Hugging Face's logo

Boulou2107
/
comic-name-classification

PEFT
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
Boulou2107 commited on
Commit
b220a6f
•
1 Parent(s): a24bced

Boulou2107/comic-name-classification

Browse files
Files changed (11) hide show
  1. README.md +64 -9
  2. adapter_config.json +12 -4
  3. adapter_model.safetensors +3 -0
  4. runs/Jan06_22-35-13_Boulou_Computer/events.out.tfevents.1704576915.Boulou_Computer.24228.25 +3 -0
  5. runs/Jan06_22-40-04_Boulou_Computer/events.out.tfevents.1704577205.Boulou_Computer.24228.26 +3 -0
  6. runs/Jan06_22-43-53_Boulou_Computer/events.out.tfevents.1704577435.Boulou_Computer.24228.27 +3 -0
  7. runs/Jan06_22-49-33_Boulou_Computer/events.out.tfevents.1704577774.Boulou_Computer.24228.28 +3 -0
  8. runs/Jan06_22-54-13_Boulou_Computer/events.out.tfevents.1704578054.Boulou_Computer.34744.0 +3 -0
  9. runs/Jan06_22-55-58_Boulou_Computer/events.out.tfevents.1704578159.Boulou_Computer.34744.1 +3 -0
  10. runs/Jan06_23-01-32_Boulou_Computer/events.out.tfevents.1704578493.Boulou_Computer.34744.2 +3 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,11 @@
1
  ---
2
  license: apache-2.0
3
- base_model: bert-base-multilingual-cased
4
  tags:
5
  - generated_from_trainer
 
 
 
6
  model-index:
7
  - name: comic-name-classification
8
  results: []
@@ -15,13 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.0353
19
- - eval_accuracy: 0.9956
20
- - eval_runtime: 0.2126
21
- - eval_samples_per_second: 940.682
22
- - eval_steps_per_second: 32.924
23
- - epoch: 50.0
24
- - step: 1250
25
 
26
  ## Model description
27
 
@@ -48,9 +46,66 @@ The following hyperparameters were used during training:
48
  - lr_scheduler_type: linear
49
  - num_epochs: 50
50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  ### Framework versions
52
 
 
53
  - Transformers 4.37.0.dev0
54
  - Pytorch 2.1.0+cu121
55
  - Datasets 2.15.0
56
- - Tokenizers 0.15.0
 
1
  ---
2
  license: apache-2.0
3
+ library_name: peft
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ base_model: bert-base-multilingual-cased
9
  model-index:
10
  - name: comic-name-classification
11
  results: []
 
18
 
19
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0445
22
+ - Accuracy: 0.9937
 
 
 
 
 
23
 
24
  ## Model description
25
 
 
46
  - lr_scheduler_type: linear
47
  - num_epochs: 50
48
 
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 25 | 0.0311 | 0.9933 |
54
+ | No log | 2.0 | 50 | 0.0330 | 0.9937 |
55
+ | No log | 3.0 | 75 | 0.0330 | 0.9933 |
56
+ | No log | 4.0 | 100 | 0.0350 | 0.9941 |
57
+ | No log | 5.0 | 125 | 0.0358 | 0.9937 |
58
+ | No log | 6.0 | 150 | 0.0363 | 0.9937 |
59
+ | No log | 7.0 | 175 | 0.0379 | 0.9945 |
60
+ | No log | 8.0 | 200 | 0.0356 | 0.9941 |
61
+ | No log | 9.0 | 225 | 0.0352 | 0.9941 |
62
+ | No log | 10.0 | 250 | 0.0376 | 0.9941 |
63
+ | No log | 11.0 | 275 | 0.0374 | 0.9941 |
64
+ | No log | 12.0 | 300 | 0.0387 | 0.9937 |
65
+ | No log | 13.0 | 325 | 0.0384 | 0.9941 |
66
+ | No log | 14.0 | 350 | 0.0392 | 0.9941 |
67
+ | No log | 15.0 | 375 | 0.0392 | 0.9941 |
68
+ | No log | 16.0 | 400 | 0.0394 | 0.9941 |
69
+ | No log | 17.0 | 425 | 0.0412 | 0.9945 |
70
+ | No log | 18.0 | 450 | 0.0404 | 0.9941 |
71
+ | No log | 19.0 | 475 | 0.0410 | 0.9941 |
72
+ | 0.0039 | 20.0 | 500 | 0.0414 | 0.9941 |
73
+ | 0.0039 | 21.0 | 525 | 0.0425 | 0.9941 |
74
+ | 0.0039 | 22.0 | 550 | 0.0416 | 0.9941 |
75
+ | 0.0039 | 23.0 | 575 | 0.0431 | 0.9941 |
76
+ | 0.0039 | 24.0 | 600 | 0.0439 | 0.9941 |
77
+ | 0.0039 | 25.0 | 625 | 0.0443 | 0.9941 |
78
+ | 0.0039 | 26.0 | 650 | 0.0440 | 0.9937 |
79
+ | 0.0039 | 27.0 | 675 | 0.0435 | 0.9937 |
80
+ | 0.0039 | 28.0 | 700 | 0.0428 | 0.9941 |
81
+ | 0.0039 | 29.0 | 725 | 0.0424 | 0.9941 |
82
+ | 0.0039 | 30.0 | 750 | 0.0431 | 0.9941 |
83
+ | 0.0039 | 31.0 | 775 | 0.0438 | 0.9941 |
84
+ | 0.0039 | 32.0 | 800 | 0.0419 | 0.9941 |
85
+ | 0.0039 | 33.0 | 825 | 0.0419 | 0.9941 |
86
+ | 0.0039 | 34.0 | 850 | 0.0416 | 0.9941 |
87
+ | 0.0039 | 35.0 | 875 | 0.0419 | 0.9941 |
88
+ | 0.0039 | 36.0 | 900 | 0.0430 | 0.9945 |
89
+ | 0.0039 | 37.0 | 925 | 0.0431 | 0.9941 |
90
+ | 0.0039 | 38.0 | 950 | 0.0439 | 0.9941 |
91
+ | 0.0039 | 39.0 | 975 | 0.0445 | 0.9937 |
92
+ | 0.0021 | 40.0 | 1000 | 0.0449 | 0.9937 |
93
+ | 0.0021 | 41.0 | 1025 | 0.0456 | 0.9941 |
94
+ | 0.0021 | 42.0 | 1050 | 0.0459 | 0.9941 |
95
+ | 0.0021 | 43.0 | 1075 | 0.0446 | 0.9937 |
96
+ | 0.0021 | 44.0 | 1100 | 0.0439 | 0.9941 |
97
+ | 0.0021 | 45.0 | 1125 | 0.0439 | 0.9941 |
98
+ | 0.0021 | 46.0 | 1150 | 0.0441 | 0.9941 |
99
+ | 0.0021 | 47.0 | 1175 | 0.0443 | 0.9941 |
100
+ | 0.0021 | 48.0 | 1200 | 0.0443 | 0.9937 |
101
+ | 0.0021 | 49.0 | 1225 | 0.0444 | 0.9937 |
102
+ | 0.0021 | 50.0 | 1250 | 0.0445 | 0.9937 |
103
+
104
+
105
  ### Framework versions
106
 
