Upload 6 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 +1,174 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-AerospaceManufacturer",
+    "1": "B-AnatomicalStructure",
+    "2": "B-ArtWork",
+    "3": "B-Artist",
+    "4": "B-Athlete",
+    "5": "B-CarManufacturer",
+    "6": "B-Cleric",
+    "7": "B-Clothing",
+    "8": "B-Disease",
+    "9": "B-Drink",
+    "10": "B-Facility",
+    "11": "B-Food",
+    "12": "B-HumanSettlement",
+    "13": "B-MedicalProcedure",
+    "14": "B-Medication/Vaccine",
+    "15": "B-MusicalGRP",
+    "16": "B-MusicalWork",
+    "17": "B-ORG",
+    "18": "B-OtherLOC",
+    "19": "B-OtherPER",
+    "20": "B-OtherPROD",
+    "21": "B-Politician",
+    "22": "B-PrivateCORP",
+    "23": "B-PrivateCorp",
+    "24": "B-PublicCORP",
+    "25": "B-PublicCorp",
+    "26": "B-Scientist",
+    "27": "B-Software",
+    "28": "B-SportsGRP",
+    "29": "B-SportsManager",
+    "30": "B-Station",
+    "31": "B-Symptom",
+    "32": "B-Vehicle",
+    "33": "B-VisualWork",
+    "34": "B-WrittenWork",
+    "35": "I-AerospaceManufacturer",
+    "36": "I-AnatomicalStructure",
+    "37": "I-ArtWork",
+    "38": "I-Artist",
+    "39": "I-Athlete",
+    "40": "I-CarManufacturer",
+    "41": "I-Cleric",
+    "42": "I-Clothing",
+    "43": "I-Disease",
+    "44": "I-Drink",
+    "45": "I-Facility",
+    "46": "I-Food",
+    "47": "I-HumanSettlement",
+    "48": "I-MedicalProcedure",
+    "49": "I-Medication/Vaccine",
+    "50": "I-MusicalGRP",
+    "51": "I-MusicalWork",
+    "52": "I-ORG",
+    "53": "I-OtherLOC",
+    "54": "I-OtherPER",
+    "55": "I-OtherPROD",
+    "56": "I-Politician",
+    "57": "I-PrivateCORP",
+    "58": "I-PrivateCorp",
+    "59": "I-PublicCORP",
+    "60": "I-PublicCorp",
+    "61": "I-Scientist",
+    "62": "I-Software",
+    "63": "I-SportsGRP",
+    "64": "I-SportsManager",
+    "65": "I-Station",
+    "66": "I-Symptom",
+    "67": "I-Vehicle",
+    "68": "I-VisualWork",
+    "69": "I-WrittenWork",
+    "70": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-AerospaceManufacturer": 0,
+    "B-AnatomicalStructure": 1,
+    "B-ArtWork": 2,
+    "B-Artist": 3,
+    "B-Athlete": 4,
+    "B-CarManufacturer": 5,
+    "B-Cleric": 6,
+    "B-Clothing": 7,
+    "B-Disease": 8,
+    "B-Drink": 9,
+    "B-Facility": 10,
+    "B-Food": 11,
+    "B-HumanSettlement": 12,
+    "B-MedicalProcedure": 13,
+    "B-Medication/Vaccine": 14,
+    "B-MusicalGRP": 15,
+    "B-MusicalWork": 16,
+    "B-ORG": 17,
+    "B-OtherLOC": 18,
+    "B-OtherPER": 19,
+    "B-OtherPROD": 20,
+    "B-Politician": 21,
+    "B-PrivateCORP": 22,
+    "B-PrivateCorp": 23,
+    "B-PublicCORP": 24,
+    "B-PublicCorp": 25,
+    "B-Scientist": 26,
+    "B-Software": 27,
+    "B-SportsGRP": 28,
+    "B-SportsManager": 29,
+    "B-Station": 30,
+    "B-Symptom": 31,
+    "B-Vehicle": 32,
+    "B-VisualWork": 33,
+    "B-WrittenWork": 34,
+    "I-AerospaceManufacturer": 35,
+    "I-AnatomicalStructure": 36,
+    "I-ArtWork": 37,
+    "I-Artist": 38,
+    "I-Athlete": 39,
+    "I-CarManufacturer": 40,
+    "I-Cleric": 41,
+    "I-Clothing": 42,
+    "I-Disease": 43,
+    "I-Drink": 44,
+    "I-Facility": 45,
+    "I-Food": 46,
+    "I-HumanSettlement": 47,
+    "I-MedicalProcedure": 48,
+    "I-Medication/Vaccine": 49,
+    "I-MusicalGRP": 50,
+    "I-MusicalWork": 51,
+    "I-ORG": 52,
+    "I-OtherLOC": 53,
+    "I-OtherPER": 54,
+    "I-OtherPROD": 55,
+    "I-Politician": 56,
+    "I-PrivateCORP": 57,
+    "I-PrivateCorp": 58,
+    "I-PublicCORP": 59,
+    "I-PublicCorp": 60,
+    "I-Scientist": 61,
+    "I-Software": 62,
+    "I-SportsGRP": 63,
+    "I-SportsManager": 64,
+    "I-Station": 65,
+    "I-Symptom": 66,
+    "I-Vehicle": 67,
+    "I-VisualWork": 68,
+    "I-WrittenWork": 69,
+    "O": 70
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "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": "float32",
+  "transformers_version": "4.48.3",
+  "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 sha256:7af5b43d3b9d3d561e38bc7eb070d52c681654e4505258d3bac20909453873dd
+size 2235702964

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": true,
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.6493010279892045,
+  "best_model_checkpoint": "./models/as_TrA50_XLM/checkpoint-4986",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 4986,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9987966305655837,
+      "grad_norm": 4.042017936706543,
+      "learning_rate": 4.1676694745286805e-05,
+      "loss": 0.7179,
+      "step": 830
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5016971754152019,
+      "eval_loss": 0.3967933654785156,
+      "eval_precision": 0.48018796774380695,
+      "eval_recall": 0.525223681705692,
+      "eval_runtime": 36.5565,
+      "eval_samples_per_second": 303.339,
+      "eval_steps_per_second": 4.76,
+      "step": 831
+    },
+    {
+      "epoch": 1.9975932611311673,
+      "grad_norm": 3.9885966777801514,
+      "learning_rate": 3.335338949057361e-05,
+      "loss": 0.4331,
+      "step": 1660
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.5287363073037502,
+      "eval_loss": 0.36940571665763855,
+      "eval_precision": 0.4921277061010278,
+      "eval_recall": 0.5712291389047528,
+      "eval_runtime": 36.6256,
+      "eval_samples_per_second": 302.766,
+      "eval_steps_per_second": 4.751,
+      "step": 1662
+    },
+    {
+      "epoch": 2.996389891696751,
+      "grad_norm": 3.235121250152588,
+      "learning_rate": 2.5030084235860413e-05,
+      "loss": 0.3391,
+      "step": 2490
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.607596501529808,
+      "eval_loss": 0.289639949798584,
+      "eval_precision": 0.5922400289191468,
+      "eval_recall": 0.623770543816232,
+      "eval_runtime": 36.3105,
+      "eval_samples_per_second": 305.393,
+      "eval_steps_per_second": 4.792,
+      "step": 2493
+    },
+    {
+      "epoch": 3.9951865222623346,
+      "grad_norm": 5.095285415649414,
+      "learning_rate": 1.6706778981147215e-05,
+      "loss": 0.2637,
+      "step": 3320
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6188354585957905,
+      "eval_loss": 0.2840094566345215,
+      "eval_precision": 0.5999046824734898,
+      "eval_recall": 0.638999936544197,
+      "eval_runtime": 36.309,
+      "eval_samples_per_second": 305.407,
+      "eval_steps_per_second": 4.792,
+      "step": 3324
+    },
+    {
+      "epoch": 4.993983152827918,
+      "grad_norm": 3.0477702617645264,
+      "learning_rate": 8.383473726434016e-06,
+      "loss": 0.2006,
+      "step": 4150
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.6398084151812781,
+      "eval_loss": 0.2787846028804779,
+      "eval_precision": 0.6125137848975565,
+      "eval_recall": 0.6696490894092265,
+      "eval_runtime": 36.4904,
+      "eval_samples_per_second": 303.888,
+      "eval_steps_per_second": 4.768,
+      "step": 4155
+    },
+    {
+      "epoch": 5.992779783393502,
+      "grad_norm": 3.478201150894165,
+      "learning_rate": 6.01684717208183e-08,
+      "loss": 0.1535,
+      "step": 4980
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.6493010279892045,
+      "eval_loss": 0.27660489082336426,
+      "eval_precision": 0.6217911487977698,
+      "eval_recall": 0.6793578272733042,
+      "eval_runtime": 36.2487,
+      "eval_samples_per_second": 305.914,
+      "eval_steps_per_second": 4.8,
+      "step": 4986
+    }
+  ],
+  "logging_steps": 830,
+  "max_steps": 4986,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.58906727159972e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}