Buho89 commited on
Commit
19cccb0
·
verified ·
1 Parent(s): b2db711

Training in progress, step 100

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: FacebookAI/xlm-roberta-large
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - conll2002
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
+ - accuracy
14
+ model-index:
15
+ - name: roberta-large-ner-qlorafinetune-runs-colab
16
+ results: []
17
+ ---
18
+
19
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+ # roberta-large-ner-qlorafinetune-runs-colab
23
+
24
+ This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the conll2002 dataset.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 0.0861
27
+ - Precision: 0.8792
28
+ - Recall: 0.8860
29
+ - F1: 0.8826
30
+ - Accuracy: 0.9817
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 0.0004
50
+ - train_batch_size: 32
51
+ - eval_batch_size: 32
52
+ - seed: 42
53
+ - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
+ - lr_scheduler_type: linear
55
+ - training_steps: 1820
56
+ - mixed_precision_training: Native AMP
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
+ | 1.1639 | 0.0766 | 20 | 0.4142 | 0.1415 | 0.0533 | 0.0774 | 0.8637 |
63
+ | 0.2638 | 0.1533 | 40 | 0.2052 | 0.5873 | 0.6105 | 0.5987 | 0.9471 |
64
+ | 0.1538 | 0.2299 | 60 | 0.1406 | 0.7147 | 0.7229 | 0.7188 | 0.9620 |
65
+ | 0.1021 | 0.3065 | 80 | 0.1212 | 0.7429 | 0.7847 | 0.7632 | 0.9682 |
66
+ | 0.1142 | 0.3831 | 100 | 0.1146 | 0.7883 | 0.7930 | 0.7906 | 0.9714 |
67
+ | 0.0836 | 0.4598 | 120 | 0.1066 | 0.8086 | 0.8263 | 0.8174 | 0.9741 |
68
+ | 0.0816 | 0.5364 | 140 | 0.0810 | 0.8441 | 0.8463 | 0.8452 | 0.9786 |
69
+ | 0.0867 | 0.6130 | 160 | 0.0784 | 0.8462 | 0.8557 | 0.8509 | 0.9786 |
70
+ | 0.0697 | 0.6897 | 180 | 0.0853 | 0.8248 | 0.8339 | 0.8293 | 0.9765 |
71
+ | 0.0719 | 0.7663 | 200 | 0.0755 | 0.8433 | 0.8555 | 0.8493 | 0.9795 |
72
+ | 0.0584 | 0.8429 | 220 | 0.0718 | 0.8492 | 0.8693 | 0.8591 | 0.9805 |
73
+ | 0.0553 | 0.9195 | 240 | 0.0792 | 0.8399 | 0.8580 | 0.8488 | 0.9775 |
74
+ | 0.049 | 0.9962 | 260 | 0.0748 | 0.8462 | 0.8725 | 0.8591 | 0.9798 |
75
+ | 0.0458 | 1.0728 | 280 | 0.0820 | 0.8180 | 0.8532 | 0.8352 | 0.9777 |
76
+ | 0.049 | 1.1494 | 300 | 0.0818 | 0.8490 | 0.8672 | 0.8580 | 0.9784 |
77
+ | 0.0521 | 1.2261 | 320 | 0.0757 | 0.8626 | 0.8727 | 0.8676 | 0.9795 |
78
