d1mitriz commited on
Commit
926e350
1 Parent(s): 3e895c1

Initial Commit.

Browse files
Files changed (10) hide show
  1. .gitignore +5 -0
  2. README.md +60 -0
  3. config.json +42 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +15 -0
  7. tf_model.h5 +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +23 -0
  10. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ /all_results.json
2
+ /eval_results.json
3
+ /training_args.bin
4
+ /trainer_state.json
5
+ /train_results.json
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - el
4
+ tags:
5
+ - text
6
+ - language-modeling
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: longformer
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # longformer
18
+
19
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 3.9004
22
+ - Accuracy: 0.3706
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 32
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 3.0
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.27.0.dev0
58
+ - Pytorch 1.13.1+cu117
59
+ - Datasets 2.9.0
60
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "greek-media-longformer-4096",
3
+ "architectures": [
4
+ "LongformerModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 512,
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "bos_token_id": 0,
22
+ "classifier_dropout": null,
23
+ "eos_token_id": 2,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 768,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 4098,
31
+ "model_type": "longformer",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "onnx_export": false,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "sep_token_id": 2,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.26.1",
40
+ "type_vocab_size": 2,
41
+ "vocab_size": 50265
42
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c341a01633820524a46ecf28b8a0efa2f924f1300f919d3981ba5becd47402f9
3
+ size 594943893
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a581b6fd2919d140b593ee81fee7078311b9e00f6effd5cec2bf0c51f2963a9e
3
+ size 594983160
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 4096,
16
+ "name_or_path": "greek-media-longformer-4096",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "LongformerTokenizer",
21
+ "trim_offsets": true,
22
+ "unk_token": "<unk>"
23
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff