Initial-commit

README.md

@@ -1,3 +1,53 @@
 ---
-license: other
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: result
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# result
+
+This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6748
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.6747965812683105,
+    "eval_runtime": 5.4911,
+    "eval_samples": 180,
+    "eval_samples_per_second": 32.78,
+    "eval_steps_per_second": 4.189,
+    "perplexity": 5.337709248585196,
+    "train_loss": 1.7737141554268243,
+    "train_runtime": 927.9599,
+    "train_samples": 3050,
+    "train_samples_per_second": 9.86,
+    "train_steps_per_second": 1.235
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.6747965812683105,
+    "eval_runtime": 5.4911,
+    "eval_samples": 180,
+    "eval_samples_per_second": 32.78,
+    "eval_steps_per_second": 4.189,
+    "perplexity": 5.337709248585196
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d798c3870494ca59fc76b651bc92e0f74c27cc9852be0b9c1cf7550b1edd2711
+size 1337852537

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.7737141554268243,
+    "train_runtime": 927.9599,
+    "train_samples": 3050,
+    "train_samples_per_second": 9.86,
+    "train_steps_per_second": 1.235
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1146,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.8184991273996508e-05,
+      "loss": 2.0847,
+      "step": 500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.369982547993019e-06,
+      "loss": 1.5616,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "step": 1146,
+      "total_flos": 4264004695910400.0,
+      "train_loss": 1.7737141554268243,
+      "train_runtime": 927.9599,
+      "train_samples_per_second": 9.86,
+      "train_steps_per_second": 1.235
+    }
+  ],
+  "max_steps": 1146,
+  "num_train_epochs": 3,
+  "total_flos": 4264004695910400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6703edad22fe46ed133f71b79f41720d7679812f503b3e592674e3ddf95da61
+size 3579