Training in progress, epoch 1

.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 +1,106 @@
+{
+  "_name_or_path": "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": "I-ORGAN",
+    "1": "B-PREVENTIVEMED",
+    "2": "B-DISEASESYMTOM",
+    "3": "B-FOODDRINK",
+    "4": "B-ORGANIZATION",
+    "5": "B-OCCUPATION",
+    "6": "B-DRUGCHEMICAL",
+    "7": "I-FOODDRINK",
+    "8": "I-DISEASESYMTOM",
+    "9": "I-UNITCALIBRATOR",
+    "10": "I-DATETIME",
+    "11": "I-DIAGNOSTICS",
+    "12": "B-TRANSPORTATION",
+    "13": "B-GENDER",
+    "14": "B-AGE",
+    "15": "B-DATETIME",
+    "16": "B-LOCATION",
+    "17": "B-TREATMENT",
+    "18": "I-DRUGCHEMICAL",
+    "19": "I-PREVENTIVEMED",
+    "20": "I-TREATMENT",
+    "21": "I-ORGANIZATION",
+    "22": "O",
+    "23": "B-UNITCALIBRATOR",
+    "24": "B-MEDDEVICETECHNIQUE",
+    "25": "I-OCCUPATION",
+    "26": "B-PERSONALCARE",
+    "27": "I-PERSONALCARE",
+    "28": "I-GENDER",
+    "29": "I-SURGERY",
+    "30": "I-AGE",
+    "31": "I-LOCATION",
+    "32": "B-DIAGNOSTICS",
+    "33": "I-MEDDEVICETECHNIQUE",
+    "34": "B-ORGAN",
+    "35": "B-SURGERY",
+    "36": "I-TRANSPORTATION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-AGE": 14,
+    "B-DATETIME": 15,
+    "B-DIAGNOSTICS": 32,
+    "B-DISEASESYMTOM": 2,
+    "B-DRUGCHEMICAL": 6,
+    "B-FOODDRINK": 3,
+    "B-GENDER": 13,
+    "B-LOCATION": 16,
+    "B-MEDDEVICETECHNIQUE": 24,
+    "B-OCCUPATION": 5,
+    "B-ORGAN": 34,
+    "B-ORGANIZATION": 4,
+    "B-PERSONALCARE": 26,
+    "B-PREVENTIVEMED": 1,
+    "B-SURGERY": 35,
+    "B-TRANSPORTATION": 12,
+    "B-TREATMENT": 17,
+    "B-UNITCALIBRATOR": 23,
+    "I-AGE": 30,
+    "I-DATETIME": 10,
+    "I-DIAGNOSTICS": 11,
+    "I-DISEASESYMTOM": 8,
+    "I-DRUGCHEMICAL": 18,
+    "I-FOODDRINK": 7,
+    "I-GENDER": 28,
+    "I-LOCATION": 31,
+    "I-MEDDEVICETECHNIQUE": 33,
+    "I-OCCUPATION": 25,
+    "I-ORGAN": 0,
+    "I-ORGANIZATION": 21,
+    "I-PERSONALCARE": 27,
+    "I-PREVENTIVEMED": 19,
+    "I-SURGERY": 29,
+    "I-TRANSPORTATION": 36,
+    "I-TREATMENT": 20,
+    "I-UNITCALIBRATOR": 9,
+    "O": 22
+  },
+  "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": "4.41.1",
+  "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:a7a8219eb1ea3070513577bc7e94ebbae921d403eb3fa41a1c8e1a20613d59b2
+size 2235563564

runs/May27_17-01-19_lab2/events.out.tfevents.1716829280.lab2.168172.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bff19cb27ba8dfc834123f20197da3cd9b1e676a621e42810733caa4f0a23fe
+size 7809

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 +1,54 @@
+{
+  "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": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3fa3a4b6b040847ca2705193033808acad9294833d7ef73c25607de7d155c2
+size 5112