Hugging Face's logo

SimoneJLaudani
/
trainerH

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
SimoneJLaudani commited on
Commit
1f396d1
•
1 Parent(s): a8c1494

End of training

Browse files
Files changed (14) hide show
  1. README.md +38 -46
  2. config.json +4 -3
  3. model.safetensors +2 -2
  4. runs/Apr02_21-05-02_5f77045950b4/events.out.tfevents.1712091912.5f77045950b4.4926.7 +3 -0
  5. runs/Apr02_21-06-06_5f77045950b4/events.out.tfevents.1712091973.5f77045950b4.4926.8 +3 -0
  6. runs/Apr02_21-08-29_5f77045950b4/events.out.tfevents.1712092349.5f77045950b4.4926.9 +3 -0
  7. runs/Apr02_21-08-29_5f77045950b4/events.out.tfevents.1712092426.5f77045950b4.4926.10 +3 -0
  8. runs/Apr02_21-15-20_5f77045950b4/events.out.tfevents.1712092526.5f77045950b4.4926.11 +3 -0
  9. runs/Apr02_21-16-05_5f77045950b4/events.out.tfevents.1712092570.5f77045950b4.4926.12 +3 -0
  10. runs/Apr02_21-18-28_5f77045950b4/events.out.tfevents.1712092716.5f77045950b4.4926.13 +3 -0
  11. runs/Apr02_21-18-28_5f77045950b4/events.out.tfevents.1712100197.5f77045950b4.4926.14 +3 -0
  12. tokenizer_config.json +1 -3
  13. training_args.bin +1 -1
  14. vocab.txt +0 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # trainerH
20
 
21
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.9240
24
- - Precision: 0.8148
25
- - Recall: 0.8095
26
- - F1: 0.8085
27
- - Accuracy: 0.8095
28
 
