Hugging Face's logo

marmarg2
/
TFMModelsandNotebooks

Keras
TensorBoard
Model card Files
xet
Metrics Community
marmarg2 commited on
Commit
a161ec5
·
1 Parent(s): 6469636

Upload 28 files

Browse files
Files changed (28) hide show
  1. BETo-t-MMG/README.md +61 -0
  2. BETo-t-MMG/checkpoint-102/config.json +28 -0
  3. BETo-t-MMG/checkpoint-102/optimizer.pt +3 -0
  4. BETo-t-MMG/checkpoint-102/pytorch_model.bin +3 -0
  5. BETo-t-MMG/checkpoint-102/rng_state.pth +3 -0
  6. BETo-t-MMG/checkpoint-102/scheduler.pt +3 -0
  7. BETo-t-MMG/checkpoint-102/trainer_state.json +43 -0
  8. BETo-t-MMG/checkpoint-102/training_args.bin +3 -0
  9. BETo-t-MMG/checkpoint-34/config.json +28 -0
  10. BETo-t-MMG/checkpoint-34/optimizer.pt +3 -0
  11. BETo-t-MMG/checkpoint-34/pytorch_model.bin +3 -0
  12. BETo-t-MMG/checkpoint-34/rng_state.pth +3 -0
  13. BETo-t-MMG/checkpoint-34/scheduler.pt +3 -0
  14. BETo-t-MMG/checkpoint-34/trainer_state.json +25 -0
  15. BETo-t-MMG/checkpoint-34/training_args.bin +3 -0
  16. BETo-t-MMG/checkpoint-68/config.json +28 -0
  17. BETo-t-MMG/checkpoint-68/optimizer.pt +3 -0
  18. BETo-t-MMG/checkpoint-68/pytorch_model.bin +3 -0
  19. BETo-t-MMG/checkpoint-68/rng_state.pth +3 -0
  20. BETo-t-MMG/checkpoint-68/scheduler.pt +3 -0
  21. BETo-t-MMG/checkpoint-68/trainer_state.json +34 -0
  22. BETo-t-MMG/checkpoint-68/training_args.bin +3 -0
  23. BETo-t-MMG/config.json +28 -0
  24. BETo-t-MMG/pytorch_model.bin +3 -0
  25. BETo-t-MMG/runs/Aug10_14-24-07_practicas/events.out.tfevents.1691670266.practicas.2806898.0 +3 -0
  26. BETo-t-MMG/runs/Aug10_14-27-12_practicas/events.out.tfevents.1691670447.practicas.2809327.0 +3 -0
  27. BETo-t-MMG/runs/Aug10_14-27-12_practicas/events.out.tfevents.1691670944.practicas.2809327.1 +3 -0
  28. BETo-t-MMG/training_args.bin +3 -0
BETo-t-MMG/README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: dccuchile/bert-base-spanish-wwm-cased
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: BETo-t-MMG
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # BETo-t-MMG
16
+
17
+ This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4422
20
+ - Accuracy: 0.8030
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 10
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | No log | 1.0 | 34 | 0.4422 | 0.8030 |
52
+ | No log | 2.0 | 68 | 0.5717 | 0.8636 |
53
+ | No log | 3.0 | 102 | 0.8172 | 0.8636 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.31.0
59
+ - Pytorch 2.0.1+cu117
60
+ - Datasets 2.14.0
61
+ - Tokenizers 0.13.3
BETo-t-MMG/checkpoint-102/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 31002
28
+ }
BETo-t-MMG/checkpoint-102/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:430a65e8c849c0d83a8159882a5e5af20a788370fdb15f04abb78c7daa69b8f9
3
+ size 878937029
BETo-t-MMG/checkpoint-102/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec23df398656ed35a60a9a4516e426c03b144e244df730b7d7e013de88aaf31
3
+ size 439478065
BETo-t-MMG/checkpoint-102/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8166e4672a330b2152739645b7617bc8d816f164b0c753c34fdd50ed3c40b0ce
3
+ size 14575
BETo-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
BETo-t-MMG/checkpoint-102/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44216740131378174,
3
+ "best_model_checkpoint": "BETo-t-MMG/checkpoint-34",
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": 0.803030303030303,
13
+ "eval_loss": 0.44216740131378174,
14
+ "eval_runtime": 2.4585,
15
+ "eval_samples_per_second": 26.846,
16
+ "eval_steps_per_second": 3.661,
17
+ "step": 34
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.8636363636363636,
22
+ "eval_loss": 0.5716877579689026,
23
+ "eval_runtime": 2.4391,
24
+ "eval_samples_per_second": 27.059,
25
+ "eval_steps_per_second": 3.69,
26
+ "step": 68
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_accuracy": 0.8636363636363636,
31
+ "eval_loss": 0.8172132968902588,
32
+ "eval_runtime": 2.4402,
33
+ "eval_samples_per_second": 27.047,
