Hugging Face's logo

docketanalyzer
/
label-complaint

Text Classification
Transformers
TensorBoard
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nadahlberg commited on
Commit
861ba19
•
1 Parent(s): c86f058

Model save

Browse files
Files changed (5) hide show
  1. README.md +24 -25
  2. eval_results.json +6 -6
  3. logs/events.out.tfevents.1721825827.nathan.19757.0 +3 -0
  4. logs/events.out.tfevents.1721827658.nathan.19757.1 +3 -0
  5. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [docketanalyzer/docket-lm-xs](https://huggingface.co/docketanalyzer/docket-lm-xs) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0037
21
- - F1: 0.9993
22
 
23
  ## Model description
24
 
@@ -52,29 +52,28 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 |
54
  |:-------------:|:------:|:----:|:---------------:|:------:|
55
- | 0.0025 | 0.0435 | 300 | 0.0193 | 0.9969 |
56
- | 0.001 | 0.0869 | 600 | 0.0154 | 0.9977 |
57
- | 0.0006 | 0.1304 | 900 | 0.0074 | 0.9988 |
58
- | 0.0004 | 0.1738 | 1200 | 0.0074 | 0.9984 |
59
- | 0.0041 | 0.2173 | 1500 | 0.0053 | 0.9990 |
60
- | 0.0026 | 0.2607 | 1800 | 0.0166 | 0.9954 |
61
- | 0.0219 | 0.3042 | 2100 | 0.0046 | 0.9990 |
62
- | 0.0001 | 0.3476 | 2400 | 0.0092 | 0.9983 |
63
- | 0.2829 | 0.3911 | 2700 | 0.0087 | 0.9988 |
64
- | 0.0005 | 0.4346 | 3000 | 0.0079 | 0.9984 |
65
- | 0.0009 | 0.4780 | 3300 | 0.0052 | 0.9988 |
66
- | 0.0002 | 0.5215 | 3600 | 0.0076 | 0.9986 |
67
- | 0.0002 | 0.5649 | 3900 | 0.0044 | 0.9991 |
68
- | 0.0002 | 0.6084 | 4200 | 0.0040 | 0.9993 |
69
- | 0.0002 | 0.6518 | 4500 | 0.0042 | 0.9993 |
70
- | 0.0004 | 0.6953 | 4800 | 0.0034 | 0.9993 |
71
- | 0.0003 | 0.7388 | 5100 | 0.0028 | 0.9995 |
72
- | 0.0002 | 0.7822 | 5400 | 0.0044 | 0.9991 |
73
- | 0.0002 | 0.8257 | 5700 | 0.0035 | 0.9993 |
74
- | 0.0002 | 0.8691 | 6000 | 0.0038 | 0.9991 |
75
- | 0.0002 | 0.9126 | 6300 | 0.0037 | 0.9993 |
76
- | 0.0003 | 0.9560 | 6600 | 0.0037 | 0.9993 |
77
- | 0.0007 | 0.9995 | 6900 | 0.0037 | 0.9993 |
78
 
79
 
80
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [docketanalyzer/docket-lm-xs](https://huggingface.co/docketanalyzer/docket-lm-xs) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0048
21
+ - F1: 0.9995
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 |
54
  |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 0.0017 | 0.0435 | 300 | 0.0115 | 0.9976 |
56
+ | 0.0011 | 0.0870 | 600 | 0.0133 | 0.9978 |
57
+ | 0.0022 | 0.1305 | 900 | 0.0116 | 0.9972 |
58
+ | 0.0002 | 0.1740 | 1200 | 0.0127 | 0.9981 |
59
+ | 0.0005 | 0.2175 | 1500 | 0.0092 | 0.9981 |
60
+ | 0.0002 | 0.2611 | 1800 | 0.0120 | 0.9979 |
61
+ | 0.0002 | 0.3046 | 2100 | 0.0079 | 0.9985 |
62
+ | 0.0001 | 0.3481 | 2400 | 0.0146 | 0.9961 |
63
+ | 0.0003 | 0.3916 | 2700 | 0.0075 | 0.9988 |
64
+ | 0.0003 | 0.4351 | 3000 | 0.0088 | 0.9986 |
65
+ | 0.0001 | 0.4786 | 3300 | 0.0095 | 0.9988 |
66
+ | 0.0001 | 0.5221 | 3600 | 0.0067 | 0.9991 |
67
+ | 0.0001 | 0.5656 | 3900 | 0.0077 | 0.9990 |
68
+ | 0.0001 | 0.6091 | 4200 | 0.0084 | 0.9985 |
69
+ | 0.0001 | 0.6526 | 4500 | 0.0049 | 0.9995 |
70
+ | 0.0347 | 0.6962 | 4800 | 0.0056 | 0.9993 |
71
+ | 0.0001 | 0.7397 | 5100 | 0.0067 | 0.9988 |
72
+ | 0.0016 | 0.7832 | 5400 | 0.0068 | 0.9986 |
73
+ | 0.0001 | 0.8267 | 5700 | 0.0054 | 0.9990 |
74
+ | 0.0001 | 0.8702 | 6000 | 0.0053 | 0.9991 |
75
+ | 0.0872 | 0.9137 | 6300 | 0.0048 | 0.9995 |
76
+ | 0.0001 | 0.9572 | 6600 | 0.0048 | 0.9995 |
 
77
 
78
 
79
  ### Framework versions
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "eval_loss": 0.0037243221886456013,
3
- "eval_f1": 0.9993084370677732,
4
- "eval_runtime": 35.4164,
5
- "eval_samples_per_second": 164.133,
6
- "eval_steps_per_second": 10.278,
7
- "epoch": 0.9999275729702325
8
  }
 
1
  {
2
+ "eval_loss": 0.004779691807925701,
3
+ "eval_f1": 0.999485155311481,
4
+ "eval_runtime": 19.4506,
5
+ "eval_samples_per_second": 298.5,
6
+ "eval_steps_per_second": 18.663,
7
+ "epoch": 1.0
8
  }
logs/events.out.tfevents.1721825827.nathan.19757.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea4dcc62b4f3973aff9efc2b1a5a7317b7ddafcce23ece7a7704f69cdf1a2dac
3
+ size 739554
logs/events.out.tfevents.1721827658.nathan.19757.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d985f569671dbb6bf88e3d646af754541a17161b3b0727c3a9a3e6882fa5f0
3
+ size 405
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c842067a8ebd7cba0aa004b881348bc61cb08f159b3ece1a5de509634d8b06a4
3
  size 283347432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1266d7a450140330afab29beb86e9f6fa0e5bb5218d67a0c223ab027937ac8b
3
  size 283347432