Hugging Face's logo

AlexMason00
/
bert-LoRA-reminder

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
AlexMason00 commited on
Commit
f436f53
·
verified ·
1 Parent(s): 3623d94

End of training

Browse files
Files changed (3) hide show
  1. README.md +33 -33
  2. adapter_model.safetensors +1 -1
  3. runs/Apr26_12-43-43_fc5a5e47cb22/events.out.tfevents.1714135424.fc5a5e47cb22.20994.0 +2 -2
README.md CHANGED
@@ -3,7 +3,7 @@ license: mit
3
  library_name: peft
4
  tags:
5
  - generated_from_trainer
6
- base_model: dbmdz/bert-base-italian-xxl-cased
7
  metrics:
8
  - accuracy
9
  model-index:
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # bert-LoRA-reminder
18
 
19
- This model is a fine-tuned version of [dbmdz/bert-base-italian-xxl-cased](https://huggingface.co/dbmdz/bert-base-italian-xxl-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2044
22
  - Accuracy: 0.9545
23
 
24
  ## Model description
@@ -50,36 +50,36 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 0.6763 | 1.0 | 22 | 0.6823 | 0.5455 |
54
- | 0.6657 | 2.0 | 44 | 0.6662 | 0.5682 |
55
- | 0.6704 | 3.0 | 66 | 0.6538 | 0.6136 |
56
- | 0.6667 | 4.0 | 88 | 0.6362 | 0.6818 |
57
- | 0.6594 | 5.0 | 110 | 0.6168 | 0.8182 |
58
- | 0.6213 | 6.0 | 132 | 0.5956 | 0.8864 |
59
- | 0.6057 | 7.0 | 154 | 0.5703 | 0.8864 |
60
- | 0.5977 | 8.0 | 176 | 0.5545 | 0.8864 |
61
- | 0.5932 | 9.0 | 198 | 0.5368 | 0.8636 |
62
- | 0.5647 | 10.0 | 220 | 0.5074 | 0.8864 |
63
- | 0.5479 | 11.0 | 242 | 0.4885 | 0.8864 |
64
- | 0.5465 | 12.0 | 264 | 0.4595 | 0.8864 |
65
- | 0.5026 | 13.0 | 286 | 0.4309 | 0.9091 |
66
- | 0.4548 | 14.0 | 308 | 0.4011 | 0.9091 |
67
- | 0.4372 | 15.0 | 330 | 0.3721 | 0.9318 |
68
- | 0.4509 | 16.0 | 352 | 0.3521 | 0.9318 |
69
- | 0.4398 | 17.0 | 374 | 0.3327 | 0.9318 |
70
- | 0.4186 | 18.0 | 396 | 0.3113 | 0.9545 |
71
- | 0.3781 | 19.0 | 418 | 0.2953 | 0.9545 |
72
- | 0.3638 | 20.0 | 440 | 0.2847 | 0.9318 |
73
- | 0.3604 | 21.0 | 462 | 0.2631 | 0.9545 |
74
- | 0.4001 | 22.0 | 484 | 0.2504 | 0.9545 |
75
- | 0.3346 | 23.0 | 506 | 0.2417 | 0.9545 |
76
- | 0.3041 | 24.0 | 528 | 0.2303 | 0.9545 |
77
- | 0.3504 | 25.0 | 550 | 0.2218 | 0.9545 |
78
- | 0.286 | 26.0 | 572 | 0.2152 | 0.9545 |
79
- | 0.3526 | 27.0 | 594 | 0.2102 | 0.9545 |
80
- | 0.2657 | 28.0 | 616 | 0.2066 | 0.9545 |
81
- | 0.3019 | 29.0 | 638 | 0.2052 | 0.9545 |
82
- | 0.307 | 30.0 | 660 | 0.2044 | 0.9545 |
83
 
