Hugging Face's logo

stulcrad
/
CNEC1_1_Supertypes_xlm-roberta-large

Token Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
1767805
·
verified ·
1 Parent(s): 2a008a5

Model save

Browse files
Files changed (3) hide show
  1. README.md +60 -21
  2. model.safetensors +1 -1
  3. runs/Mar19_02-46-31_n30/events.out.tfevents.1710812793.n30.592725.0 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.814618211514904
29
  - name: Recall
30
  type: recall
31
- value: 0.8819628647214854
32
  - name: F1
33
  type: f1
34
- value: 0.8469539375928677
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9609664701979
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.2034
48
- - Precision: 0.8146
49
- - Recall: 0.8820
50
- - F1: 0.8470
51
- - Accuracy: 0.9610
52
 
53
  ## Model description
54
 
@@ -68,24 +68,63 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
- - train_batch_size: 32
72
- - eval_batch_size: 32
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - lr_scheduler_warmup_ratio: 0.1
77
- - lr_scheduler_warmup_steps: 500
78
- - num_epochs: 20
79
 
80
  ### Training results
81
 
82
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
83
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
84
- | 0.8235 | 3.4 | 500 | 0.1975 | 0.7474 | 0.8148 | 0.7796 | 0.9508 |
85
- | 0.1575 | 6.8 | 1000 | 0.1749 | 0.7711 | 0.8696 | 0.8174 | 0.9575 |
86
- | 0.0952 | 10.2 | 1500 | 0.1794 | 0.8076 | 0.8793 | 0.8419 | 0.9628 |
87
- | 0.0655 | 13.61 | 2000 | 0.1890 | 0.8123 | 0.8802 | 0.8449 | 0.9617 |
88
- | 0.0475 | 17.01 | 2500 | 0.2034 | 0.8146 | 0.8820 | 0.8470 | 0.9610 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
 
90
 
91
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.829450915141431
29
  - name: Recall
30
  type: recall
31
+ value: 0.8815207780725022
32
  - name: F1
33
  type: f1
34
+ value: 0.8546935276468067
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9615129396151294
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
 
45
  This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.3089
48
+ - Precision: 0.8295
49
+ - Recall: 0.8815
50
+ - F1: 0.8547
51
+ - Accuracy: 0.9615
52
 
53
  ## Model description
54
 
 
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
+ - train_batch_size: 1
72
+ - eval_batch_size: 1
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 5
 
