Hugging Face's logo

tuquyennnn
/
LoRA-FlanT5-small-v2

PEFT
Safetensors
Generated from Trainer
Model card Files Community
tuquyennnn commited on
Commit
841ea9d
•
1 Parent(s): cde3622

End of training

Browse files
Files changed (4) hide show
  1. README.md +19 -19
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.1183
20
 
21
  ## Model description
22
 
@@ -49,24 +49,24 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 1.2283 | 0.32 | 250 | 0.1639 |
53
- | 0.1808 | 0.64 | 500 | 0.1314 |
54
- | 0.1624 | 0.96 | 750 | 0.1232 |
55
- | 0.1563 | 1.28 | 1000 | 0.1205 |
56
- | 0.153 | 1.61 | 1250 | 0.1194 |
57
- | 0.1519 | 1.93 | 1500 | 0.1189 |
58
- | 0.1527 | 2.25 | 1750 | 0.1187 |
59
- | 0.152 | 2.57 | 2000 | 0.1185 |
60
- | 0.1518 | 2.89 | 2250 | 0.1184 |
61
- | 0.1523 | 3.21 | 2500 | 0.1183 |
62
- | 0.1525 | 3.53 | 2750 | 0.1183 |
63
- | 0.1513 | 3.85 | 3000 | 0.1183 |
64
- | 0.1514 | 4.17 | 3250 | 0.1183 |
65
- | 0.1501 | 4.49 | 3500 | 0.1183 |
66
- | 0.1526 | 4.82 | 3750 | 0.1183 |
67
- | 0.1506 | 5.14 | 4000 | 0.1183 |
68
- | 0.1507 | 5.46 | 4250 | 0.1183 |
69
- | 0.1512 | 5.78 | 4500 | 0.1183 |
70
 
71
 
72
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1180
20
 
21
  ## Model description
22
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.2177 | 0.32 | 250 | 0.1693 |
53
+ | 0.1834 | 0.64 | 500 | 0.1321 |
54
+ | 0.1633 | 0.96 | 750 | 0.1227 |
55
+ | 0.1567 | 1.28 | 1000 | 0.1201 |
56
+ | 0.1533 | 1.61 | 1250 | 0.1189 |
57
+ | 0.1521 | 1.93 | 1500 | 0.1185 |
58
+ | 0.1531 | 2.25 | 1750 | 0.1182 |
59
+ | 0.1524 | 2.57 | 2000 | 0.1181 |
60
+ | 0.1523 | 2.89 | 2250 | 0.1181 |
61
+ | 0.1527 | 3.21 | 2500 | 0.1181 |
62
+ | 0.1527 | 3.53 | 2750 | 0.1180 |
63
+ | 0.152 | 3.85 | 3000 | 0.1181 |
64
+ | 0.1518 | 4.17 | 3250 | 0.1180 |
65
+ | 0.1504 | 4.49 | 3500 | 0.1180 |
66
+ | 0.1528 | 4.82 | 3750 | 0.1180 |
67
+ | 0.1511 | 5.14 | 4000 | 0.1180 |
68
+ | 0.1511 | 5.46 | 4250 | 0.1180 |
69
+ | 0.1517 | 5.78 | 4500 | 0.1180 |
70
 
71
 
72
  ### Framework versions
adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v",
24
- "q"
25
  ],
26
  "task_type": "SEQ_2_SEQ_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q",
24
+ "v"
25
  ],
26
  "task_type": "SEQ_2_SEQ_LM",
27
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea1b08a95481866f2c44513ea5a67807972a131da86a046510c068c83b0812b0
3
  size 2765976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b594e8c2c4a519270b3f458f369a0d208267c69cd5ffe086236298fa84d26003
3
  size 2765976
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8eb740be88baefb42c32a1549b52cc12407a52a616870b4a11959bacf1a4f044
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50839991ae2635ea3cd4d0e2f84cc99f7261ba8dfa109ffa97bc018265bb0086
3
  size 5112