End of training
Browse files- README.md +62 -0
- config.json +25 -0
- model.safetensors +3 -0
- runs/Dec18_06-09-16_9501bdc42b04/events.out.tfevents.1702879762.9501bdc42b04.4290.0 +3 -0
- runs/Dec18_06-09-16_9501bdc42b04/events.out.tfevents.1702880077.9501bdc42b04.4290.1 +3 -0
- runs/Dec18_06-16-35_9501bdc42b04/events.out.tfevents.1702880227.9501bdc42b04.4290.2 +3 -0
- runs/Dec18_06-16-35_9501bdc42b04/events.out.tfevents.1702880422.9501bdc42b04.4290.3 +3 -0
- runs/Dec18_06-16-35_9501bdc42b04/events.out.tfevents.1702880630.9501bdc42b04.4290.4 +3 -0
- runs/Dec18_06-25-12_9501bdc42b04/events.out.tfevents.1702880723.9501bdc42b04.4290.5 +3 -0
- runs/Dec18_06-25-12_9501bdc42b04/events.out.tfevents.1702880822.9501bdc42b04.4290.6 +3 -0
- runs/Dec18_06-25-12_9501bdc42b04/events.out.tfevents.1702880924.9501bdc42b04.4290.7 +3 -0
- runs/Dec18_06-30-08_9501bdc42b04/events.out.tfevents.1702881013.9501bdc42b04.4290.8 +3 -0
- runs/Dec18_06-30-52_9501bdc42b04/events.out.tfevents.1702881056.9501bdc42b04.4290.9 +3 -0
- runs/Dec18_06-56-22_9501bdc42b04/events.out.tfevents.1702882592.9501bdc42b04.16654.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: distilbert-imdb
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# distilbert-imdb
|
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: 0.1248
|
21 |
+
- Accuracy: 0.97
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
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 |
+
- num_epochs: 3
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 0.0812 | 1.0 | 313 | 0.1134 | 0.966 |
|
53 |
+
| 0.0386 | 2.0 | 626 | 0.1193 | 0.9705 |
|
54 |
+
| 0.0007 | 3.0 | 939 | 0.1248 | 0.97 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.36.1
|
60 |
+
- Pytorch 2.1.0+cu121
|
61 |
+
- Datasets 2.15.0
|
62 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.36.1",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c92f4e930e1925c4575f79d5f8ebdc509048c110994db8f4aa1a88f598b197a
|
3 |
+
size 267832560
|
runs/Dec18_06-09-16_9501bdc42b04/events.out.tfevents.1702879762.9501bdc42b04.4290.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb43e3165669d65c7a6b4ecf5700f008ecce8ea10514d9d5a7f10965d4689876
|
3 |
+
size 4229
|
runs/Dec18_06-09-16_9501bdc42b04/events.out.tfevents.1702880077.9501bdc42b04.4290.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d7f72c9e950711995eb2eab65e8e1dff3a025d64edb5227579ec9b031275c95
|
3 |
+
size 5063
|
runs/Dec18_06-16-35_9501bdc42b04/events.out.tfevents.1702880227.9501bdc42b04.4290.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:116cad4e8d70dd5a9eb0025275eb2d998ec0f623a3de2e9c1f65b5fd6cc0cc09
|
3 |
+
size 9827
|
runs/Dec18_06-16-35_9501bdc42b04/events.out.tfevents.1702880422.9501bdc42b04.4290.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccf8d330a75edd1619f980600c6943d6e9ddbdf584582dc5082f544a756b669b
|
3 |
+
size 7315
|
runs/Dec18_06-16-35_9501bdc42b04/events.out.tfevents.1702880630.9501bdc42b04.4290.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfec75fdd25a4908c8aef4bcac25c1b22de784ce6b10243c6cb432b3ef4666d
|
3 |
+
size 6062
|
runs/Dec18_06-25-12_9501bdc42b04/events.out.tfevents.1702880723.9501bdc42b04.4290.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4483468fe724746e046a100c2c8d295244909c2757bd04b59aa5827270da7c9b
|
3 |
+
size 5446
|
runs/Dec18_06-25-12_9501bdc42b04/events.out.tfevents.1702880822.9501bdc42b04.4290.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dbbffbafea61e34c1105b4e96094ae2b2373d7fd91a9a4488054bc054d009f6
|
3 |
+
size 5355
|
runs/Dec18_06-25-12_9501bdc42b04/events.out.tfevents.1702880924.9501bdc42b04.4290.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:067e5e2faee753f94afe116c2ac571dc914015130a957e4776abbeb73ddc8573
|
3 |
+
size 7224
|
runs/Dec18_06-30-08_9501bdc42b04/events.out.tfevents.1702881013.9501bdc42b04.4290.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88e4d84247c530e40045f89006e3f722c099c5fad02a2f770e1a5b29712d091e
|
3 |
+
size 6134
|
runs/Dec18_06-30-52_9501bdc42b04/events.out.tfevents.1702881056.9501bdc42b04.4290.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9deac53d63df2bbd177b99565819f2eb65419d41bd8f328c60ed3b852fa36ab5
|
3 |
+
size 6913
|
runs/Dec18_06-56-22_9501bdc42b04/events.out.tfevents.1702882592.9501bdc42b04.16654.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d37a5d7a712bcdf3b85fbfa5138397ca3f5fc4ea3576e1ec79f82aa813e95f68
|
3 |
+
size 20116
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e2e8be7f268a7e4752c35ee374d1fe3c097879a719c7265f6b5e323c1104a58
|
3 |
+
size 4664
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|