Training in progress, epoch 1
Browse files- README.md +62 -0
- config.json +14 -2
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/bert_uncased_L-2_H-128_A-2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: berttiny-hateXplain-parentpretrained
|
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 |
+
# berttiny-hateXplain-parentpretrained
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2286
|
21 |
+
- Accuracy: 0.7601
|
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: 0.0001286744242350192
|
41 |
+
- train_batch_size: 128
|
42 |
+
- eval_batch_size: 128
|
43 |
+
- seed: 33
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 7
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 0.236 | 1.0 | 121 | 0.2296 | 0.7581 |
|
53 |
+
| 0.2239 | 2.0 | 242 | 0.2274 | 0.7591 |
|
54 |
+
| 0.2174 | 3.0 | 363 | 0.2286 | 0.7601 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.36.0.dev0
|
60 |
+
- Pytorch 2.1.1
|
61 |
+
- Datasets 2.15.0
|
62 |
+
- Tokenizers 0.15.0
|
config.json
CHANGED
@@ -2,12 +2,17 @@
|
|
2 |
"_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
"attention_dropout": 0.1,
|
|
|
|
|
8 |
"dim": 768,
|
9 |
"dropout": 0.1,
|
|
|
10 |
"hidden_dim": 3072,
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": 0,
|
13 |
"1": 1,
|
@@ -15,17 +20,22 @@
|
|
15 |
"3": 3
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
|
|
18 |
"label2id": {
|
19 |
"0": 0,
|
20 |
"1": 1,
|
21 |
"2": 2,
|
22 |
"3": 3
|
23 |
},
|
|
|
24 |
"max_position_embeddings": 512,
|
25 |
-
"model_type": "
|
26 |
"n_heads": 12,
|
27 |
"n_layers": 6,
|
|
|
|
|
28 |
"pad_token_id": 0,
|
|
|
29 |
"problem_type": "single_label_classification",
|
30 |
"qa_dropout": 0.1,
|
31 |
"seq_classif_dropout": 0.2,
|
@@ -33,5 +43,7 @@
|
|
33 |
"tie_weights_": true,
|
34 |
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.36.0.dev0",
|
|
|
|
|
36 |
"vocab_size": 30522
|
37 |
}
|
|
|
2 |
"_name_or_path": "agvidit1/DistilledBert_HateSpeech_pretrain",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
],
|
7 |
"attention_dropout": 0.1,
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"classifier_dropout": null,
|
10 |
"dim": 768,
|
11 |
"dropout": 0.1,
|
12 |
+
"hidden_act": "gelu",
|
13 |
"hidden_dim": 3072,
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
"id2label": {
|
17 |
"0": 0,
|
18 |
"1": 1,
|
|
|
20 |
"3": 3
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
"label2id": {
|
25 |
"0": 0,
|
26 |
"1": 1,
|
27 |
"2": 2,
|
28 |
"3": 3
|
29 |
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
"max_position_embeddings": 512,
|
32 |
+
"model_type": "bert",
|
33 |
"n_heads": 12,
|
34 |
"n_layers": 6,
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
"pad_token_id": 0,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
"problem_type": "single_label_classification",
|
40 |
"qa_dropout": 0.1,
|
41 |
"seq_classif_dropout": 0.2,
|
|
|
43 |
"tie_weights_": true,
|
44 |
"torch_dtype": "float32",
|
45 |
"transformers_version": "4.36.0.dev0",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_cache": true,
|
48 |
"vocab_size": 30522
|
49 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5f2b07901305af79e865683b356eb4ab715f6de4a310edcafd9a9f4f108274c
|
3 |
+
size 437964800
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd291d568e2c39552c50319c78392acde4dc20f897814064a3491ade1c9c0893
|
3 |
size 4792
|