begnini/diarios_uniao_finetuned_classification

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: pierreguillou/bert-large-cased-pt-lenerbr
+base_model: pierreguillou/bert-base-cased-pt-lenerbr
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test_trainer
 
-This model is a fine-tuned version of [pierreguillou/bert-large-cased-pt-lenerbr](https://huggingface.co/pierreguillou/bert-large-cased-pt-lenerbr) on an unknown dataset.
+This model is a fine-tuned version of [pierreguillou/bert-base-cased-pt-lenerbr](https://huggingface.co/pierreguillou/bert-base-cased-pt-lenerbr) on an unknown dataset.
 
 ## Model description
 
@@ -32,8 +32,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "pierreguillou/bert-large-cased-pt-lenerbr",
+  "_name_or_path": "pierreguillou/bert-base-cased-pt-lenerbr",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,14 +8,14 @@
   "directionality": "bidi",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -24,8 +24,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b36d01042268e79de59c358795688747d8d1400381655bbe4261d7e9f65df1d6
-size 1337644972
+oid sha256:b94927c5b18bf381b85f746cd5bd9e07242ad5d5333a113f5cf607cf571f42c5
+size 435725300

runs/Dec06_22-00-10_38c6e04459d0/events.out.tfevents.1701900017.38c6e04459d0.1228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf05d453a5a7a8744d4ea258cb0dd8971af6aefe941af260496b8bbd7ade4056
+size 4570

runs/Dec06_22-01-19_38c6e04459d0/events.out.tfevents.1701900088.38c6e04459d0.1228.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ff9bb6eac85e05716068ac156710dd359f667d012496b3d9fb4d62304f58d9
+size 4635

runs/Dec06_22-02-34_38c6e04459d0/events.out.tfevents.1701900161.38c6e04459d0.1228.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15971ed848e5f91372e802cde009b47a149622d55d495f989538273637e176d9
+size 6402

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8603bd29304510c06301e9a17795871bafe9be939d52508f52cd2d70bf15580
+oid sha256:d4be2e345b5e1ce2b6dcd3fcdd88565f35f0c07f986815f2f32e3e951aa368af
 size 4536