+ | 0.0492 | 1.3027 | 340 | 0.0828 | 0.8284 | 0.8552 | 0.8416 | 0.9776 |
79
+ | 0.0517 | 1.3793 | 360 | 0.0808 | 0.8409 | 0.8523 | 0.8465 | 0.9780 |
80
+ | 0.0464 | 1.4559 | 380 | 0.0852 | 0.8385 | 0.8509 | 0.8447 | 0.9772 |
81
+ | 0.0487 | 1.5326 | 400 | 0.0761 | 0.8573 | 0.8656 | 0.8614 | 0.9782 |
82
+ | 0.0517 | 1.6092 | 420 | 0.0714 | 0.8403 | 0.8624 | 0.8512 | 0.9796 |
83
+ | 0.0587 | 1.6858 | 440 | 0.0700 | 0.8398 | 0.8603 | 0.8499 | 0.9806 |
84
+ | 0.0541 | 1.7625 | 460 | 0.0665 | 0.8679 | 0.8844 | 0.8761 | 0.9814 |
85
+ | 0.0459 | 1.8391 | 480 | 0.0677 | 0.8653 | 0.8736 | 0.8694 | 0.9807 |
86
+ | 0.0494 | 1.9157 | 500 | 0.0633 | 0.8707 | 0.8819 | 0.8763 | 0.9817 |
87
+ | 0.0412 | 1.9923 | 520 | 0.0717 | 0.8552 | 0.8660 | 0.8606 | 0.9801 |
88
+ | 0.048 | 2.0690 | 540 | 0.0735 | 0.8642 | 0.8757 | 0.8699 | 0.9797 |
89
+ | 0.0343 | 2.1456 | 560 | 0.0721 | 0.8574 | 0.8690 | 0.8632 | 0.9799 |
90
+ | 0.0276 | 2.2222 | 580 | 0.0784 | 0.8438 | 0.8612 | 0.8524 | 0.9800 |
91
+ | 0.0376 | 2.2989 | 600 | 0.0758 | 0.8459 | 0.8631 | 0.8544 | 0.9787 |
92
+ | 0.0334 | 2.3755 | 620 | 0.0736 | 0.8474 | 0.8578 | 0.8526 | 0.9791 |
93
+ | 0.0342 | 2.4521 | 640 | 0.0681 | 0.8523 | 0.8789 | 0.8654 | 0.9813 |
94
+ | 0.0325 | 2.5287 | 660 | 0.0708 | 0.8771 | 0.8837 | 0.8804 | 0.9814 |
95
+ | 0.0319 | 2.6054 | 680 | 0.0822 | 0.8703 | 0.8729 | 0.8716 | 0.9793 |
96
+ | 0.0376 | 2.6820 | 700 | 0.0733 | 0.8622 | 0.8727 | 0.8674 | 0.9793 |
97
+ | 0.034 | 2.7586 | 720 | 0.0686 | 0.8808 | 0.8867 | 0.8838 | 0.9825 |
98
+ | 0.0342 | 2.8352 | 740 | 0.0693 | 0.8654 | 0.8819 | 0.8736 | 0.9813 |
99
+ | 0.0334 | 2.9119 | 760 | 0.0718 | 0.8686 | 0.8867 | 0.8775 | 0.9813 |
100
+ | 0.0366 | 2.9885 | 780 | 0.0661 | 0.8775 | 0.8888 | 0.8831 | 0.9823 |
101
+ | 0.0433 | 3.0651 | 800 | 0.0785 | 0.8434 | 0.8787 | 0.8607 | 0.9805 |
102
+ | 0.0257 | 3.1418 | 820 | 0.0773 | 0.8705 | 0.8759 | 0.8732 | 0.9805 |
103
+ | 0.0264 | 3.2184 | 840 | 0.0791 | 0.8736 | 0.8812 | 0.8774 | 0.9801 |
104
+ | 0.0256 | 3.2950 | 860 | 0.0756 | 0.8591 | 0.8716 | 0.8653 | 0.9801 |
105
+ | 0.0229 | 3.3716 | 880 | 0.0751 | 0.8656 | 0.8748 | 0.8702 | 0.9801 |
106
+ | 0.0276 | 3.4483 | 900 | 0.0808 | 0.8440 | 0.8665 | 0.8551 | 0.9775 |
107
+ | 0.0374 | 3.5249 | 920 | 0.0685 | 0.8824 | 0.8899 | 0.8862 | 0.9820 |
108
+ | 0.0243 | 3.6015 | 940 | 0.0738 | 0.8776 | 0.8863 | 0.8819 | 0.9817 |
109
+ | 0.027 | 3.6782 | 960 | 0.0741 | 0.8761 | 0.8835 | 0.8798 | 0.9813 |
110
+ | 0.0225 | 3.7548 | 980 | 0.0674 | 0.8895 | 0.9012 | 0.8953 | 0.9830 |
111
+ | 0.0285 | 3.8314 | 1000 | 0.0702 | 0.8801 | 0.8886 | 0.8843 | 0.9827 |
112
+ | 0.0251 | 3.9080 | 1020 | 0.0745 | 0.8767 | 0.8842 | 0.8804 | 0.9810 |
113
+ | 0.0297 | 3.9847 | 1040 | 0.0713 | 0.8782 | 0.8867 | 0.8825 | 0.9820 |
114
+ | 0.0177 | 4.0613 | 1060 | 0.0805 | 0.8784 | 0.8851 | 0.8818 | 0.9814 |
115
+ | 0.0211 | 4.1379 | 1080 | 0.0842 | 0.8802 | 0.8812 | 0.8807 | 0.9812 |
116
+ | 0.0182 | 4.2146 | 1100 | 0.0771 | 0.8747 | 0.8874 | 0.8810 | 0.9814 |
117
+ | 0.0187 | 4.2912 | 1120 | 0.0844 | 0.8737 | 0.8851 | 0.8794 | 0.9813 |
118
+ | 0.017 | 4.3678 | 1140 | 0.0779 | 0.8834 | 0.8929 | 0.8881 | 0.9822 |
119
+ | 0.0203 | 4.4444 | 1160 | 0.0806 | 0.8798 | 0.8913 | 0.8855 | 0.9822 |
120
+ | 0.0176 | 4.5211 | 1180 | 0.0839 | 0.8740 | 0.8865 | 0.8802 | 0.9804 |
121
+ | 0.0168 | 4.5977 | 1200 | 0.0862 | 0.8759 | 0.8835 | 0.8797 | 0.9809 |
122
+ | 0.0199 | 4.6743 | 1220 | 0.0795 | 0.8747 | 0.8869 | 0.8808 | 0.9819 |
123
+ | 0.0238 | 4.7510 | 1240 | 0.0785 | 0.8680 | 0.8782 | 0.8731 | 0.9807 |
124
+ | 0.0204 | 4.8276 | 1260 | 0.0775 | 0.8638 | 0.8741 | 0.8689 | 0.9800 |
125
+ | 0.0205 | 4.9042 | 1280 | 0.0770 | 0.8699 | 0.8805 | 0.8752 | 0.9813 |
126
+ | 0.0161 | 4.9808 | 1300 | 0.0764 | 0.8744 | 0.8817 | 0.8780 | 0.9813 |
127
+ | 0.0145 | 5.0575 | 1320 | 0.0794 | 0.8755 | 0.8874 | 0.8814 | 0.9817 |
128
+ | 0.0124 | 5.1341 | 1340 | 0.0790 | 0.8851 | 0.8886 | 0.8868 | 0.9823 |
129
+ | 0.016 | 5.2107 | 1360 | 0.0818 | 0.8823 | 0.8890 | 0.8857 | 0.9815 |
130
+ | 0.0151 | 5.2874 | 1380 | 0.0806 | 0.8844 | 0.8879 | 0.8861 | 0.9823 |
131
+ | 0.0112 | 5.3640 | 1400 | 0.0833 | 0.8784 | 0.8844 | 0.8814 | 0.9813 |
132
+ | 0.0141 | 5.4406 | 1420 | 0.0841 | 0.8805 | 0.8840 | 0.8822 | 0.9810 |
133
+ | 0.0137 | 5.5172 | 1440 | 0.0851 | 0.8850 | 0.8879 | 0.8864 | 0.9822 |
134
+ | 0.0167 | 5.5939 | 1460 | 0.0830 | 0.8807 | 0.8853 | 0.8830 | 0.9816 |
135
+ | 0.0154 | 5.6705 | 1480 | 0.0808 | 0.8721 | 0.8819 | 0.8770 | 0.9810 |
136
+ | 0.0114 | 5.7471 | 1500 | 0.0816 | 0.8816 | 0.8897 | 0.8856 | 0.9820 |
137
+ | 0.0123 | 5.8238 | 1520 | 0.0832 | 0.8769 | 0.8835 | 0.8802 | 0.9814 |
138
+ | 0.0151 | 5.9004 | 1540 | 0.0863 | 0.8735 | 0.8778 | 0.8756 | 0.9807 |
139
+ | 0.0113 | 5.9770 | 1560 | 0.0874 | 0.8719 | 0.8805 | 0.8762 | 0.9807 |
140
+ | 0.0076 | 6.0536 | 1580 | 0.0896 | 0.8763 | 0.8826 | 0.8795 | 0.9814 |
141
+ | 0.0098 | 6.1303 | 1600 | 0.0880 | 0.8838 | 0.8876 | 0.8857 | 0.9819 |
142
+ | 0.0104 | 6.2069 | 1620 | 0.0887 | 0.8760 | 0.8812 | 0.8786 | 0.9807 |
143
+ | 0.0108 | 6.2835 | 1640 | 0.0854 | 0.8773 | 0.8837 | 0.8805 | 0.9815 |
144
+ | 0.0116 | 6.3602 | 1660 | 0.0830 | 0.8837 | 0.8888 | 0.8862 | 0.9820 |
145
+ | 0.0105 | 6.4368 | 1680 | 0.0838 | 0.8827 | 0.8890 | 0.8859 | 0.9820 |
146
+ | 0.0092 | 6.5134 | 1700 | 0.0847 | 0.8794 | 0.8879 | 0.8836 | 0.9817 |
147
+ | 0.0105 | 6.5900 | 1720 | 0.0842 | 0.8778 | 0.8865 | 0.8821 | 0.9819 |
148
+ | 0.0114 | 6.6667 | 1740 | 0.0847 | 0.8802 | 0.8863 | 0.8832 | 0.9818 |
149
+ | 0.0089 | 6.7433 | 1760 | 0.0851 | 0.8794 | 0.8865 | 0.8829 | 0.9819 |
150
+ | 0.0104 | 6.8199 | 1780 | 0.0861 | 0.8797 | 0.8856 | 0.8826 | 0.9816 |
151
+ | 0.0099 | 6.8966 | 1800 | 0.0863 | 0.8804 | 0.8860 | 0.8832 | 0.9816 |
152
+ | 0.0078 | 6.9732 | 1820 | 0.0861 | 0.8792 | 0.8860 | 0.8826 | 0.9817 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - PEFT 0.13.2
158
+ - Transformers 4.47.0
159
+ - Pytorch 2.5.1+cu121
160
+ - Datasets 3.2.0
161
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "FacebookAI/xlm-roberta-large",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": [
18
+ "classifier",
19
+ "score"
20
+ ],
21
+ "peft_type": "LORA",
22
+ "r": 256,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "query",
27
+ "key",
28
+ "dense",
29
+ "value"
30
+ ],
31
+ "task_type": "TOKEN_CLS",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d862a46ee58cb78259191081b428d91cbb7217e3ced1c487feba42b7ad116bad
3
+ size 453150800
runs/Dec11_00-18-37_1e297c6b4493/events.out.tfevents.1733876322.1e297c6b4493.920.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5778a0855cb024f67a4c8f5bf4143a9768bac3b569edcaf4e7dcfe7ab362b7
3
+ size 68484
runs/Dec11_01-56-58_1e297c6b4493/events.out.tfevents.1733882242.1e297c6b4493.920.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:920a2aa6e9f8941fa77fa68fd3a41140c65f2b4942b31d3353c37db33cd2775c
3
+ size 10453
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feba82f9289979360599a18e45f4fd53716e565a507fea2b42c357e009c98e5f
3
+ size 5368