sibyl commited on
Commit
45cf744
1 Parent(s): c972901
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imdb
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: bert-base-uncased-imdb
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: imdb
17
+ type: imdb
18
+ args: plain_text
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.91264
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # bert-base-uncased-imdb
29
+
30
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the imdb dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.4942
33
+ - Accuracy: 0.9126
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 5e-05
53
+ - train_batch_size: 8
54
+ - eval_batch_size: 16
55
+ - seed: 42
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - lr_scheduler_warmup_steps: 1546
59
+ - training_steps: 15468
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
65
+ | 0.3952 | 0.65 | 2000 | 0.4012 | 0.86 |
66
+ | 0.2954 | 1.29 | 4000 | 0.4535 | 0.892 |
67
+ | 0.2595 | 1.94 | 6000 | 0.4320 | 0.892 |
68
+ | 0.1516 | 2.59 | 8000 | 0.5309 | 0.896 |
69
+ | 0.1167 | 3.23 | 10000 | 0.4070 | 0.928 |
70
+ | 0.0624 | 3.88 | 12000 | 0.5055 | 0.908 |
71
+ | 0.0329 | 4.52 | 14000 | 0.4342 | 0.92 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.10.2
77
+ - Pytorch 1.7.1
78
+ - Datasets 1.6.1
79
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.10.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788af80f711869e4c5bd27b1a75013863ff03241b61dd5284da82d0e0b1d3228
3
+ size 438024063
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2eb53a6da76dc3e82fb8677e790622e55aee6e092b84d4ac71a63fedc75536
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff