Hugging Face's logo

kearney
/
office-character

Text Classification
Transformers
PyTorch
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
6
kearney commited on
Commit
69c32be
·
1 Parent(s): 5afaf96

End of training

Browse files
Files changed (5) hide show
  1. .DS_Store +0 -0
  2. README.md +11 -20
  3. config.json +16 -14
  4. pytorch_model.bin +2 -2
  5. training_args.bin +1 -1
.DS_Store ADDED
Binary file (6.15 kB). View file
 
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # office-character
17
 
18
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.5873
21
- - Accuracy: 0.1544
22
 
23
  ## Model description
24
 
@@ -43,27 +43,18 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 2.5
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | 2.6964 | 0.16 | 60 | 2.6756 | 0.0834 |
53
- | 2.6947 | 0.31 | 120 | 2.6670 | 0.0947 |
54
- | 2.6716 | 0.47 | 180 | 2.6428 | 0.1139 |
55
- | 2.6315 | 0.63 | 240 | 2.6252 | 0.1268 |
56
- | 2.6113 | 0.79 | 300 | 2.6205 | 0.1310 |
57
- | 2.5936 | 0.94 | 360 | 2.6137 | 0.1293 |
58
- | 2.5298 | 1.1 | 420 | 2.6065 | 0.1381 |
59
- | 2.4691 | 1.26 | 480 | 2.6097 | 0.1452 |
60
- | 2.4645 | 1.42 | 540 | 2.6015 | 0.1519 |
61
- | 2.4404 | 1.57 | 600 | 2.5912 | 0.1414 |
62
- | 2.4435 | 1.73 | 660 | 2.5890 | 0.1464 |
63
- | 2.4425 | 1.89 | 720 | 2.5928 | 0.1514 |
64
- | 2.4038 | 2.05 | 780 | 2.5880 | 0.1481 |
65
- | 2.2601 | 2.2 | 840 | 2.5941 | 0.1423 |
66
- | 2.2858 | 2.36 | 900 | 2.5873 | 0.1544 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: bert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # office-character
17
 
18
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.6075
21
+ - Accuracy: 0.1381
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 1.0
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 2.7041 | 0.16 | 60 | 2.6752 | 0.0864 |
53
+ | 2.6928 | 0.31 | 120 | 2.6589 | 0.1118 |
54
+ | 2.6579 | 0.47 | 180 | 2.6806 | 0.0989 |
55
+ | 2.645 | 0.63 | 240 | 2.6248 | 0.1260 |
56
+ | 2.6157 | 0.79 | 300 | 2.6219 | 0.1272 |
57
+ | 2.6076 | 0.94 | 360 | 2.6075 | 0.1381 |
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
config.json CHANGED
@@ -1,13 +1,14 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "Andy",
13
  "1": "Angela",
@@ -26,6 +27,7 @@
26
  "14": "Toby"
27
  },
28
  "initializer_range": 0.02,
 
29
  "label2id": {
30
  "Andy": 0,
31
  "Angela": 1,
@@ -43,17 +45,17 @@
43
  "Ryan": 13,
44
  "Toby": 14
45
  },
 
46
  "max_position_embeddings": 512,
47
- "model_type": "distilbert",
48
- "n_heads": 12,
49
- "n_layers": 6,
50
  "pad_token_id": 0,
 
51
  "problem_type": "single_label_classification",
52
- "qa_dropout": 0.1,
53
- "seq_classif_dropout": 0.2,
54
- "sinusoidal_pos_embds": false,
55
- "tie_weights_": true,
56
  "torch_dtype": "float32",
57
  "transformers_version": "4.32.1",
 
 
58
  "vocab_size": 30522
59
  }
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
 
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
  "id2label": {
13
  "0": "Andy",
14
  "1": "Angela",
 
27
  "14": "Toby"
28
  },
29
  "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
  "label2id": {
32
  "Andy": 0,
33
  "Angela": 1,
 
45
  "Ryan": 13,
46
  "Toby": 14
47
  },
48
+ "layer_norm_eps": 1e-12,
49
  "max_position_embeddings": 512,
50
+ "model_type": "bert",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
53
  "pad_token_id": 0,
54
+ "position_embedding_type": "absolute",
55
  "problem_type": "single_label_classification",
 
 
 
 
56
  "torch_dtype": "float32",
57
  "transformers_version": "4.32.1",
58
+ "type_vocab_size": 2,
59
+ "use_cache": true,
60
  "vocab_size": 30522
61
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6e7388bce18b2b605553aea45357ee7a822d9f49d16d49e39eb9bbaa29bade
3
- size 267894125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a684c06ce3d6f306726bd49fc83c37e924bfc58fa168409e39a80f71a31bbf03
3
+ size 438040689
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6485da611124e3d8ce3a90f9e543316e68cc53c2a3f561390488a73fcbbd490
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f75199ada056e7250135951a860537241a5618166c68d833060a1c1cf7d7686
3
  size 4027