Shruthikaa commited on
Commit
a9baed6
1 Parent(s): 0ecb782

Training in progress, epoch 1

Browse files
README.md CHANGED
@@ -1,3 +1,61 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/muril-base-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: muril_classification
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
+ # muril_classification
17
+
18
+ This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4072
21
+ - Accuracy: 0.843
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: 2e-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: 2
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.6127 | 1.0 | 625 | 0.4807 | 0.809 |
53
+ | 0.4818 | 2.0 | 1250 | 0.4072 | 0.843 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.32.1
59
+ - Pytorch 2.2.1+cpu
60
+ - Datasets 2.12.0
61
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/fnet-base",
3
+ "actual_seq_length": 512,
4
+ "architectures": [
5
+ "FNetForSequenceClassification"
6
+ ],
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu_new",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Non-Hate",
14
+ "1": "Hate"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Hate": 1,
20
+ "Non-Hate": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "fnet",
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 3,
27
+ "problem_type": "single_label_classification",
28
+ "torch_dtype": "float32",
29
+ "tpu_short_seq_length": 512,
30
+ "transformers_version": "4.32.1",
31
+ "type_vocab_size": 4,
32
+ "use_fft": true,
33
+ "use_latest": false,
34
+ "use_tpu_fourier_optimizations": false,
35
+ "vocab_size": 32000
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7bcc2fd0d56cc7e9e9625b46096f333831bd1abb7ae8a993dc5700c9fd59f36
3
+ size 331485174
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": {
4
+ "content": "[MASK]",
5
+ "lstrip": true,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "pad_token": "<pad>",
11
+ "sep_token": "[SEP]",
12
+ "unk_token": "<unk>"
13
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "keep_accents": true,
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "[MASK]",
9
+ "lstrip": false,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "remove_space": true,
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "FNetTokenizer",
20
+ "unk_token": "<unk>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4b3c3289a93e95db4784e40af7830dd76b067d50d6ec848c2667888e4bb65df
3
+ size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff