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 +1,37 @@
+{
+  "_name_or_path": "BAAI/bge-m3-retromae",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-Segmento",
+    "1": "I-Segmento"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-Segmento": 0,
+    "I-Segmento": 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",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "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 sha256:9a769caae68e02a377bd7f9ced59665c667a3950bc3a34d1c566b1c905c3681c
+size 1133462708

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 sha256:95c87c2955c3edd5cce0a9d3ea8d1e49b444b9f75b82ab9e68f7005cd6371142
+size 17082898

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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>",
+  "mask_token": "<mask>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.060787502089570386,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012157500417914077,
+      "eval_accuracy": 0.9978134671943089,
+      "eval_f1": 0.5720789074355084,
+      "eval_loss": NaN,
+      "eval_precision": 0.5,
+      "eval_recall": 0.6684397163120568,
+      "eval_runtime": 6.301,
+      "eval_samples_per_second": 8.094,
+      "eval_steps_per_second": 8.094,
+      "step": 100
+    },
+    {
+      "epoch": 0.024315000835828153,
+      "eval_accuracy": 0.9982138182714072,
+      "eval_f1": 0.5731497418244406,
+      "eval_loss": NaN,
+      "eval_precision": 0.5568561872909699,
+      "eval_recall": 0.5904255319148937,
+      "eval_runtime": 6.4319,
+      "eval_samples_per_second": 7.929,
+      "eval_steps_per_second": 7.929,
+      "step": 200
+    },
+    {
+      "epoch": 0.03647250125374223,
+      "eval_accuracy": 0.9982908088631569,
+      "eval_f1": 0.5572232645403377,
+      "eval_loss": NaN,
+      "eval_precision": 0.5916334661354582,
+      "eval_recall": 0.526595744680851,
+      "eval_runtime": 6.4708,
+      "eval_samples_per_second": 7.882,
+      "eval_steps_per_second": 7.882,
+      "step": 300
+    },
+    {
+      "epoch": 0.048630001671656306,
+      "eval_accuracy": 0.9986911599402553,
+      "eval_f1": 0.6862416107382551,
+      "eval_loss": NaN,
+      "eval_precision": 0.6512738853503185,
+      "eval_recall": 0.725177304964539,
+      "eval_runtime": 6.2745,
+      "eval_samples_per_second": 8.128,
+      "eval_steps_per_second": 8.128,
+      "step": 400
+    },
+    {
+      "epoch": 0.060787502089570386,
+      "grad_norm": 1.1875,
+      "learning_rate": 9.39209726443769e-05,
+      "loss": 0.044,
+      "step": 500
+    },
+    {
+      "epoch": 0.060787502089570386,
+      "eval_accuracy": 0.9986449655852054,
+      "eval_f1": 0.6560402684563759,
+      "eval_loss": NaN,
+      "eval_precision": 0.6226114649681529,
+      "eval_recall": 0.6932624113475178,
+      "eval_runtime": 8.7006,
+      "eval_samples_per_second": 5.862,
+      "eval_steps_per_second": 5.862,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9176158363192776.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbfe65b6f225e858c1e1b1653e972ffd46b1e5e085f98028ee462abc46a85dec
+size 5216