34
+ "eval_steps_per_second": 3.688,
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
+ }
BETo-t-MMG/checkpoint-102/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaf6ae1e384adc0701390d175cfbd61d954c7d49e6e0390b9ab78d5451a51c9
3
+ size 3963
BETo-t-MMG/checkpoint-34/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 31002
28
+ }
BETo-t-MMG/checkpoint-34/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e783bac16ff7cc56aa45c4c0fd1b904340f1cc9d32623420446488968c4a9449
3
+ size 878937029
BETo-t-MMG/checkpoint-34/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36255fc1490af3fe1d10916f7bfd97305f2782fd72a27f285cfe91e83ab45c72
3
+ size 439478065
BETo-t-MMG/checkpoint-34/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6240db54ec5d8e68e422054a7ac15b52594fa55680ba495f5f5e1c7bca4f5d5
3
+ size 14575
BETo-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
BETo-t-MMG/checkpoint-34/trainer_state.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44216740131378174,
3
+ "best_model_checkpoint": "BETo-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": 0.803030303030303,
13
+ "eval_loss": 0.44216740131378174,
14
+ "eval_runtime": 2.4585,
15
+ "eval_samples_per_second": 26.846,
16
+ "eval_steps_per_second": 3.661,
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
+ }
BETo-t-MMG/checkpoint-34/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaf6ae1e384adc0701390d175cfbd61d954c7d49e6e0390b9ab78d5451a51c9
3
+ size 3963
BETo-t-MMG/checkpoint-68/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 31002
28
+ }
BETo-t-MMG/checkpoint-68/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0543a5ba97f5cc38f15fdce3dba2fcd7d475482b2d44769e1f0eb211cab226e
3
+ size 878937029
BETo-t-MMG/checkpoint-68/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a88b379b210225893ef5a779a85b02d93d3dc9e6340595a21b445e8620d91f0
3
+ size 439478065
BETo-t-MMG/checkpoint-68/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b386f92443211ed864a270aa60382c492ac928b9a86f65925534197e53a0fad2
3
+ size 14575
BETo-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
BETo-t-MMG/checkpoint-68/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44216740131378174,
3
+ "best_model_checkpoint": "BETo-t-MMG/checkpoint-34",
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": 0.803030303030303,
13
+ "eval_loss": 0.44216740131378174,
14
+ "eval_runtime": 2.4585,
15
+ "eval_samples_per_second": 26.846,
16
+ "eval_steps_per_second": 3.661,
17
+ "step": 34
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.8636363636363636,
22
+ "eval_loss": 0.5716877579689026,
23
+ "eval_runtime": 2.4391,
24
+ "eval_samples_per_second": 27.059,
25
+ "eval_steps_per_second": 3.69,
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
+ }
BETo-t-MMG/checkpoint-68/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaf6ae1e384adc0701390d175cfbd61d954c7d49e6e0390b9ab78d5451a51c9
3
+ size 3963
BETo-t-MMG/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 31002
28
+ }
BETo-t-MMG/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36255fc1490af3fe1d10916f7bfd97305f2782fd72a27f285cfe91e83ab45c72
3
+ size 439478065
BETo-t-MMG/runs/Aug10_14-24-07_practicas/events.out.tfevents.1691670266.practicas.2806898.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b10408cf904f8dd900fd0e138ab1c26692b0e24a3fba64d393b554c6986bd9e
3
+ size 88
BETo-t-MMG/runs/Aug10_14-27-12_practicas/events.out.tfevents.1691670447.practicas.2809327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa86e72e84db344ac4d2b1558da34d474013d133542bd6797706c8c715f4b742
3
+ size 5360
BETo-t-MMG/runs/Aug10_14-27-12_practicas/events.out.tfevents.1691670944.practicas.2809327.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e10ac7473a3d7fe40fe01ed1aab21031c7e4e4b4fb28d6d2aa9f1bf38bb85fe
3
+ size 405
BETo-t-MMG/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaf6ae1e384adc0701390d175cfbd61d954c7d49e6e0390b9ab78d5451a51c9
3
+ size 3963