Hugging Face's logo

Shakhovak
/
flan-t5-large-absa-multitask-rest

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Model card Files Community
Shakhovak commited on
Commit
27f8d75
·
verified ·
1 Parent(s): 3aacce3

End of training

Browse files
Files changed (3) hide show
  1. README.md +13 -13
  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-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1006
19
 
20
  ## Model description
21
 
@@ -47,18 +47,18 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 1.3649 | 0.32 | 200 | 0.2684 |
51
- | 0.2693 | 0.63 | 400 | 0.1816 |
52
- | 0.203 | 0.95 | 600 | 0.1584 |
53
- | 0.155 | 1.27 | 800 | 0.1516 |
54
- | 0.1258 | 1.58 | 1000 | 0.1296 |
55
- | 0.1191 | 1.9 | 1200 | 0.1186 |
56
- | 0.0989 | 2.22 | 1400 | 0.1085 |
57
- | 0.0801 | 2.53 | 1600 | 0.1126 |
58
- | 0.0765 | 2.85 | 1800 | 0.1084 |
59
- | 0.0613 | 3.16 | 2000 | 0.1035 |
60
- | 0.0525 | 3.48 | 2200 | 0.1055 |
61
- | 0.0554 | 3.8 | 2400 | 0.1006 |
62
 
63
 
64
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0807
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 1.3816 | 0.32 | 200 | 0.2912 |
51
+ | 0.2673 | 0.63 | 400 | 0.1971 |
52
+ | 0.2042 | 0.95 | 600 | 0.1625 |
53
+ | 0.1531 | 1.27 | 800 | 0.1406 |
54
+ | 0.1328 | 1.58 | 1000 | 0.1395 |
55
+ | 0.1214 | 1.9 | 1200 | 0.1135 |
56
+ | 0.1027 | 2.22 | 1400 | 0.1092 |
57
+ | 0.0808 | 2.53 | 1600 | 0.1041 |
58
+ | 0.0766 | 2.85 | 1800 | 0.0920 |
59
+ | 0.0586 | 3.16 | 2000 | 0.0855 |
60
+ | 0.053 | 3.48 | 2200 | 0.0851 |
61
+ | 0.0598 | 3.8 | 2400 | 0.0807 |
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a341fe2cf326596a686f8e4bbcecc58f41300711f22f2d0a50d787fcb8dfb58
3
  size 3132668808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558c17b5423df70ba8881225002dee8530cf4e7423871322c1f4e3e8d11962a3
3
  size 3132668808
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbd7ed198e2dd101e70dc0c3c3b35f087aaceba2ec6037c9b6a12dc31bc9622f
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51cac8d7a68d5ad12ee19217ad717b78b8049856faa09994b4b271e7e0c31fd6
3
  size 5112