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
73bd912
•
1 Parent(s): 965f244

Model save

Browse files
Files changed (7) hide show
  1. README.md +16 -17
  2. eval_results.json +5 -5
  3. logs/events.out.tfevents.1722463228.nathan.173807.0 +3 -0
  4. logs/events.out.tfevents.1722465205.nathan.173807.1 +3 -0
  5. model.safetensors +1 -1
  6. run_config.json +4 -3
  7. training_args.bin +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: 0.0064
21
- - F1: 0.9987
22
 
23
  ## Model description
24
 
@@ -38,32 +38,31 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 8
42
  - eval_batch_size: 16
43
  - seed: 42
44
- - gradient_accumulation_steps: 2
45
- - total_train_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.02
49
  - num_epochs: 1
 
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|
55
- | 0.016 | 0.08 | 380 | 0.0157 | 0.9965 |
56
- | 0.0006 | 0.16 | 760 | 0.0150 | 0.9975 |
57
- | 0.0007 | 0.24 | 1140 | 0.0136 | 0.9977 |
58
- | 0.0003 | 0.32 | 1520 | 0.0128 | 0.9982 |
59
- | 0.0005 | 0.4 | 1900 | 0.0110 | 0.9985 |
60
- | 0.0004 | 0.48 | 2280 | 0.0053 | 0.9987 |
61
- | 0.0004 | 0.56 | 2660 | 0.0035 | 0.9995 |
62
- | 0.0003 | 0.64 | 3040 | 0.0049 | 0.9987 |
63
- | 0.0004 | 0.72 | 3420 | 0.0080 | 0.9985 |
64
- | 0.0577 | 0.8 | 3800 | 0.0081 | 0.9982 |
65
- | 0.0002 | 0.88 | 4180 | 0.0077 | 0.9987 |
66
- | 0.0002 | 0.96 | 4560 | 0.0063 | 0.9987 |
67
 
68
 
69
  ### 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: 0.0015
21
+ - F1: 0.9995
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 16
42
  - eval_batch_size: 16
43
  - seed: 42
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.02
47
  - num_epochs: 1
48
+ - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 0.0013 | 0.08 | 380 | 0.0054 | 0.9983 |
55
+ | 0.0007 | 0.16 | 760 | 0.0139 | 0.9976 |
56
+ | 0.0003 | 0.24 | 1140 | 0.0061 | 0.9985 |
57
+ | 0.0002 | 0.32 | 1520 | 0.0109 | 0.9981 |
58
+ | 0.0005 | 0.4 | 1900 | 0.0093 | 0.9985 |
59
+ | 0.0002 | 0.48 | 2280 | 0.0080 | 0.9988 |
60
+ | 0.0004 | 0.56 | 2660 | 0.0099 | 0.9978 |
61
+ | 0.0004 | 0.64 | 3040 | 0.0024 | 0.9990 |
62
+ | 0.0002 | 0.72 | 3420 | 0.0037 | 0.9988 |
63
+ | 0.0003 | 0.8 | 3800 | 0.0013 | 0.9998 |
64
+ | 0.0003 | 0.88 | 4180 | 0.0034 | 0.9993 |
65
+ | 0.0002 | 0.96 | 4560 | 0.0017 | 0.9993 |
66
 
67
 
68
  ### Framework versions
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "eval_loss": 0.0064284102991223335,
3
- "eval_f1": 0.9987344975955453,
4
- "eval_runtime": 40.1494,
5
- "eval_samples_per_second": 99.628,
6
- "eval_steps_per_second": 6.227,
7
  "epoch": 1.0
8
  }
 
1
  {
2
+ "eval_loss": 0.0014596829423680902,
3
+ "eval_f1": 0.9995131450827653,
4
+ "eval_runtime": 8.2463,
5
+ "eval_samples_per_second": 485.069,
6
+ "eval_steps_per_second": 30.317,
7
  "epoch": 1.0
8
  }
logs/events.out.tfevents.1722463228.nathan.173807.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e8708557de010a167899eb5d5e54a4960bf8ed5e9b084c3dffc66f4c703bf3
3
+ size 510331
logs/events.out.tfevents.1722465205.nathan.173807.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f985d34adea2e9a1d80da94c3239daa4d1945bbf531e2934080619656a049ae5
3
+ size 405
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2de238ced3864b54a6be60056b08d535489fec6bf3a5ee54b5e9aaa702d890
3
  size 283347432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0566ceb185a37aceb7b77f0d65402f1449a3d7df5c6688cfc268627f2c4ab89b
3
  size 283347432
run_config.json CHANGED
@@ -5,16 +5,17 @@
5
  },
6
  "training_args": {
7
  "num_train_epochs": 1,
8
- "per_device_train_batch_size": 8,
9
  "per_device_eval_batch_size": 16,
10
- "gradient_accumulation_steps": 2,
11
  "learning_rate": 5e-05,
12
  "weight_decay": 0.1,
13
  "warmup_ratio": 0.02,
14
  "evaluation_strategy": "steps",
15
  "eval_steps": 0.08,
16
  "save_steps": 0.08,
17
- "save_total_limit": 2
 
18
  },
19
  "run_name": "complaint",
20
  "run_type": "ClassificationRoutine"
 
5
  },
6
  "training_args": {
7
  "num_train_epochs": 1,
8
+ "per_device_train_batch_size": 16,
9
  "per_device_eval_batch_size": 16,
10
+ "gradient_accumulation_steps": 1,
11
  "learning_rate": 5e-05,
12
  "weight_decay": 0.1,
13
  "warmup_ratio": 0.02,
14
  "evaluation_strategy": "steps",
15
  "eval_steps": 0.08,
16
  "save_steps": 0.08,
17
+ "save_total_limit": 2,
18
+ "fp16": true
19
  },
20
  "run_name": "complaint",
21
  "run_type": "ClassificationRoutine"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ef2207833c0afa403c72448d2b06f189c7278d0be4661827287b01ffc17100
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d3579d075a2b7dcef799631a3bf63aed51391f5e3e930601890e8d9c6c88eb
3
  size 5240