Hugging Face's logo

AlmogMor345
/
my_awesome_model

Token Classification
Transformers
TensorFlow
distilbert
generated_from_keras_callback
Model card Files
xet
 Community
AlmogMor345 commited on
Commit
f15fa2d
·
1 Parent(s): aeebdfc

Training in progress epoch 0

Browse files
Files changed (4) hide show
  1. README.md +11 -109
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
  4. tokenizer_config.json +1 -1
README.md CHANGED
@@ -14,13 +14,13 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.2654
18
- - Validation Loss: 0.4115
19
- - Train Precision: 0.3171
20
- - Train Recall: 0.2316
21
- - Train F1: 0.2677
22
- - Train Accuracy: 0.9237
23
- - Epoch: 98
24
 
25
  ## Model description
26
 
@@ -39,117 +39,19 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 300, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
43
  - training_precision: float32
44
 
45
  ### Training results
46
 
47
  | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
48
  |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
49
- | 2.6686 | 2.0689 | 0.0 | 0.0 | 0.0 | 0.9140 | 0 |
50
- | 1.6820 | 1.1778 | 0.0 | 0.0 | 0.0 | 0.9140 | 1 |
51
- | 1.0504 | 0.7035 | 0.0 | 0.0 | 0.0 | 0.9140 | 2 |
52
- | 0.6313 | 0.5891 | 0.0 | 0.0 | 0.0 | 0.9140 | 3 |
53
- | 0.5843 | 0.5567 | 0.0 | 0.0 | 0.0 | 0.9140 | 4 |
54
- | 0.5171 | 0.5498 | 0.0 | 0.0 | 0.0 | 0.9140 | 5 |
55
- | 0.5841 | 0.5460 | 0.0 | 0.0 | 0.0 | 0.9140 | 6 |
56
- | 0.4974 | 0.5408 | 0.0 | 0.0 | 0.0 | 0.9140 | 7 |
57
- | 0.5809 | 0.5344 | 0.0 | 0.0 | 0.0 | 0.9140 | 8 |
58
- | 0.5262 | 0.5307 | 0.0 | 0.0 | 0.0 | 0.9140 | 9 |
59
- | 0.5099 | 0.5265 | 0.0 | 0.0 | 0.0 | 0.9140 | 10 |
60
- | 0.4552 | 0.5213 | 0.0 | 0.0 | 0.0 | 0.9140 | 11 |
61
- | 0.5308 | 0.5167 | 0.0 | 0.0 | 0.0 | 0.9140 | 12 |
62
- | 0.4778 | 0.5127 | 0.0 | 0.0 | 0.0 | 0.9140 | 13 |
63
- | 0.5030 | 0.5086 | 0.0 | 0.0 | 0.0 | 0.9140 | 14 |
64
- | 0.4281 | 0.5042 | 0.0 | 0.0 | 0.0 | 0.9140 | 15 |
65
- | 0.5538 | 0.5005 | 0.0 | 0.0 | 0.0 | 0.9140 | 16 |
66
- | 0.4368 | 0.4935 | 0.0 | 0.0 | 0.0 | 0.9140 | 17 |
67
- | 0.4503 | 0.4880 | 0.0 | 0.0 | 0.0 | 0.9140 | 18 |
68
- | 0.4546 | 0.4816 | 0.0 | 0.0 | 0.0 | 0.9140 | 19 |
69
- | 0.4267 | 0.4743 | 0.0 | 0.0 | 0.0 | 0.9140 | 20 |
70
- | 0.4535 | 0.4667 | 0.0 | 0.0 | 0.0 | 0.9140 | 21 |
71
- | 0.4546 | 0.4592 | 0.0 | 0.0 | 0.0 | 0.9140 | 22 |
72
- | 0.3890 | 0.4662 | 0.0 | 0.0 | 0.0 | 0.9140 | 23 |
73
- | 0.4579 | 0.4476 | 0.0 | 0.0 | 0.0 | 0.9140 | 24 |