29
  ## Model description
30
 
@@ -49,54 +49,46 @@ The following hyperparameters were used during training:
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 5
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 1.9362 | 0.14 | 30 | 1.8590 | 0.2709 | 0.2521 | 0.2166 | 0.2521 |
59
- | 1.7693 | 0.27 | 60 | 1.5403 | 0.4339 | 0.4538 | 0.4032 | 0.4538 |
60
- | 1.4217 | 0.41 | 90 | 1.3401 | 0.4658 | 0.4706 | 0.3921 | 0.4706 |
61
- | 1.3121 | 0.54 | 120 | 1.1863 | 0.6652 | 0.6190 | 0.6092 | 0.6190 |
62
- | 1.1994 | 0.68 | 150 | 0.9959 | 0.7354 | 0.7115 | 0.7070 | 0.7115 |
63
- | 0.9937 | 0.81 | 180 | 0.8418 | 0.7401 | 0.7227 | 0.7093 | 0.7227 |
64
- | 0.7953 | 0.95 | 210 | 0.7477 | 0.7756 | 0.7563 | 0.7491 | 0.7563 |
65
- | 0.6038 | 1.08 | 240 | 0.6583 | 0.7882 | 0.7843 | 0.7827 | 0.7843 |
66
- | 0.5213 | 1.22 | 270 | 0.6735 | 0.7966 | 0.7843 | 0.7840 | 0.7843 |
67
- | 0.4313 | 1.35 | 300 | 0.6661 | 0.8142 | 0.7871 | 0.7855 | 0.7871 |
68
- | 0.4077 | 1.49 | 330 | 0.6784 | 0.7938 | 0.7731 | 0.7732 | 0.7731 |
69
- | 0.4095 | 1.62 | 360 | 0.6522 | 0.8064 | 0.7983 | 0.7978 | 0.7983 |
70
- | 0.3463 | 1.76 | 390 | 0.6827 | 0.8198 | 0.8095 | 0.8081 | 0.8095 |
71
- | 0.3221 | 1.89 | 420 | 0.7073 | 0.8190 | 0.7983 | 0.7947 | 0.7983 |
72
- | 0.3645 | 2.03 | 450 | 0.6673 | 0.8246 | 0.8179 | 0.8175 | 0.8179 |
73
- | 0.1191 | 2.16 | 480 | 0.7730 | 0.8005 | 0.7955 | 0.7928 | 0.7955 |
74
- | 0.1524 | 2.3 | 510 | 0.9105 | 0.8086 | 0.8011 | 0.7994 | 0.8011 |
75
- | 0.1701 | 2.43 | 540 | 0.8482 | 0.8003 | 0.7955 | 0.7939 | 0.7955 |
76
- | 0.2633 | 2.57 | 570 | 0.7490 | 0.8121 | 0.8039 | 0.8035 | 0.8039 |
77
- | 0.191 | 2.7 | 600 | 0.7528 | 0.8016 | 0.7955 | 0.7959 | 0.7955 |
78
- | 0.103 | 2.84 | 630 | 0.7891 | 0.8212 | 0.8151 | 0.8131 | 0.8151 |
79
- | 0.1179 | 2.97 | 660 | 0.7611 | 0.8128 | 0.8067 | 0.8048 | 0.8067 |
80
- | 0.065 | 3.11 | 690 | 0.7939 | 0.8208 | 0.8151 | 0.8141 | 0.8151 |
81
- | 0.088 | 3.24 | 720 | 0.8769 | 0.8099 | 0.7955 | 0.7941 | 0.7955 |
82
- | 0.1397 | 3.38 | 750 | 0.7566 | 0.8306 | 0.8263 | 0.8259 | 0.8263 |
83
- | 0.0526 | 3.51 | 780 | 0.7722 | 0.8176 | 0.8151 | 0.8136 | 0.8151 |
84
- | 0.0073 | 3.65 | 810 | 0.8817 | 0.8223 | 0.8123 | 0.8110 | 0.8123 |
85
- | 0.0564 | 3.78 | 840 | 0.9068 | 0.8277 | 0.8179 | 0.8155 | 0.8179 |
86
- | 0.0481 | 3.92 | 870 | 0.8703 | 0.8115 | 0.8067 | 0.8051 | 0.8067 |
87
- | 0.0573 | 4.05 | 900 | 0.8761 | 0.8300 | 0.8207 | 0.8205 | 0.8207 |
88
- | 0.0253 | 4.19 | 930 | 0.8925 | 0.8287 | 0.8207 | 0.8201 | 0.8207 |
89
- | 0.0067 | 4.32 | 960 | 0.9603 | 0.8069 | 0.7983 | 0.7964 | 0.7983 |
90
- | 0.0279 | 4.46 | 990 | 0.9283 | 0.8034 | 0.7983 | 0.7970 | 0.7983 |
91
- | 0.0133 | 4.59 | 1020 | 0.9180 | 0.8119 | 0.8067 | 0.8053 | 0.8067 |
92
- | 0.0154 | 4.73 | 1050 | 0.9232 | 0.8086 | 0.8039 | 0.8024 | 0.8039 |
93
- | 0.0207 | 4.86 | 1080 | 0.9236 | 0.8086 | 0.8039 | 0.8024 | 0.8039 |
94
- | 0.0305 | 5.0 | 1110 | 0.9240 | 0.8148 | 0.8095 | 0.8085 | 0.8095 |
95
 
96
 
97
  ### Framework versions
98
 
99
- - Transformers 4.39.2
100
  - Pytorch 2.2.1+cu121
101
  - Datasets 2.18.0
102
  - Tokenizers 0.15.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
18
 
