lucasbalponti commited on
Commit
b901948
1 Parent(s): e8f820e

fine-tuned-bertimbau-for-law-weighted-2

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: neuralmind/bert-large-portuguese-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: modelo-pesos-2
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
+ # modelo-pesos-2
16
+
17
+ This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the None dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-06
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 2
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.44.2
51
+ - Pytorch 2.4.1+cu121
52
+ - Datasets 3.0.0
53
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-large-portuguese-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3,
26
+ "LABEL_4": 4
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_position_embeddings": 512,
30
+ "model_type": "bert",
31
+ "num_attention_heads": 16,
32
+ "num_hidden_layers": 24,
33
+ "output_past": true,
34
+ "pad_token_id": 0,
35
+ "pooler_fc_size": 768,
36
+ "pooler_num_attention_heads": 12,
37
+ "pooler_num_fc_layers": 3,
38
+ "pooler_size_per_head": 128,
39
+ "pooler_type": "first_token_transform",
40
+ "position_embedding_type": "absolute",
41
+ "problem_type": "single_label_classification",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.44.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 29794
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba124b766980d34a35b3dfdca0165e9c31a08cb51afb8cb0b02c01d20c264f5
3
+ size 1337653172
runs/Sep23_02-31-54_instance-20240921-203352/events.out.tfevents.1727058734.instance-20240921-203352 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18728f190936142c5ac301ee2b1583d356c74eea235feed1075149638a36e0d7
3
+ size 5380
runs/Sep23_02-31-54_instance-20240921-203352/events.out.tfevents.1727058834.instance-20240921-203352 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e82e255ef7caa3d8e6a5814ec056b809718c6953c6d0b0b13afba008d2fcf30
3
+ size 5380
runs/Sep23_02-35-44_instance-20240921-203352/events.out.tfevents.1727058965.instance-20240921-203352 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc3010fd9a43209ad82cefb80d28544ee2ed4c3fa2ee91c2f9d59630c37dccb
3
+ size 5301
runs/Sep23_02-39-18_instance-20240921-203352/events.out.tfevents.1727059172.instance-20240921-203352 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd6bca1e4d2f14b830a13b78ca2cf6083ceb62f6f6614f088bdd230a426cd06
3
+ size 9099
runs/Sep23_10-47-11_instance-20240921-203352/events.out.tfevents.1727088464.instance-20240921-203352 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1861e39a971c481ef56707b4db485fa5cffc603c70a206f0a1f6a486ea563f71
3
+ size 13484
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58f093fcbf6228c8b2fdccb8e91f97f078c3eed24ed9e8f0c59ab6a87f8ab1b
3
+ size 5240