74
- | 0.4745 | 0.4473 | 0.0 | 0.0 | 0.0 | 0.9140 | 25 |
75
- | 0.3569 | 0.4440 | 0.0 | 0.0 | 0.0 | 0.9140 | 26 |
76
- | 0.4133 | 0.4320 | 0.0 | 0.0 | 0.0 | 0.9140 | 27 |
77
- | 0.4219 | 0.4297 | 0.0 | 0.0 | 0.0 | 0.9140 | 28 |
78
- | 0.5131 | 0.4289 | 0.0 | 0.0 | 0.0 | 0.9140 | 29 |
79
- | 0.4068 | 0.4199 | 0.0 | 0.0 | 0.0 | 0.9140 | 30 |
80
- | 0.4136 | 0.4176 | 0.0 | 0.0 | 0.0 | 0.9140 | 31 |
81
- | 0.3237 | 0.4178 | 0.0 | 0.0 | 0.0 | 0.9140 | 32 |
82
- | 0.4391 | 0.4130 | 0.0 | 0.0 | 0.0 | 0.9140 | 33 |
83
- | 0.3532 | 0.4125 | 0.0 | 0.0 | 0.0 | 0.9140 | 34 |
84
- | 0.3137 | 0.4118 | 0.3333 | 0.0012 | 0.0024 | 0.9141 | 35 |
85
- | 0.3363 | 0.4087 | 0.3077 | 0.0048 | 0.0094 | 0.9143 | 36 |
86
- | 0.3243 | 0.4073 | 0.2381 | 0.0059 | 0.0116 | 0.9143 | 37 |
87
- | 0.3739 | 0.4069 | 0.2333 | 0.0083 | 0.0161 | 0.9143 | 38 |
88
- | 0.3774 | 0.4035 | 0.2203 | 0.0154 | 0.0289 | 0.9148 | 39 |
89
- | 0.3370 | 0.4034 | 0.2459 | 0.0178 | 0.0332 | 0.9149 | 40 |
90
- | 0.3775 | 0.4049 | 0.2542 | 0.0178 | 0.0333 | 0.9149 | 41 |
91
- | 0.3195 | 0.4005 | 0.2810 | 0.0404 | 0.0706 | 0.9161 | 42 |
92
- | 0.2774 | 0.4009 | 0.2941 | 0.0416 | 0.0728 | 0.9162 | 43 |
93
- | 0.3702 | 0.4007 | 0.2771 | 0.0546 | 0.0913 | 0.9171 | 44 |
94
- | 0.3367 | 0.4003 | 0.2556 | 0.0677 | 0.1070 | 0.9178 | 45 |
95
- | 0.3210 | 0.4030 | 0.2954 | 0.0831 | 0.1297 | 0.9188 | 46 |
96
- | 0.3540 | 0.3994 | 0.2661 | 0.1128 | 0.1585 | 0.9198 | 47 |
97
- | 0.3181 | 0.4002 | 0.2771 | 0.1152 | 0.1628 | 0.9202 | 48 |
98
- | 0.2839 | 0.4025 | 0.2861 | 0.1128 | 0.1618 | 0.9202 | 49 |
99
- | 0.3065 | 0.4001 | 0.2723 | 0.1342 | 0.1798 | 0.9205 | 50 |
100
- | 0.3143 | 0.4008 | 0.2734 | 0.1354 | 0.1811 | 0.9207 | 51 |
101
- | 0.2258 | 0.4017 | 0.2787 | 0.1354 | 0.1823 | 0.9213 | 52 |
102
- | 0.2755 | 0.4016 | 0.2748 | 0.1413 | 0.1867 | 0.9213 | 53 |
103
- | 0.3415 | 0.4004 | 0.2589 | 0.1461 | 0.1868 | 0.9208 | 54 |
104
- | 0.2846 | 0.4035 | 0.2715 | 0.1461 | 0.1900 | 0.9214 | 55 |
105
- | 0.3056 | 0.4013 | 0.2632 | 0.1544 | 0.1946 | 0.9211 | 56 |
106
- | 0.2296 | 0.3992 | 0.2397 | 0.1591 | 0.1913 | 0.9197 | 57 |
107
- | 0.2061 | 0.4043 | 0.2667 | 0.1520 | 0.1936 | 0.9216 | 58 |
108
- | 0.2989 | 0.4056 | 0.2668 | 0.1508 | 0.1927 | 0.9215 | 59 |
109
- | 0.2897 | 0.4016 | 0.2529 | 0.1568 | 0.1935 | 0.9205 | 60 |
110
- | 0.2991 | 0.4035 | 0.2672 | 0.1568 | 0.1976 | 0.9212 | 61 |
111
- | 0.3058 | 0.4020 | 0.2704 | 0.1651 | 0.2050 | 0.9215 | 62 |