19
  # trainerH
20
 
21
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.8441
24
+ - Precision: 0.8317
25
+ - Recall: 0.8263
26
+ - F1: 0.8264
27
+ - Accuracy: 0.8263
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 4
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 1.9384 | 0.14 | 30 | 1.8276 | 0.4095 | 0.2857 | 0.2208 | 0.2857 |
59
+ | 1.7136 | 0.27 | 60 | 1.4275 | 0.3928 | 0.4846 | 0.4071 | 0.4846 |
60
+ | 1.3598 | 0.41 | 90 | 1.1745 | 0.6202 | 0.5770 | 0.5490 | 0.5770 |
61
+ | 1.1651 | 0.54 | 120 | 1.0125 | 0.7164 | 0.6751 | 0.6557 | 0.6751 |
62
+ | 1.06 | 0.68 | 150 | 0.9011 | 0.7276 | 0.7031 | 0.6976 | 0.7031 |
63
+ | 0.9305 | 0.81 | 180 | 0.8200 | 0.7456 | 0.7087 | 0.6914 | 0.7087 |
64
+ | 0.7333 | 0.95 | 210 | 0.7067 | 0.7960 | 0.7619 | 0.7542 | 0.7619 |
65
+ | 0.5304 | 1.08 | 240 | 0.6204 | 0.8225 | 0.8067 | 0.8050 | 0.8067 |
66
+ | 0.4939 | 1.22 | 270 | 0.6531 | 0.8159 | 0.7843 | 0.7801 | 0.7843 |
67
+ | 0.4205 | 1.35 | 300 | 0.6128 | 0.8149 | 0.8039 | 0.8035 | 0.8039 |
68
+ | 0.3442 | 1.49 | 330 | 0.6345 | 0.8194 | 0.8067 | 0.8036 | 0.8067 |
69
+ | 0.3659 | 1.62 | 360 | 0.6248 | 0.7982 | 0.7955 | 0.7947 | 0.7955 |
70
+ | 0.3697 | 1.76 | 390 | 0.7024 | 0.7932 | 0.7871 | 0.7821 | 0.7871 |
71
+ | 0.2861 | 1.89 | 420 | 0.6599 | 0.8247 | 0.8179 | 0.8171 | 0.8179 |
72
+ | 0.3195 | 2.03 | 450 | 0.7034 | 0.8257 | 0.8207 | 0.8204 | 0.8207 |
73
+ | 0.158 | 2.16 | 480 | 0.6999 | 0.8312 | 0.8179 | 0.8164 | 0.8179 |
74
+ | 0.1053 | 2.3 | 510 | 0.7991 | 0.8225 | 0.8151 | 0.8144 | 0.8151 |
75
+ | 0.187 | 2.43 | 540 | 0.7483 | 0.8320 | 0.8235 | 0.8231 | 0.8235 |
76
+ | 0.1683 | 2.57 | 570 | 0.7192 | 0.8363 | 0.8319 | 0.8310 | 0.8319 |
77
+ | 0.1616 | 2.7 | 600 | 0.7693 | 0.8314 | 0.8263 | 0.8263 | 0.8263 |
78
+ | 0.124 | 2.84 | 630 | 0.7845 | 0.8337 | 0.8291 | 0.8288 | 0.8291 |
79
+ | 0.1188 | 2.97 | 660 | 0.8111 | 0.8398 | 0.8319 | 0.8321 | 0.8319 |
80
+ | 0.0636 | 3.11 | 690 | 0.7845 | 0.8317 | 0.8263 | 0.8259 | 0.8263 |
81
+ | 0.0876 | 3.24 | 720 | 0.8005 | 0.8289 | 0.8235 | 0.8235 | 0.8235 |
82
+ | 0.0181 | 3.38 | 750 | 0.8088 | 0.8308 | 0.8263 | 0.8262 | 0.8263 |
83
+ | 0.0491 | 3.51 | 780 | 0.8411 | 0.8283 | 0.8235 | 0.8237 | 0.8235 |
84
+ | 0.0228 | 3.65 | 810 | 0.8307 | 0.8348 | 0.8291 | 0.8290 | 0.8291 |
85
+ | 0.0857 | 3.78 | 840 | 0.8456 | 0.8353 | 0.8291 | 0.8293 | 0.8291 |
86
+ | 0.0431 | 3.92 | 870 | 0.8460 | 0.8317 | 0.8263 | 0.8264 | 0.8263 |
 
