Hugging Face's logo

MiMe-MeMo
/
Dialogue_dfm

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yemen2016 commited on
Commit
6969f48
·
verified ·
1 Parent(s): 648f6d7

End of training

Browse files
Files changed (5) hide show
  1. README.md +29 -19
  2. model.safetensors +1 -1
  3. runs/Oct23_11-06-09_08287b92a2e8/events.out.tfevents.1729681570.08287b92a2e8.40887.5 +3 -0
  4. runs/Oct23_11-06-09_08287b92a2e8/events.out.tfevents.1729681666.08287b92a2e8.40887.6 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # dfm
20
 
21
- This model is a fine-tuned version of [KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align](https://huggingface.co/KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Accuracy: 0.9981
24
- - Precision: 0.9980
25
- - Recall: 0.9981
26
- - F1: 0.9979
27
- - Loss: 0.0066
28
 
29
  ## Model description
30
 
@@ -51,27 +51,37 @@ The following hyperparameters were used during training:
51
  - total_train_batch_size: 8
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - num_epochs: 10
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Accuracy | Precision | Recall | F1 | Validation Loss |
60
- |:-------------:|:------:|:----:|:--------:|:---------:|:------:|:------:|:---------------:|
61
- | No log | 0.9524 | 10 | 0.9116 | 0.8719 | 0.9116 | 0.8909 | 0.3402 |
62
- | No log | 2.0 | 21 | 0.9585 | 0.9581 | 0.9585 | 0.9535 | 0.1368 |
63
- | No log | 2.9524 | 31 | 0.9818 | 0.9806 | 0.9818 | 0.9812 | 0.0664 |
64
- | No log | 4.0 | 42 | 0.9926 | 0.9912 | 0.9926 | 0.9919 | 0.0286 |
65
- | No log | 4.9524 | 52 | 0.9947 | 0.9934 | 0.9947 | 0.9940 | 0.0209 |
66
- | No log | 6.0 | 63 | 0.9953 | 0.9941 | 0.9953 | 0.9946 | 0.0159 |
67
- | No log | 6.9524 | 73 | 0.9967 | 0.9968 | 0.9967 | 0.9963 | 0.0107 |
68
- | No log | 8.0 | 84 | 0.9977 | 0.9977 | 0.9977 | 0.9975 | 0.0082 |
69
- | No log | 8.9524 | 94 | 0.9980 | 0.9979 | 0.9980 | 0.9978 | 0.0067 |
70
- | No log | 9.5238 | 100 | 0.9981 | 0.9980 | 0.9981 | 0.9979 | 0.0066 |
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
74
 
75
  - Transformers 4.44.2
76
  - Pytorch 2.4.1+cu121
 
77
  - Tokenizers 0.19.1
 
18
 
19
  # dfm
20
 
21
+ This model is a fine-tuned version of [KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align](https://huggingface.co/KennethEnevoldsen/dfm-sentence-encoder-large-exp2-no-lang-align) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Accuracy: 0.9421
24
+ - Precision: 0.9470
25
+ - Recall: 0.9421
26
+ - F1: 0.9422
27
+ - Loss: 0.5839
28
 
29
  ## Model description
30
 
 
51
  - total_train_batch_size: 8
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
+ - num_epochs: 20
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Accuracy | Precision | Recall | F1 | Validation Loss |
60
+ |:-------------:|:-------:|:----:|:--------:|:---------:|:------:|:------:|:---------------:|
61
+ | No log | 0.9412 | 8 | 0.8711 | 0.8341 | 0.8711 | 0.8507 | 0.4719 |
62
+ | No log | 2.0 | 17 | 0.9237 | 0.9242 | 0.9237 | 0.9217 | 0.3301 |
63
+ | No log | 2.9412 | 25 | 0.9225 | 0.9301 | 0.9225 | 0.9232 | 0.3470 |
64
+ | No log | 4.0 | 34 | 0.9317 | 0.9315 | 0.9317 | 0.9299 | 0.2004 |
65
+ | No log | 4.9412 | 42 | 0.9379 | 0.9443 | 0.9379 | 0.9383 | 0.4529 |
66
+ | No log | 6.0 | 51 | 0.9394 | 0.9454 | 0.9394 | 0.9399 | 0.4719 |
67
+ | No log | 6.9412 | 59 | 0.9425 | 0.9458 | 0.9425 | 0.9419 | 0.4498 |
68
+ | No log | 8.0 | 68 | 0.9421 | 0.9471 | 0.9421 | 0.9423 | 0.4921 |
69
+ | No log | 8.9412 | 76 | 0.9440 | 0.9486 | 0.9440 | 0.9440 | 0.5242 |
70
+ | No log | 10.0 | 85 | 0.9444 | 0.9488 | 0.9444 | 0.9443 | 0.5476 |
71
+ | No log | 10.9412 | 93 | 0.9421 | 0.9471 | 0.9421 | 0.9422 | 0.5733 |
72
+ | No log | 12.0 | 102 | 0.9432 | 0.9479 | 0.9432 | 0.9433 | 0.5725 |
73
+ | No log | 12.9412 | 110 | 0.9432 | 0.9478 | 0.9432 | 0.9432 | 0.5677 |
74
+ | No log | 14.0 | 119 | 0.9432 | 0.9478 | 0.9432 | 0.9432 | 0.5714 |
75
+ | No log | 14.9412 | 127 | 0.9425 | 0.9473 | 0.9425 | 0.9425 | 0.5802 |
76
+ | No log | 16.0 | 136 | 0.9417 | 0.9468 | 0.9417 | 0.9418 | 0.5838 |
77
+ | No log | 16.9412 | 144 | 0.9421 | 0.9470 | 0.9421 | 0.9422 | 0.5857 |
78
+ | No log | 18.0 | 153 | 0.9421 | 0.9470 | 0.9421 | 0.9422 | 0.5840 |
79
+ | No log | 18.8235 | 160 | 0.9421 | 0.9470 | 0.9421 | 0.9422 | 0.5839 |
80
 
81
 
82
  ### Framework versions
83
 
84
  - Transformers 4.44.2
85
  - Pytorch 2.4.1+cu121
86
+ - Datasets 3.0.2
87
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a902b63b039d601544df14e7502853ceb129d623cad057509d5c1c677366a32d
3
  size 1416218404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003d33f76a410852ef6d48ebe2ff12b18fe2ee0b259b8a6ea78be82c83e89c61
3
  size 1416218404
runs/Oct23_11-06-09_08287b92a2e8/events.out.tfevents.1729681570.08287b92a2e8.40887.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445177ab4b07ea1b30f5a2c5cbe1ef0711489f4116de50c87322c50aaea3b54d
3
+ size 14512
runs/Oct23_11-06-09_08287b92a2e8/events.out.tfevents.1729681666.08287b92a2e8.40887.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f555d98306690e3630e7200bf40c4a63c1d8f56f9a5cc37cbbb53083bd0c1c4
3
+ size 560
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b62232183cae99300c88674fb43444c6df48ca32eaf25259a64f8c64f5f693db
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16198da7ff65e77dab30111090fab65628f4b4c7c09910503f3502722bd53b1
3
  size 5240