84
 
85
  ### Framework versions
 
3
  library_name: peft
4
  tags:
5
  - generated_from_trainer
6
+ base_model: dbmdz/bert-base-italian-uncased
7
  metrics:
8
  - accuracy
9
  model-index:
 
16
 
17
  # bert-LoRA-reminder
18
 
19
+ This model is a fine-tuned version of [dbmdz/bert-base-italian-uncased](https://huggingface.co/dbmdz/bert-base-italian-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2139
22
  - Accuracy: 0.9545
23
 
24
  ## Model description
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.6677 | 1.0 | 22 | 0.6283 | 0.7955 |
54
+ | 0.6524 | 2.0 | 44 | 0.6168 | 0.8409 |
55
+ | 0.6299 | 3.0 | 66 | 0.6096 | 0.8182 |
56
+ | 0.6258 | 4.0 | 88 | 0.5980 | 0.8636 |
57
+ | 0.6206 | 5.0 | 110 | 0.5849 | 0.8409 |
58
+ | 0.5685 | 6.0 | 132 | 0.5694 | 0.8636 |
59
+ | 0.5896 | 7.0 | 154 | 0.5528 | 0.8864 |
60
+ | 0.5636 | 8.0 | 176 | 0.5361 | 0.8636 |
61
+ | 0.5681 | 9.0 | 198 | 0.5217 | 0.8864 |
62
+ | 0.5575 | 10.0 | 220 | 0.4968 | 0.8864 |
63
+ | 0.5097 | 11.0 | 242 | 0.4776 | 0.9091 |
64
+ | 0.5001 | 12.0 | 264 | 0.4541 | 0.9091 |
65
+ | 0.4712 | 13.0 | 286 | 0.4269 | 0.9318 |
66
+ | 0.4462 | 14.0 | 308 | 0.4016 | 0.9318 |
67
+ | 0.4255 | 15.0 | 330 | 0.3778 | 0.9545 |
68
+ | 0.3943 | 16.0 | 352 | 0.3566 | 0.9545 |
69
+ | 0.3889 | 17.0 | 374 | 0.3358 | 0.9545 |
70
+ | 0.3845 | 18.0 | 396 | 0.3169 | 0.9545 |
71
+ | 0.3397 | 19.0 | 418 | 0.2987 | 0.9545 |
72
+ | 0.3677 | 20.0 | 440 | 0.2862 | 0.9545 |
73
+ | 0.3271 | 21.0 | 462 | 0.2729 | 0.9545 |
74
+ | 0.3495 | 22.0 | 484 | 0.2607 | 0.9545 |
75
+ | 0.3057 | 23.0 | 506 | 0.2495 | 0.9545 |
76
+ | 0.2621 | 24.0 | 528 | 0.2399 | 0.9545 |
77
+ | 0.2911 | 25.0 | 550 | 0.2314 | 0.9545 |
78
+ | 0.2685 | 26.0 | 572 | 0.2253 | 0.9545 |
79
+ | 0.248 | 27.0 | 594 | 0.2200 | 0.9545 |
80
+ | 0.2421 | 28.0 | 616 | 0.2164 | 0.9545 |
81
+ | 0.2688 | 29.0 | 638 | 0.2147 | 0.9545 |
82
+ | 0.2723 | 30.0 | 660 | 0.2139 | 0.9545 |
83
 
84
 
85
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:043fc8d8e743c6aaf62cb9ec4844a0d2f8fd9cab0621af5d3436cd172f310317
3
  size 160400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a136b3e30fb7f7dfb4954d1b3b96fab2d598e4457b3aea8a56cd54b89d99c3
3
  size 160400
runs/Apr26_12-43-43_fc5a5e47cb22/events.out.tfevents.1714135424.fc5a5e47cb22.20994.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d9f9ef58159e9a17573e374e44bf32daddd50f14a0d08e6a1181b8ded41ab27
3
- size 22223
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd4f4670b240c25d2b504448185d4f856193d7ffe03c36f342116781dced9ad
3
+ size 28537