Hugging Face's logo

marmarg2
/
TFMModelsandNotebooks

Keras
TensorBoard
Model card Files
xet
 Metrics Community
marmarg2 commited on
Commit
dff2554
·
1 Parent(s): e73edce

Upload 34 files

Browse files
Files changed (34) hide show
  1. RoBERTa-t-MMG/README.md +63 -0
  2. RoBERTa-t-MMG/checkpoint-102/config.json +29 -0
  3. RoBERTa-t-MMG/checkpoint-102/optimizer.pt +3 -0
  4. RoBERTa-t-MMG/checkpoint-102/pytorch_model.bin +3 -0
  5. RoBERTa-t-MMG/checkpoint-102/rng_state.pth +3 -0
  6. RoBERTa-t-MMG/checkpoint-102/scheduler.pt +3 -0
  7. RoBERTa-t-MMG/checkpoint-102/trainer_state.json +43 -0
  8. RoBERTa-t-MMG/checkpoint-102/training_args.bin +3 -0
  9. RoBERTa-t-MMG/checkpoint-136/config.json +29 -0
  10. RoBERTa-t-MMG/checkpoint-136/optimizer.pt +3 -0
  11. RoBERTa-t-MMG/checkpoint-136/pytorch_model.bin +3 -0
  12. RoBERTa-t-MMG/checkpoint-136/rng_state.pth +3 -0
  13. RoBERTa-t-MMG/checkpoint-136/scheduler.pt +3 -0
  14. RoBERTa-t-MMG/checkpoint-136/trainer_state.json +52 -0
  15. RoBERTa-t-MMG/checkpoint-136/training_args.bin +3 -0
  16. RoBERTa-t-MMG/checkpoint-34/config.json +29 -0
  17. RoBERTa-t-MMG/checkpoint-34/optimizer.pt +3 -0
  18. RoBERTa-t-MMG/checkpoint-34/pytorch_model.bin +3 -0
  19. RoBERTa-t-MMG/checkpoint-34/rng_state.pth +3 -0
  20. RoBERTa-t-MMG/checkpoint-34/scheduler.pt +3 -0
  21. RoBERTa-t-MMG/checkpoint-34/trainer_state.json +25 -0
  22. RoBERTa-t-MMG/checkpoint-34/training_args.bin +3 -0
  23. RoBERTa-t-MMG/checkpoint-68/config.json +29 -0
  24. RoBERTa-t-MMG/checkpoint-68/optimizer.pt +3 -0
  25. RoBERTa-t-MMG/checkpoint-68/pytorch_model.bin +3 -0
  26. RoBERTa-t-MMG/checkpoint-68/rng_state.pth +3 -0
  27. RoBERTa-t-MMG/checkpoint-68/scheduler.pt +3 -0
  28. RoBERTa-t-MMG/checkpoint-68/trainer_state.json +34 -0
  29. RoBERTa-t-MMG/checkpoint-68/training_args.bin +3 -0
  30. RoBERTa-t-MMG/config.json +29 -0
  31. RoBERTa-t-MMG/pytorch_model.bin +3 -0
  32. RoBERTa-t-MMG/runs/Aug10_13-50-09_practicas/events.out.tfevents.1691668254.practicas.2780945.0 +3 -0
  33. RoBERTa-t-MMG/runs/Aug10_13-50-09_practicas/events.out.tfevents.1691668394.practicas.2780945.1 +3 -0
  34. RoBERTa-t-MMG/training_args.bin +3 -0
RoBERTa-t-MMG/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: PlanTL-GOB-ES/roberta-base-bne
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: RoBERTa-t-MMG
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
+ # RoBERTa-t-MMG
17
+
18
+ This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.3975
21
+ - Accuracy: 0.8333
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: 5e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 34 | 0.5695 | 0.7121 |
53
+ | No log | 2.0 | 68 | 0.3975 | 0.8333 |
54
+ | No log | 3.0 | 102 | 0.8007 | 0.8636 |
55
+ | No log | 4.0 | 136 | 0.6453 | 0.8636 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.31.0
61
+ - Pytorch 2.0.1+cu117
62
+ - Datasets 2.14.0
63
+ - Tokenizers 0.13.3
RoBERTa-t-MMG/checkpoint-102/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.31.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50262
29
+ }
RoBERTa-t-MMG/checkpoint-102/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bde832d67da97727fc8dae33ca701c818efcacd288164866c751b7833b5d3e0
3
+ size 997276613
RoBERTa-t-MMG/checkpoint-102/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a18fbe8b62cb4a5b439925b3fc467284e54e19216cd007396e523846ff7ae0a
3
+ size 498648433
RoBERTa-t-MMG/checkpoint-102/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd3a816ab8628e6038ecf426e93a907752049203fbc39b63fcde557182a866f
3
+ size 14575
RoBERTa-t-MMG/checkpoint-102/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90fa10e0cfd5b10317e4c2bf4786b790892ca6387b6cf42d60555e376f66d3dd
3
+ size 627
RoBERTa-t-MMG/checkpoint-102/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.39754465222358704,
3
