Hugging Face's logo

Shakhovak
/
flan-t5-xl-absa-multitask-laptops

Generated from Trainer
Model card Files Community
Shakhovak commited on
Commit
ae08aa5
·
verified ·
1 Parent(s): 98acd49

End of training

Browse files
Files changed (3) hide show
  1. README.md +32 -32
  2. adapter_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.1208
18
 
19
  ## Model description
20
 
@@ -46,37 +46,37 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 4.7847 | 0.32 | 200 | 3.2074 |
50
- | 1.4287 | 0.63 | 400 | 0.4428 |
51
- | 0.4472 | 0.95 | 600 | 0.2733 |
52
- | 0.3147 | 1.26 | 800 | 0.2284 |
53
- | 0.2677 | 1.58 | 1000 | 0.2058 |
54
- | 0.2405 | 1.9 | 1200 | 0.1909 |
55
- | 0.22 | 2.21 | 1400 | 0.1817 |
56
- | 0.1952 | 2.53 | 1600 | 0.1680 |
57
- | 0.1945 | 2.84 | 1800 | 0.1607 |
58
- | 0.179 | 3.16 | 2000 | 0.1524 |
59
- | 0.1635 | 3.48 | 2200 | 0.1506 |
60
- | 0.1581 | 3.79 | 2400 | 0.1521 |
61
- | 0.1492 | 4.11 | 2600 | 0.1473 |
62
- | 0.1436 | 4.42 | 2800 | 0.1418 |
63
- | 0.1385 | 4.74 | 3000 | 0.1340 |
64
- | 0.1416 | 5.06 | 3200 | 0.1355 |
65
- | 0.1326 | 5.37 | 3400 | 0.1276 |
66
- | 0.1255 | 5.69 | 3600 | 0.1307 |
67
- | 0.1312 | 6.0 | 3800 | 0.1263 |
68
- | 0.1224 | 6.32 | 4000 | 0.1235 |
69
- | 0.115 | 6.64 | 4200 | 0.1323 |
70
- | 0.1201 | 6.95 | 4400 | 0.1254 |
71
- | 0.1148 | 7.27 | 4600 | 0.1240 |
72
- | 0.1162 | 7.58 | 4800 | 0.1226 |
73
- | 0.1155 | 7.9 | 5000 | 0.1200 |
74
- | 0.1085 | 8.21 | 5200 | 0.1204 |
75
- | 0.1057 | 8.53 | 5400 | 0.1209 |
76
- | 0.1095 | 8.85 | 5600 | 0.1207 |
77
- | 0.1027 | 9.16 | 5800 | 0.1219 |
78
- | 0.101 | 9.48 | 6000 | 0.1217 |
79
- | 0.1169 | 9.79 | 6200 | 0.1208 |
80
 
81
 
82
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0986
18
 
19
  ## Model description
20
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 4.7611 | 0.32 | 200 | 3.2781 |
50
+ | 1.4428 | 0.63 | 400 | 0.4469 |
51
+ | 0.4548 | 0.95 | 600 | 0.2874 |
52
+ | 0.3146 | 1.26 | 800 | 0.2316 |
53
+ | 0.2675 | 1.58 | 1000 | 0.2096 |
54
+ | 0.2438 | 1.9 | 1200 | 0.1935 |
55
+ | 0.2244 | 2.21 | 1400 | 0.1714 |
56
+ | 0.2127 | 2.53 | 1600 | 0.1587 |
57
+ | 0.1927 | 2.84 | 1800 | 0.1541 |
58
+ | 0.1787 | 3.16 | 2000 | 0.1467 |
59
+ | 0.1715 | 3.48 | 2200 | 0.1350 |
60
+ | 0.1625 | 3.79 | 2400 | 0.1357 |
61
+ | 0.1579 | 4.11 | 2600 | 0.1304 |
62
+ | 0.1522 | 4.42 | 2800 | 0.1222 |
63
+ | 0.1417 | 4.74 | 3000 | 0.1204 |
64
+ | 0.1399 | 5.06 | 3200 | 0.1234 |
65
+ | 0.1303 | 5.37 | 3400 | 0.1211 |
66
+ | 0.1326 | 5.69 | 3600 | 0.1093 |
67
+ | 0.1241 | 6.0 | 3800 | 0.1090 |
68
+ | 0.1212 | 6.32 | 4000 | 0.1127 |
69
+ | 0.1189 | 6.64 | 4200 | 0.1045 |
70
+ | 0.124 | 6.95 | 4400 | 0.1077 |
71
+ | 0.1152 | 7.27 | 4600 | 0.1024 |
72
+ | 0.1141 | 7.58 | 4800 | 0.1008 |
73
+ | 0.1072 | 7.9 | 5000 | 0.1043 |
74
+ | 0.1146 | 8.21 | 5200 | 0.1011 |
75
+ | 0.1071 | 8.53 | 5400 | 0.0996 |
76
+ | 0.1149 | 8.85 | 5600 | 0.0990 |
77
+ | 0.1088 | 9.16 | 5800 | 0.1003 |
78
+ | 0.1064 | 9.48 | 6000 | 0.0988 |
79
+ | 0.1049 | 9.79 | 6200 | 0.0986 |
80
 
81
 
82
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a66dc8e18fb2e32eec55181bda8ae43784ee8ac8d083d409e9709344b77fd16
3
  size 37855242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a6bfc1ff95c358a45f865e3ee65a5c9700227eac69675246718a426335966f
3
  size 37855242
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c3e8f0b61375d1b1225020de253de43e1c098f313a5849e8c89da7880d0c2f5
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d3af44547131f829b7d522845b78f4059cec16846056d0f9ecd90b5369c9ed
3
  size 5112