 1.11 | 1400 | 0.1686 |
57
- | 0.2115 | 1.27 | 1600 | 0.1692 |
58
- | 0.1974 | 1.42 | 1800 | 0.1635 |
59
- | 0.1945 | 1.58 | 2000 | 0.1500 |
60
- | 0.1868 | 1.74 | 2200 | 0.1420 |
61
- | 0.1827 | 1.9 | 2400 | 0.1418 |
62
- | 0.1788 | 2.06 | 2600 | 0.1331 |
63
- | 0.1489 | 2.22 | 2800 | 0.1456 |
64
- | 0.1475 | 2.37 | 3000 | 0.1341 |
65
- | 0.1419 | 2.53 | 3200 | 0.1254 |
66
- | 0.1521 | 2.69 | 3400 | 0.1232 |
67
- | 0.1374 | 2.85 | 3600 | 0.1213 |
68
- | 0.148 | 3.01 | 3800 | 0.1220 |
69
- | 0.1219 | 3.16 | 4000 | 0.1196 |
70
- | 0.1252 | 3.32 | 4200 | 0.1251 |
71
- | 0.1231 | 3.48 | 4400 | 0.1184 |
72
- | 0.1219 | 3.64 | 4600 | 0.1160 |
73
- | 0.1258 | 3.8 | 4800 | 0.1148 |
74
- | 0.1145 | 3.96 | 5000 | 0.1154 |
75
 
76
 
77
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1276
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.5367 | 0.16 | 200 | 0.5267 |
51
+ | 0.5433 | 0.32 | 400 | 0.3377 |
52
+ | 0.3887 | 0.47 | 600 | 0.2688 |
53
+ | 0.3123 | 0.63 | 800 | 0.2205 |
54
+ | 0.2724 | 0.79 | 1000 | 0.2282 |
55
+ | 0.2627 | 0.95 | 1200 | 0.1881 |
56
+ | 0.2294 | 1.11 | 1400 | 0.1827 |
57
+ | 0.2221 | 1.27 | 1600 | 0.1844 |
58
+ | 0.1957 | 1.42 | 1800 | 0.1860 |
59
+ | 0.2007 | 1.58 | 2000 | 0.1674 |
60
+ | 0.1866 | 1.74 | 2200 | 0.1628 |
61
+ | 0.175 | 1.9 | 2400 | 0.1636 |
62
+ | 0.1637 | 2.06 | 2600 | 0.1506 |
63
+ | 0.1541 | 2.22 | 2800 | 0.1505 |
64
+ | 0.1484 | 2.37 | 3000 | 0.1465 |
65
+ | 0.1442 | 2.53 | 3200 | 0.1496 |
66
+ | 0.1338 | 2.69 | 3400 | 0.1355 |
67
+ | 0.1415 | 2.85 | 3600 | 0.1369 |
68
+ | 0.1435 | 3.01 | 3800 | 0.1343 |
69
+ | 0.1242 | 3.16 | 4000 | 0.1348 |
70
+ | 0.1227 | 3.32 | 4200 | 0.1328 |
71
+ | 0.1229 | 3.48 | 4400 | 0.1287 |
72
+ | 0.1272 | 3.64 | 4600 | 0.1280 |
73
+ | 0.1132 | 3.8 | 4800 | 0.1264 |
74
+ | 0.1131 | 3.96 | 5000 | 0.1276 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c80a50c96e45df3f932896d7d5ce2c9133af23aa8d5e0f4f5f76bc5fefe9a1f
3
  size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2575e161e9581d86f1dba2718ea2ff43f083d481c65462a35c51128275d43ed6
3
  size 990345064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:648fa74e046885c613c55b23c4e31e9c4437ae27f184bb8419ef55dd267f0012
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e816c6799d88ab620ecd2f7813d6d260b2d2219f7ca2a7b2070b4e562c1422
3
  size 5112