Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "BAAI/bge-m3-retromae",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Adequada",
+    "1": "N\u00e3o Adequada"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Adequada": 0,
+    "N\u00e3o Adequada": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651a9d0b44e1e253a67d6f44f7a9d4660901671955e3c3322c55d30df63365f9
+size 1135562140

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5c31728cbe195b27d5573d469c6d2dd6b32825275c481387e01b8b42d04bfe
+size 17083066

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.8888888888888888,
+  "best_model_checkpoint": "./models/tese_classification_bge/checkpoint-50",
+  "epoch": 4.545454545454545,
+  "eval_steps": 10,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9090909090909091,
+      "eval_accuracy": 0.6296296296296297,
+      "eval_loss": 0.6555988788604736,
+      "eval_runtime": 0.9975,
+      "eval_samples_per_second": 27.067,
+      "eval_steps_per_second": 4.01,
+      "step": 10
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_accuracy": 0.4444444444444444,
+      "eval_loss": 0.7899305820465088,
+      "eval_runtime": 0.9781,
+      "eval_samples_per_second": 27.604,
+      "eval_steps_per_second": 4.089,
+      "step": 20
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_loss": 0.6174768805503845,
+      "eval_runtime": 1.0113,
+      "eval_samples_per_second": 26.699,
+      "eval_steps_per_second": 3.955,
+      "step": 30
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "eval_accuracy": 0.8148148148148148,
+      "eval_loss": 0.536119282245636,
+      "eval_runtime": 0.9728,
+      "eval_samples_per_second": 27.755,
+      "eval_steps_per_second": 4.112,
+      "step": 40
+    },
+    {
+      "epoch": 4.545454545454545,
+      "eval_accuracy": 0.8888888888888888,
+      "eval_loss": 0.46799495816230774,
+      "eval_runtime": 1.0054,
+      "eval_samples_per_second": 26.856,
+      "eval_steps_per_second": 3.979,
+      "step": 50
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1461268377698304.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40693c659f11d882fe01af8c4ed630c17d40e5cbb0441d224aecd1d5cd8188c2
+size 5368