Hugging Face's logo

johannes-garstenauer
/
bin_clean_seq_class

Text Classification
Transformers
PyTorch
distilbert
text-embeddings-inference
Model card Files
xet
Community
1
Johannes Garstenauer commited on
Commit
b4e5f70
·
1 Parent(s): 0184011

Training in progress, step 432

Browse files
Files changed (17) hide show
  1. .gitignore +1 -0
  2. config.json +33 -0
  3. last-checkpoint/config.json +33 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/special_tokens_map.json +6 -0
  9. last-checkpoint/tokenizer.json +0 -0
  10. last-checkpoint/tokenizer_config.json +9 -0
  11. last-checkpoint/trainer_state.json +15 -0
  12. last-checkpoint/training_args.bin +3 -0
  13. pytorch_model.bin +3 -0
  14. special_tokens_map.json +6 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +9 -0
  17. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "johannes-garstenauer/distilbert-heaps-masked",
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
+ "id2label": {
12
+ "0": "IRRELEVANT",
13
+ "1": "RELEVANT"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "IRRELEVANT": 0,
18
+ "RELEVANT": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_hidden_states": true,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.31.0",
32
+ "vocab_size": 30005
33
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "johannes-garstenauer/distilbert-heaps-masked",
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
+ "id2label": {
12
+ "0": "IRRELEVANT",
13
+ "1": "RELEVANT"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "IRRELEVANT": 0,
18
+ "RELEVANT": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_hidden_states": true,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.31.0",
32
+ "vocab_size": 30005
33
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321e9abbc94913b4cb6f7194f94aa3b72f11a0779c3339b55f3581dc7dce35be
3
+ size 532524613
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297ad30cc0ff758993d9463c4130a643312aa83e46d16ed66db52073c1adcd1c
3
+ size 266267309
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea517a4313924cc4916b15da26a638e88a614c589cc852f8ff0f2e827bd29fe
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5dbc0d18a0ec8d214cb813b6fb328577ebd4709c0bd2782d78ea796d4ab5ed
3
+ size 627
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "pad_token": "[PAD]",
4
+ "sep_token": "[SEP]",
5
+ "unk_token": "[UNK]"
6
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "sep_token": "[SEP]",
7
+ "tokenizer_class": "PreTrainedTokenizerFast",
8
+ "unk_token": "[UNK]"
9
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.10018552875695733,
5
+ "global_step": 432,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 8624,
11
+ "num_train_epochs": 2,
12
+ "total_flos": 3662458638041088.0,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453c494945352f15c079868c03eb3c8c82c0d0d63526edb1c2beea4590409120
3
+ size 4027
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297ad30cc0ff758993d9463c4130a643312aa83e46d16ed66db52073c1adcd1c
3
+ size 266267309
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "pad_token": "[PAD]",
4
+ "sep_token": "[SEP]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "[PAD]",
6
+ "sep_token": "[SEP]",
7
+ "tokenizer_class": "PreTrainedTokenizerFast",
8
+ "unk_token": "[UNK]"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453c494945352f15c079868c03eb3c8c82c0d0d63526edb1c2beea4590409120
3
+ size 4027