+ "best_model_checkpoint": "RoBERTa-t-MMG/checkpoint-68",
4
+ "epoch": 3.0,
5
+ "global_step": 102,
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_accuracy": 0.7121212121212122,
13
+ "eval_loss": 0.569523811340332,
14
+ "eval_runtime": 2.4052,
15
+ "eval_samples_per_second": 27.44,
16
+ "eval_steps_per_second": 3.742,
17
+ "step": 34
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.8333333333333334,
22
+ "eval_loss": 0.39754465222358704,
23
+ "eval_runtime": 2.4032,
24
+ "eval_samples_per_second": 27.463,
25
+ "eval_steps_per_second": 3.745,
26
+ "step": 68
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_accuracy": 0.8636363636363636,
31
+ "eval_loss": 0.8006694316864014,
32
+ "eval_runtime": 2.4275,
33
+ "eval_samples_per_second": 27.188,
34
+ "eval_steps_per_second": 3.708,
35
+ "step": 102
36
+ }
37
+ ],
38
+ "max_steps": 340,
39
+ "num_train_epochs": 10,
40
+ "total_flos": 211541288509440.0,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
RoBERTa-t-MMG/checkpoint-102/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6d8e4fcd77ae6a69937315ab66ce381c47e3faa4e28c2fc04039ada281826f
3
+ size 3963
RoBERTa-t-MMG/checkpoint-136/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.31.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50262
29
+ }
RoBERTa-t-MMG/checkpoint-136/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b198cc5d925dc658eef8145a4cbfb910d83c44896a4907dc0ed7b1d4495c68d
3
+ size 997276613
RoBERTa-t-MMG/checkpoint-136/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd505de0c95ac9c10e48e72cb6fb4b448f235a7def1c9465588e5bfa5573e03f
3
+ size 498648433
RoBERTa-t-MMG/checkpoint-136/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6162bb9db25c89c41e126a7a00a5d0695219447bff9b18d08731531620758440
3
+ size 14575
RoBERTa-t-MMG/checkpoint-136/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8265df91ddb3a8c71b4208b3313c24acdf60ac5ce8681251e2df91b897c72abd
3
+ size 627
RoBERTa-t-MMG/checkpoint-136/trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.39754465222358704,
3
+ "best_model_checkpoint": "RoBERTa-t-MMG/checkpoint-68",
4
+ "epoch": 4.0,
5
+ "global_step": 136,
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_accuracy": 0.7121212121212122,
13
+ "eval_loss": 0.569523811340332,
14
+ "eval_runtime": 2.4052,
15
+ "eval_samples_per_second": 27.44,
16
+ "eval_steps_per_second": 3.742,
17
+ "step": 34
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.8333333333333334,
22
+ "eval_loss": 0.39754465222358704,
23
+ "eval_runtime": 2.4032,
24
+ "eval_samples_per_second": 27.463,
25
+ "eval_steps_per_second": 3.745,
26
+ "step": 68
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_accuracy": 0.8636363636363636,
31
+ "eval_loss": 0.8006694316864014,
32
+ "eval_runtime": 2.4275,
33
+ "eval_samples_per_second": 27.188,
34
+ "eval_steps_per_second": 3.708,
35
+ "step": 102
36
+ },
37
+ {
38
+ "epoch": 4.0,
39
+ "eval_accuracy": 0.8636363636363636,
40
+ "eval_loss": 0.645268440246582,
41
+ "eval_runtime": 2.4104,
42
+ "eval_samples_per_second": 27.382,
43
+ "eval_steps_per_second": 3.734,
44
+ "step": 136
45
+ }
46
+ ],
47
+ "max_steps": 340,
48
+ "num_train_epochs": 10,
49
+ "total_flos": 282055051345920.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
RoBERTa-t-MMG/checkpoint-136/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6d8e4fcd77ae6a69937315ab66ce381c47e3faa4e28c2fc04039ada281826f
3
+ size 3963
RoBERTa-t-MMG/checkpoint-34/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.31.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50262
29
+ }
RoBERTa-t-MMG/checkpoint-34/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33019812b18505ab8289931a60371dc9c647f68e6d652f002fbede610fc5f55
3
+ size 997276613
RoBERTa-t-MMG/checkpoint-34/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ada3d5bea339b2432d27fd39a3fdce81ee60e34ce97c88a5636a2ce8204c765