107
+ - PEFT 0.7.1
108
  - Transformers 4.37.0.dev0
109
  - Pytorch 2.1.0+cu121
110
  - Datasets 2.15.0
111
+ - Tokenizers 0.15.0
adapter_config.json CHANGED
@@ -1,18 +1,26 @@
1
  {
 
 
2
  "base_model_name_or_path": "bert-base-multilingual-cased",
3
  "bias": "all",
4
- "enable_lora": null,
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
 
 
 
 
7
  "lora_alpha": 16,
8
  "lora_dropout": 0.2,
9
- "merge_weights": true,
 
10
  "modules_to_save": null,
11
  "peft_type": "LORA",
12
  "r": 16,
 
 
13
  "target_modules": [
14
- "query",
15
- "value"
16
  ],
17
  "task_type": "TOKEN_CLS"
18
  }
 
1
  {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
  "base_model_name_or_path": "bert-base-multilingual-cased",
5
  "bias": "all",
 
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
  "lora_alpha": 16,
13
  "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
  "modules_to_save": null,
17
  "peft_type": "LORA",
18
  "r": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
  "target_modules": [
22
+ "value",
23
+ "query"
24
  ],
25
  "task_type": "TOKEN_CLS"
26
  }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d831c9784414f3fc46e63de2a4aad8b24aa87aa7b315a2ae1b38d2c2bc399e34
3
+ size 2793840
runs/Jan06_22-35-13_Boulou_Computer/events.out.tfevents.1704576915.Boulou_Computer.24228.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1ce6ba4808aacf66e1a973622fe8ac53a0bbf2d1a010c08c8d7e4c58885198
3
+ size 21341
runs/Jan06_22-40-04_Boulou_Computer/events.out.tfevents.1704577205.Boulou_Computer.24228.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73f2772af04979073a0af0862810c46fba3742f1d98b5ba7b477d6417e94e9f
3
+ size 21029
runs/Jan06_22-43-53_Boulou_Computer/events.out.tfevents.1704577435.Boulou_Computer.24228.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38be598c77d121cc337e555930a4575fbb90efe60a7251c793a57259b0f4abcd
3
+ size 21341
runs/Jan06_22-49-33_Boulou_Computer/events.out.tfevents.1704577774.Boulou_Computer.24228.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e19cd79ab3df5932552ce763f2df52e7d7ff1b7f25c980fd807265d40b2155c
3
+ size 21029
runs/Jan06_22-54-13_Boulou_Computer/events.out.tfevents.1704578054.Boulou_Computer.34744.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c223259d32b4f0d0403683b291b9aa9da22d5f475fc5ccdbf31a0fdc3f3b4d5d
3
+ size 7107
runs/Jan06_22-55-58_Boulou_Computer/events.out.tfevents.1704578159.Boulou_Computer.34744.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe84a77274f13f02b5bc403898cbb90c0895eb06e41cb22a18744a85ee9eeb1c
3
+ size 21380
runs/Jan06_23-01-32_Boulou_Computer/events.out.tfevents.1704578493.Boulou_Computer.34744.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454fbc0b72cd5abc4e49b3778398ed6eb2ba3f1e57235614c9e4df5c713a5c08
3
+ size 21383
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab4d4408eb568aeb420f45cd3fa89de7ac68ce4731ec003907c3b45db9fc9496
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:322ad07e804328dafac2f1d58a6bf2667294d73e8bc56e6a8844e5186ee55107
3
  size 4728