 
 
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
90
 
91
+ - Transformers 4.39.3
92
  - Pytorch 2.2.1+cu121
93
  - Datasets 2.18.0
94
  - Tokenizers 0.15.2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
@@ -31,6 +31,7 @@
31
  "model_type": "distilbert",
32
  "n_heads": 12,
33
  "n_layers": 6,
 
34
  "pad_token_id": 0,
35
  "problem_type": "single_label_classification",
36
  "qa_dropout": 0.1,
@@ -38,6 +39,6 @@
38
  "sinusoidal_pos_embds": false,
39
  "tie_weights_": true,
40
  "torch_dtype": "float32",
41
- "transformers_version": "4.39.2",
42
- "vocab_size": 30522
43
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-cased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
 
31
  "model_type": "distilbert",
32
  "n_heads": 12,
33
  "n_layers": 6,
34
+ "output_past": true,
35
  "pad_token_id": 0,
36
  "problem_type": "single_label_classification",
37
  "qa_dropout": 0.1,
 
39
  "sinusoidal_pos_embds": false,
40
  "tie_weights_": true,
41
  "torch_dtype": "float32",
42
+ "transformers_version": "4.39.3",
43
+ "vocab_size": 28996
44
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69d2daf8f453723480d2c5d837cdb9099dc77133b8bb6271dc8558017422722d
3
- size 267847948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d631bec8db3f323d100786c115afb1cdfd005f2bf446e1c53823cb48501f220
3
+ size 263160068
runs/Apr02_21-05-02_5f77045950b4/events.out.tfevents.1712091912.5f77045950b4.4926.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19add8d691a09b1bcb4e70ae5ed33474ccc0274caac40fa02427262ee902430c
3
+ size 4763
runs/Apr02_21-06-06_5f77045950b4/events.out.tfevents.1712091973.5f77045950b4.4926.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ec3e7d1d14fb698ec9cafe017f6a0f4048470441f97f94e9b83b012e3f9236
3
+ size 4763
runs/Apr02_21-08-29_5f77045950b4/events.out.tfevents.1712092349.5f77045950b4.4926.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f33e028d6cfed986ec69bde3d45c197c0946e1ae4f59b7dc9059518d3655add
3
+ size 4763
runs/Apr02_21-08-29_5f77045950b4/events.out.tfevents.1712092426.5f77045950b4.4926.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a6acdea1c8c1f6042b6ea6e0536eefc15b80878a77ab2fbdefcdd8ae49afe5
3
+ size 4763
runs/Apr02_21-15-20_5f77045950b4/events.out.tfevents.1712092526.5f77045950b4.4926.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12823151669a22b3021ec030d148226fb3403b313cddddbcbd7b92775ad90bb1
3
+ size 4763
runs/Apr02_21-16-05_5f77045950b4/events.out.tfevents.1712092570.5f77045950b4.4926.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42f01202ca060f8bf009770fec4d2a3e537f066dd913fea18ce3b7d2c92ccaa
3
+ size 4763
runs/Apr02_21-18-28_5f77045950b4/events.out.tfevents.1712092716.5f77045950b4.4926.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fabbee903cfb37973c535d3a36d3cb423712217c391a9db770056150cadc527
3
+ size 24885
runs/Apr02_21-18-28_5f77045950b4/events.out.tfevents.1712100197.5f77045950b4.4926.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93636616805335823cdee06c83c4aa7db483d46929ac2e582d9433913e4778be
3
+ size 560
tokenizer_config.json CHANGED
@@ -43,11 +43,9 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
- "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_lower_case": false,
 
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
 
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e4d5e579cb54793fe56674437c0d06448c302eaa2901282a3480ccd8bd2121c
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84990d5f97ee8ef3737cb22b4b2951f699ba3948a106d8c797a84b8d582a58f0
3
  size 4920
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff