Hugging Face's logo

jorgeortizfuentes
/
spanish_incivility

Text Classification
Transformers
PyTorch
TensorFlow
TensorBoard
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Metrics Community
1
jorgeortizfuentes commited on
Commit
78b58d2
•
1 Parent(s): a95f1be

Upload with huggingface_hub

Browse files
Files changed (24) hide show
  1. all_results.json +7 -0
  2. checkpoint-215/config.json +36 -0
  3. checkpoint-215/optimizer.pt +3 -0
  4. checkpoint-215/pytorch_model.bin +3 -0
  5. checkpoint-215/rng_state.pth +3 -0
  6. checkpoint-215/scheduler.pt +3 -0
  7. checkpoint-215/trainer_state.json +25 -0
  8. checkpoint-215/training_args.bin +3 -0
  9. checkpoint-430/config.json +36 -0
  10. checkpoint-430/optimizer.pt +3 -0
  11. checkpoint-430/pytorch_model.bin +3 -0
  12. checkpoint-430/rng_state.pth +3 -0
  13. checkpoint-430/scheduler.pt +3 -0
  14. checkpoint-430/trainer_state.json +34 -0
  15. checkpoint-430/training_args.bin +3 -0
  16. config.json +3 -2
  17. pytorch_model.bin +2 -2
  18. runs/Mar03_23-11-30_relela-04/1677895890.4250722/events.out.tfevents.1677895890.relela-04.431592.40 +3 -0
  19. runs/Mar03_23-11-30_relela-04/events.out.tfevents.1677895890.relela-04.431592.39 +3 -0
  20. runs/Mar03_23-11-30_relela-04/events.out.tfevents.1677896531.relela-04.431592.41 +3 -0
  21. tokenizer_config.json +1 -1
  22. train_results.json +7 -0
  23. trainer_state.json +52 -0
  24. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.40287496877271073,
4
+ "train_runtime": 634.4306,
5
+ "train_samples_per_second": 86.572,
6
+ "train_steps_per_second": 0.678
7
+ }
checkpoint-215/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jorgeortizfuentes/patana-bert",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "no_incivility",
14
+ "1": "incivility"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "incivility": 1,
20
+ "no_incivility": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.26.1",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 31002
36
+ }
checkpoint-215/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d18766c7393e2d2d69161ef5786bdff18414b67b74ce925755e1f7b69590c2
3
+ size 878986949
checkpoint-215/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc8cb608cc9bc9a55f065d219efa2a72a9de60f669e7d3abaca358b9cd9b909d
3
+ size 439482485
checkpoint-215/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03bf49e42afa9dd77db8f4b65941d13b2bd9ad851072d7a18f0be59ed58c3e43
3
+ size 15661
checkpoint-215/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d032e2ff71dd3255328fddbc0715ebc743e8326fd2615c6065f9890beffa4a7
3
+ size 627
checkpoint-215/trainer_state.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8026981450252951,
3
+ "best_model_checkpoint": "models/jorgeortizfuentes-patana-bert_lr-1.1928601506060306e-05_lr_scheduler_type-linear_weight_decay-0.1_optim-adamw_torch_aug-3/checkpoint-215",
4
+ "epoch": 1.0,
5
+ "global_step": 215,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_f1": 0.8026981450252951,
13
+ "eval_loss": 0.32584312558174133,
14
+ "eval_runtime": 6.8661,
15
+ "eval_samples_per_second": 233.029,
16
+ "eval_steps_per_second": 1.893,
17
+ "step": 215
18
+ }
19
+ ],
20
+ "max_steps": 430,
21
+ "num_train_epochs": 2,
22
+ "total_flos": 7225555802296320.0,
23
+ "trial_name": null,
24
+ "trial_params": null
25
+ }
checkpoint-215/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4ce9fa28f3140305ba7411d8190b2838ca9a6f20cfec85b8d9bddbf4b6da14
3
+ size 3707
checkpoint-430/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jorgeortizfuentes/patana-bert",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "no_incivility",
14
+ "1": "incivility"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "incivility": 1,
20
+ "no_incivility": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.26.1",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 31002
36
+ }
checkpoint-430/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f938afe84fd01fc1bdcd803c2f616af875f74c8402b7e27047e05b5920772a3b
3
+ size 878986949
checkpoint-430/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e87681c938ce305062a5b389b25080997122db21851b7687fd705ce55d99c72
3
+ size 439482485
checkpoint-430/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6bb002a9b669c75cf98776ea8cc2392de0ab74610dfdff69fd3c368a5cf6baa
3
+ size 15661
checkpoint-430/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcaf6c266d9b229f039bbbdd3dc7bad68c3630240144069e76060693f7ceeddf
3
+ size 627
checkpoint-430/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8026981450252951,
3
+ "best_model_checkpoint": "models/jorgeortizfuentes-patana-bert_lr-1.1928601506060306e-05_lr_scheduler_type-linear_weight_decay-0.1_optim-adamw_torch_aug-3/checkpoint-215",
4
+ "epoch": 2.0,
5
+ "global_step": 430,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_f1": 0.8026981450252951,
13
+ "eval_loss": 0.32584312558174133,
14
+ "eval_runtime": 6.8661,
15
+ "eval_samples_per_second": 233.029,
16
+ "eval_steps_per_second": 1.893,
17
+ "step": 215
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_f1": 0.7835420393559929,
22
+ "eval_loss": 0.33152076601982117,
23
+ "eval_runtime": 6.8681,
24
+ "eval_samples_per_second": 232.96,
25
+ "eval_steps_per_second": 1.893,
26
+ "step": 430
27
+ }
28
+ ],
29
+ "max_steps": 430,
30
+ "num_train_epochs": 2,
31
+ "total_flos": 1.445111160459264e+16,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
checkpoint-430/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4ce9fa28f3140305ba7411d8190b2838ca9a6f20cfec85b8d9bddbf4b6da14
3
+ size 3707
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "_name_or_path": "models/dccuchile-bert-base-spanish-wwm-cased_lr-3.545878616805076e-05_lr_scheduler_type-polynomial_weight_decay-0.1_optim-adafactor_aug-2",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
@@ -27,6 +27,7 @@
27
  "output_past": true,
28
  "pad_token_id": 1,
29
  "position_embedding_type": "absolute",
 
30
  "transformers_version": "4.26.1",
31
  "type_vocab_size": 2,
32
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "jorgeortizfuentes/patana-bert",
3
  "architectures": [
4
+ "BertForMaskedLM"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
27
  "output_past": true,
28
  "pad_token_id": 1,
29
  "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
  "transformers_version": "4.26.1",
32
  "type_vocab_size": 2,
33
  "use_cache": true,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f5a0d15a216f9819faf51a26992c2814b77dc861ba7a18bc188f2967b756c1
3
- size 439479669
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc8cb608cc9bc9a55f065d219efa2a72a9de60f669e7d3abaca358b9cd9b909d
3
+ size 439482485
runs/Mar03_23-11-30_relela-04/1677895890.4250722/events.out.tfevents.1677895890.relela-04.431592.40 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff8dbd4eaeb176c306d1af0b1698dd944294be9c438fcc14a3f8c34b899e547
3
+ size 6027
runs/Mar03_23-11-30_relela-04/events.out.tfevents.1677895890.relela-04.431592.39 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ff93efa8ae20a579291a3ffdf78c8920434ba9f5e80110f11a49e06811b3e3
3
+ size 5351
runs/Mar03_23-11-30_relela-04/events.out.tfevents.1677896531.relela-04.431592.41 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f29a0cd450d95735b511260e199c978c2d437150ac7561cc98df224ff8f3f3
3
+ size 357
tokenizer_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "do_lower_case": false,
5
  "mask_token": "[MASK]",
6
  "model_max_length": 512,
7
- "name_or_path": "models/dccuchile-bert-base-spanish-wwm-cased_lr-3.545878616805076e-05_lr_scheduler_type-polynomial_weight_decay-0.1_optim-adafactor_aug-2",
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
 
4
  "do_lower_case": false,
5
  "mask_token": "[MASK]",
6
  "model_max_length": 512,
7
+ "name_or_path": "jorgeortizfuentes/patana-bert",
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.40287496877271073,
4
+ "train_runtime": 634.4306,
5
+ "train_samples_per_second": 86.572,
6
+ "train_steps_per_second": 0.678
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8026981450252951,
3
+ "best_model_checkpoint": "models/jorgeortizfuentes-patana-bert_lr-1.1928601506060306e-05_lr_scheduler_type-linear_weight_decay-0.1_optim-adamw_torch_aug-3/checkpoint-215",
4
+ "epoch": 2.0,
5
+ "global_step": 430,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_f1": 0.8026981450252951,
13
+ "eval_loss": 0.32584312558174133,
14
+ "eval_runtime": 6.8661,
15
+ "eval_samples_per_second": 233.029,
16
+ "eval_steps_per_second": 1.893,
17
+ "step": 215
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_f1": 0.7835420393559929,
22
+ "eval_loss": 0.33152076601982117,
23
+ "eval_runtime": 6.8681,
24
+ "eval_samples_per_second": 232.96,
25
+ "eval_steps_per_second": 1.893,
26
+ "step": 430
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "step": 430,
31
+ "total_flos": 1.445111160459264e+16,
32
+ "train_loss": 0.40287496877271073,
33
+ "train_runtime": 634.4306,
34
+ "train_samples_per_second": 86.572,
35
+ "train_steps_per_second": 0.678
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_f1": 0.8026981450252951,
40
+ "eval_loss": 0.32584312558174133,
41
+ "eval_runtime": 6.8665,
42
+ "eval_samples_per_second": 233.016,
43
+ "eval_steps_per_second": 1.893,
44
+ "step": 430
45
+ }
46
+ ],
47
+ "max_steps": 430,
48
+ "num_train_epochs": 2,
49
+ "total_flos": 1.445111160459264e+16,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4ce9fa28f3140305ba7411d8190b2838ca9a6f20cfec85b8d9bddbf4b6da14
3
+ size 3707