 
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.7892 | 0.11 | 500 | 0.5205 | 0.5042 | 0.6631 | 0.5728 | 0.9114 |
83
+ | 0.5593 | 0.21 | 1000 | 0.3722 | 0.6071 | 0.7241 | 0.6605 | 0.9246 |
84
+ | 0.5423 | 0.32 | 1500 | 0.3822 | 0.6001 | 0.7445 | 0.6646 | 0.9289 |
85
+ | 0.4507 | 0.43 | 2000 | 0.3354 | 0.7023 | 0.8073 | 0.7511 | 0.9423 |
86
+ | 0.4301 | 0.53 | 2500 | 0.3867 | 0.6740 | 0.7878 | 0.7265 | 0.9364 |
87
+ | 0.4034 | 0.64 | 3000 | 0.3318 | 0.7601 | 0.8011 | 0.7800 | 0.9435 |
88
+ | 0.4184 | 0.75 | 3500 | 0.3698 | 0.7133 | 0.7732 | 0.7420 | 0.9407 |
89
+ | 0.4236 | 0.85 | 4000 | 0.3648 | 0.7252 | 0.8258 | 0.7722 | 0.9415 |
90
+ | 0.3578 | 0.96 | 4500 | 0.2941 | 0.7341 | 0.8373 | 0.7823 | 0.9450 |
91
+ | 0.4098 | 1.06 | 5000 | 0.3095 | 0.7428 | 0.8386 | 0.7878 | 0.9456 |
92
+ | 0.3196 | 1.17 | 5500 | 0.2866 | 0.7563 | 0.8532 | 0.8018 | 0.9486 |
93
+ | 0.3572 | 1.28 | 6000 | 0.3165 | 0.7445 | 0.8232 | 0.7819 | 0.9479 |
94
+ | 0.2977 | 1.38 | 6500 | 0.2743 | 0.7762 | 0.8249 | 0.7998 | 0.9487 |
95
+ | 0.279 | 1.49 | 7000 | 0.3120 | 0.7637 | 0.8572 | 0.8077 | 0.9525 |
96
+ | 0.308 | 1.6 | 7500 | 0.3020 | 0.7589 | 0.8364 | 0.7958 | 0.9465 |
97
+ | 0.2879 | 1.7 | 8000 | 0.2717 | 0.7817 | 0.8594 | 0.8187 | 0.9514 |
98
+ | 0.2365 | 1.81 | 8500 | 0.2849 | 0.7780 | 0.8554 | 0.8149 | 0.9535 |
99
+ | 0.2658 | 1.92 | 9000 | 0.2476 | 0.7829 | 0.8484 | 0.8143 | 0.9551 |
100
+ | 0.2698 | 2.02 | 9500 | 0.3102 | 0.7622 | 0.8457 | 0.8018 | 0.9520 |
101
+ | 0.2297 | 2.13 | 10000 | 0.3206 | 0.7767 | 0.8612 | 0.8168 | 0.9523 |
102
+ | 0.2489 | 2.24 | 10500 | 0.3014 | 0.7662 | 0.8722 | 0.8158 | 0.9522 |
103
+ | 0.1962 | 2.34 | 11000 | 0.2986 | 0.7723 | 0.8652 | 0.8161 | 0.9528 |
104
+ | 0.2458 | 2.45 | 11500 | 0.2584 | 0.7812 | 0.8696 | 0.8230 | 0.9536 |
105
+ | 0.2108 | 2.56 | 12000 | 0.2866 | 0.7922 | 0.8798 | 0.8337 | 0.9575 |
106
+ | 0.2838 | 2.66 | 12500 | 0.2601 | 0.7740 | 0.8599 | 0.8147 | 0.9557 |
107
+ | 0.2092 | 2.77 | 13000 | 0.3028 | 0.7846 | 0.8585 | 0.8199 | 0.9536 |
108
+ | 0.2121 | 2.88 | 13500 | 0.2591 | 0.7798 | 0.8687 | 0.8218 | 0.9568 |
109
+ | 0.2445 | 2.98 | 14000 | 0.2742 | 0.7921 | 0.8758 | 0.8318 | 0.9557 |
110
+ | 0.1728 | 3.09 | 14500 | 0.2930 | 0.8080 | 0.8612 | 0.8337 | 0.9571 |
111
+ | 0.1426 | 3.19 | 15000 | 0.2775 | 0.7932 | 0.8665 | 0.8282 | 0.9569 |
112
+ | 0.1705 | 3.3 | 15500 | 0.3666 | 0.8082 | 0.8683 | 0.8372 | 0.9570 |
113
+ | 0.1324 | 3.41 | 16000 | 0.3011 | 0.8041 | 0.8727 | 0.8370 | 0.9574 |
114
+ | 0.1716 | 3.51 | 16500 | 0.3092 | 0.8002 | 0.8572 | 0.8277 | 0.9568 |
115
+ | 0.1465 | 3.62 | 17000 | 0.3439 | 0.7970 | 0.8643 | 0.8293 | 0.9574 |
116
+ | 0.1277 | 3.73 | 17500 | 0.3394 | 0.8126 | 0.8798 | 0.8448 | 0.9586 |
117
+ | 0.2132 | 3.83 | 18000 | 0.3296 | 0.8085 | 0.8736 | 0.8398 | 0.9589 |
118
+ | 0.211 | 3.94 | 18500 | 0.3000 | 0.8220 | 0.8820 | 0.8509 | 0.9587 |
119
+ | 0.137 | 4.05 | 19000 | 0.3241 | 0.8132 | 0.8740 | 0.8425 | 0.9582 |
120
+ | 0.1247 | 4.15 | 19500 | 0.3241 | 0.8205 | 0.8771 | 0.8479 | 0.9590 |
121
+ | 0.118 | 4.26 | 20000 | 0.3204 | 0.8336 | 0.8749 | 0.8538 | 0.9594 |
122
+ | 0.1403 | 4.37 | 20500 | 0.3130 | 0.8345 | 0.8780 | 0.8557 | 0.9612 |
123
+ | 0.1354 | 4.47 | 21000 | 0.3173 | 0.8229 | 0.8811 | 0.8510 | 0.9604 |
124
+ | 0.124 | 4.58 | 21500 | 0.3079 | 0.8236 | 0.8811 | 0.8513 | 0.9616 |
125
+ | 0.1115 | 4.69 | 22000 | 0.3020 | 0.8336 | 0.8815 | 0.8569 | 0.9618 |
126
+ | 0.0826 | 4.79 | 22500 | 0.3018 | 0.8301 | 0.8811 | 0.8548 | 0.9619 |
127
+ | 0.1467 | 4.9 | 23000 | 0.3089 | 0.8295 | 0.8815 | 0.8547 | 0.9615 |
128
 
129
 
130
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef5292fbf6ab5010d52f5ee7122140c6ad93470c14a9073a4852910f610d8115
3
  size 2235497956
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:850ed246737835de40479fae20876778d31d6e13ec7ad824c381cac5a294ef0f
3
  size 2235497956
runs/Mar19_02-46-31_n30/events.out.tfevents.1710812793.n30.592725.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cf4c3cb1b2593d6a8148295afc2a8b9721a416cf57961b7b1ab59a7f81711de
3
- size 34210
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2420baa53827725536d7b6e80a93872d7aeb409ca4296890024fc07ae22e831e
3
+ size 34570