3
+ size 498648433
RoBERTa-t-MMG/checkpoint-34/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
3
+ size 14575
RoBERTa-t-MMG/checkpoint-34/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1135ccdc6ff911cd34976d2d6f74e50eda157c783d2100d5cfc14ea275faaba
3
+ size 627
RoBERTa-t-MMG/checkpoint-34/trainer_state.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.569523811340332,
3
+ "best_model_checkpoint": "RoBERTa-t-MMG/checkpoint-34",
4
+ "epoch": 1.0,
5
+ "global_step": 34,
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_accuracy": 0.7121212121212122,
13
+ "eval_loss": 0.569523811340332,
14
+ "eval_runtime": 2.4052,
15
+ "eval_samples_per_second": 27.44,
16
+ "eval_steps_per_second": 3.742,
17
+ "step": 34
18
+ }
19
+ ],
20
+ "max_steps": 340,
21
+ "num_train_epochs": 10,
22
+ "total_flos": 70513762836480.0,
23
+ "trial_name": null,
24
+ "trial_params": null
25
+ }
RoBERTa-t-MMG/checkpoint-34/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6d8e4fcd77ae6a69937315ab66ce381c47e3faa4e28c2fc04039ada281826f
3
+ size 3963
RoBERTa-t-MMG/checkpoint-68/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.31.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50262
29
+ }
RoBERTa-t-MMG/checkpoint-68/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d6613fc5d3179062d0ce34d161ecb4d08dca9ed13db74013db9cfc900b3479
3
+ size 997276613
RoBERTa-t-MMG/checkpoint-68/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ea967fed97d42ad77d8afb87d13227a3c50d812231721aafafc7a54198384d
3
+ size 498648433
RoBERTa-t-MMG/checkpoint-68/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
3
+ size 14575
RoBERTa-t-MMG/checkpoint-68/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b160d770f4f8d28e5c183009a8b11a7d3b6b0ebd3406b3dc6d0fd9adf77a3b8
3
+ size 627
RoBERTa-t-MMG/checkpoint-68/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.39754465222358704,
3
+ "best_model_checkpoint": "RoBERTa-t-MMG/checkpoint-68",
4
+ "epoch": 2.0,
5
+ "global_step": 68,
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_accuracy": 0.7121212121212122,
13
+ "eval_loss": 0.569523811340332,
14
+ "eval_runtime": 2.4052,
15
+ "eval_samples_per_second": 27.44,
16
+ "eval_steps_per_second": 3.742,
17
+ "step": 34
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.8333333333333334,
22
+ "eval_loss": 0.39754465222358704,
23
+ "eval_runtime": 2.4032,
24
+ "eval_samples_per_second": 27.463,
25
+ "eval_steps_per_second": 3.745,
26
+ "step": 68
27
+ }
28
+ ],
29
+ "max_steps": 340,
30
+ "num_train_epochs": 10,
31
+ "total_flos": 141027525672960.0,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
RoBERTa-t-MMG/checkpoint-68/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6d8e4fcd77ae6a69937315ab66ce381c47e3faa4e28c2fc04039ada281826f
3
+ size 3963
RoBERTa-t-MMG/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "problem_type": "single_label_classification",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.31.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50262
29
+ }
RoBERTa-t-MMG/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ea967fed97d42ad77d8afb87d13227a3c50d812231721aafafc7a54198384d
3
+ size 498648433
RoBERTa-t-MMG/runs/Aug10_13-50-09_practicas/events.out.tfevents.1691668254.practicas.2780945.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df087b751fb58dc2dcfcc6a68a3db48d32f5e39f4d77ff0dcaa580c1b120df48
3
+ size 5716
RoBERTa-t-MMG/runs/Aug10_13-50-09_practicas/events.out.tfevents.1691668394.practicas.2780945.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f7d0c72099292761bd67dd2c2e5cc8d6b96a8bc62218523975b54fd3539a3d
3
+ size 411
RoBERTa-t-MMG/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6d8e4fcd77ae6a69937315ab66ce381c47e3faa4e28c2fc04039ada281826f
3
+ size 3963