Hugging Face's logo

ltuzova
/
citation_intent_classification_roberta

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
1
ltuzova commited on
Commit
985fc95
·
1 Parent(s): 612c31a

Training in progress, epoch 0

Browse files
Files changed (26) hide show
  1. .gitignore +1 -0
  2. config.json +45 -0
  3. last-checkpoint/config.json +45 -0
  4. last-checkpoint/merges.txt +0 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/special_tokens_map.json +15 -0
  10. last-checkpoint/tokenizer.json +0 -0
  11. last-checkpoint/tokenizer_config.json +15 -0
  12. last-checkpoint/trainer_state.json +26 -0
  13. last-checkpoint/training_args.bin +3 -0
  14. last-checkpoint/vocab.json +0 -0
  15. merges.txt +0 -0
  16. pytorch_model.bin +3 -0
  17. runs/Apr20_23-00-31_jupyter/events.out.tfevents.1713654041.jupyter.2680601.0 +3 -0
  18. runs/Apr20_23-02-19_jupyter/events.out.tfevents.1713654145.jupyter.2681483.0 +3 -0
  19. runs/Apr20_23-03-31_jupyter/events.out.tfevents.1713654217.jupyter.2681929.0 +3 -0
  20. runs/Apr20_23-08-27_jupyter/events.out.tfevents.1713654512.jupyter.2682369.0 +3 -0
  21. runs/Apr20_23-15-31_jupyter/events.out.tfevents.1713654936.jupyter.2682803.0 +3 -0
  22. special_tokens_map.json +15 -0
  23. tokenizer.json +0 -0
  24. tokenizer_config.json +15 -0
  25. training_args.bin +3 -0
  26. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Background",
15
+ "1": "CompareOrContrast",
16
+ "2": "Uses",
17
+ "3": "Motivation",
18
+ "4": "Future",
19
+ "5": "Extends"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "Background": 0,
25
+ "CompareOrContrast": 1,
26
+ "Extends": 5,
27
+ "Future": 4,
28
+ "Motivation": 3,
29
+ "Uses": 2
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "num_of_labels": 6,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.30.2",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Background",
15
+ "1": "CompareOrContrast",
16
+ "2": "Uses",
17
+ "3": "Motivation",
18
+ "4": "Future",
19
+ "5": "Extends"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "Background": 0,
25
+ "CompareOrContrast": 1,
26
+ "Extends": 5,
27
+ "Future": 4,
28
+ "Motivation": 3,
29
+ "Uses": 2
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "num_of_labels": 6,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.30.2",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f525129ca7b6e8cb1f751d66ad648d58b5992dedf526cb3ef41c804238a216
3
+ size 997319621
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e75301c5e4af3635bd5e07704c7eed2e40638fd609c91e2990c471c15313b7
3
+ size 498674357
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c35b1ae88be42b3fc92099950abfbbe324644492e7989ad94dbaa43aedacea0
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be33b98103a754b8daaa7225a843cc0a81e2ebb32ec4f7e3413258e9dc61582
3
+ size 627
last-checkpoint/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
+ }
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.11368015414258188,
3
+ "best_model_checkpoint": "citation_intent_classification_roberta/checkpoint-26",
4
+ "epoch": 0.9811320754716981,
5
+ "global_step": 26,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.98,
12
+ "eval_accuracy": 0.5175438596491229,
13
+ "eval_f1_macro": 0.11368015414258188,
14
+ "eval_loss": 1.3068338632583618,
15
+ "eval_runtime": 0.2396,
16
+ "eval_samples_per_second": 475.837,
17
+ "eval_steps_per_second": 8.348,
18
+ "step": 26
19
+ }
20
+ ],
21
+ "max_steps": 260,
22
+ "num_train_epochs": 10,
23
+ "total_flos": 123604968402720.0,
24
+ "trial_name": null,
25
+ "trial_params": null
26
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2668fca69256bc1da1da97c2ece2b0d4a0f71090eb4e5006b84cfc66515971
3
+ size 4027
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
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 sha256:00e75301c5e4af3635bd5e07704c7eed2e40638fd609c91e2990c471c15313b7
3
+ size 498674357
runs/Apr20_23-00-31_jupyter/events.out.tfevents.1713654041.jupyter.2680601.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117251c7c034c4494642f6af3dfdf3eaba7b6c4caf2b8b0294be63e2923bf0b5
3
+ size 4136
runs/Apr20_23-02-19_jupyter/events.out.tfevents.1713654145.jupyter.2681483.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b4af6b202269d4b6e69d9711b78e2c982035ff1a333b3f5219e818024b2dce
3
+ size 4136
runs/Apr20_23-03-31_jupyter/events.out.tfevents.1713654217.jupyter.2681929.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a760862c0ba24a0ecd71d208b40b38c93ec6b3db7e9f96b0f1b7de25c04d91
3
+ size 4353
runs/Apr20_23-08-27_jupyter/events.out.tfevents.1713654512.jupyter.2682369.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8097b91db1148e09b6efa4c0a2df6f2824f8faba0642eef213a97d25893e0b4c
3
+ size 4353
runs/Apr20_23-15-31_jupyter/events.out.tfevents.1713654936.jupyter.2682803.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a55293406e22cf5a742d25758c67fe1c8b08decf23e4b9b88ec2aada316f38
3
+ size 4721
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2668fca69256bc1da1da97c2ece2b0d4a0f71090eb4e5006b84cfc66515971
3
+ size 4027
vocab.json ADDED
The diff for this file is too large to render. See raw diff