112
- | 0.2282 | 0.4029 | 0.2599 | 0.1639 | 0.2010 | 0.9207 | 63 |
113
- | 0.2824 | 0.4090 | 0.2759 | 0.1520 | 0.1960 | 0.9220 | 64 |
114
- | 0.2809 | 0.4034 | 0.2478 | 0.1698 | 0.2016 | 0.9200 | 65 |
115
- | 0.2198 | 0.4028 | 0.2434 | 0.1758 | 0.2041 | 0.9195 | 66 |
116
- | 0.2783 | 0.4116 | 0.2755 | 0.1603 | 0.2027 | 0.9216 | 67 |
117
- | 0.2525 | 0.4113 | 0.2766 | 0.1639 | 0.2058 | 0.9217 | 68 |
118
- | 0.2590 | 0.4038 | 0.2577 | 0.1888 | 0.2180 | 0.9204 | 69 |
119
- | 0.2058 | 0.4041 | 0.2573 | 0.1876 | 0.2170 | 0.9206 | 70 |
120
- | 0.3008 | 0.4170 | 0.3173 | 0.1722 | 0.2232 | 0.9231 | 71 |
121
- | 0.2704 | 0.4116 | 0.3086 | 0.1829 | 0.2297 | 0.9231 | 72 |
122
- | 0.2458 | 0.4037 | 0.2848 | 0.2138 | 0.2442 | 0.9216 | 73 |
123
- | 0.2232 | 0.4054 | 0.3 | 0.2102 | 0.2472 | 0.9225 | 74 |
124
- | 0.2216 | 0.4111 | 0.3107 | 0.1900 | 0.2358 | 0.9232 | 75 |
125
- | 0.2228 | 0.4095 | 0.3104 | 0.1983 | 0.2420 | 0.9231 | 76 |
126
- | 0.2580 | 0.4060 | 0.3023 | 0.2233 | 0.2568 | 0.9226 | 77 |
127
- | 0.2394 | 0.4059 | 0.2987 | 0.2257 | 0.2571 | 0.9225 | 78 |
128
- | 0.2262 | 0.4076 | 0.3053 | 0.2197 | 0.2555 | 0.9231 | 79 |
129
- | 0.2467 | 0.4103 | 0.3114 | 0.2078 | 0.2493 | 0.9237 | 80 |
130
- | 0.2287 | 0.4106 | 0.3131 | 0.2078 | 0.2498 | 0.9239 | 81 |
131
- | 0.2365 | 0.4071 | 0.3081 | 0.2268 | 0.2613 | 0.9232 | 82 |
132
- | 0.2394 | 0.4060 | 0.2956 | 0.2328 | 0.2605 | 0.9223 | 83 |
133
- | 0.2313 | 0.4101 | 0.3164 | 0.2150 | 0.2560 | 0.9240 | 84 |
134
- | 0.1960 | 0.4143 | 0.3283 | 0.2055 | 0.2527 | 0.9242 | 85 |
135
- | 0.2632 | 0.4121 | 0.3196 | 0.2114 | 0.2545 | 0.9241 | 86 |
136
- | 0.2322 | 0.4088 | 0.3145 | 0.2316 | 0.2668 | 0.9235 | 87 |
137
- | 0.2986 | 0.4077 | 0.2977 | 0.2352 | 0.2628 | 0.9222 | 88 |
138
- | 0.2244 | 0.4088 | 0.3063 | 0.2328 | 0.2645 | 0.9228 | 89 |
139
- | 0.2290 | 0.4112 | 0.3206 | 0.2292 | 0.2673 | 0.9242 | 90 |
140
- | 0.2422 | 0.4119 | 0.3216 | 0.2280 | 0.2669 | 0.9244 | 91 |
141
- | 0.2780 | 0.4114 | 0.3190 | 0.2292 | 0.2668 | 0.9240 | 92 |
142
- | 0.2645 | 0.4118 | 0.3211 | 0.2292 | 0.2675 | 0.9242 | 93 |
143
- | 0.2482 | 0.4116 | 0.3234 | 0.2328 | 0.2707 | 0.9242 | 94 |
144
- | 0.2989 | 0.4118 | 0.3224 | 0.2328 | 0.2703 | 0.9241 | 95 |
145
- | 0.2072 | 0.4117 | 0.3213 | 0.2328 | 0.2700 | 0.9240 | 96 |
146
- | 0.3276 | 0.4116 | 0.3160 | 0.2304 | 0.2665 | 0.9236 | 97 |
147
- | 0.2654 | 0.4115 | 0.3171 | 0.2316 | 0.2677 | 0.9237 | 98 |
148
 
149
 
150
  ### Framework versions
151
 
152
- - Transformers 4.27.4
153
  - TensorFlow 2.12.0
154
  - Datasets 2.11.0
155
- - Tokenizers 0.13.2
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.6690
18
+ - Validation Loss: 2.1130
19
+ - Train Precision: 0.0
20
+ - Train Recall: 0.0
21
+ - Train F1: 0.0
22
+ - Train Accuracy: 0.9140
23
+ - Epoch: 0
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 9, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
43
  - training_precision: float32
44
 
45
  ### Training results
46
 
47
  | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
48
  |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
49
+ | 2.6690 | 2.1130 | 0.0 | 0.0 | 0.0 | 0.9140 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
 
51
 
52
  ### Framework versions
53
 
54
+ - Transformers 4.28.1
55
  - TensorFlow 2.12.0
56
  - Datasets 2.11.0
57
+ - Tokenizers 0.13.3
config.json CHANGED
@@ -60,6 +60,6 @@
60
  "seq_classif_dropout": 0.2,
61
  "sinusoidal_pos_embds": false,
62
  "tie_weights_": true,
63
- "transformers_version": "4.27.4",
64
  "vocab_size": 30522
65
  }
 
60
  "seq_classif_dropout": 0.2,
61
  "sinusoidal_pos_embds": false,
62
  "tie_weights_": true,
63
+ "transformers_version": "4.28.1",
64
  "vocab_size": 30522
65
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1617c918f5bbca1edad853fee467390db581531c42405d54dc68441f8305b5ad
3
  size 265637136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24212659859c29e92a9f859fde8a05b625f872e13820721a6f408bf82978457
3
  size 265637136
tokenizer_config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
 
2
  "cls_token": "[CLS]",
3
  "do_lower_case": false,
4
  "mask_token": "[MASK]",
5
  "model_max_length": 512,
6
  "pad_token": "[PAD]",
7
  "sep_token": "[SEP]",
8
- "special_tokens_map_file": null,
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
  "tokenizer_class": "BertTokenizer",
 
1
  {
2
+ "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
  "do_lower_case": false,
5
  "mask_token": "[MASK]",
6
  "model_max_length": 512,
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
 
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
  "tokenizer_class": "BertTokenizer",