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 +1,144 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "O",
+    "1": "date",
+    "10": "coffee_type",
+    "11": "time",
+    "12": "music_album",
+    "13": "radio_name",
+    "14": "game_type",
+    "15": "business_name",
+    "16": "relation",
+    "17": "time_zone",
+    "18": "sport_type",
+    "19": "audiobook_name",
+    "2": "meal_type",
+    "20": "movie_name",
+    "21": "podcast_descriptor",
+    "22": "media_type",
+    "23": "playlist_name",
+    "24": "device_type",
+    "25": "podcast_name",
+    "26": "music_genre",
+    "27": "person",
+    "28": "place_name",
+    "29": "house_place",
+    "3": "alarm_type",
+    "30": "definition_word",
+    "31": "timeofday",
+    "32": "food_type",
+    "33": "player_setting",
+    "34": "email_folder",
+    "35": "transport_type",
+    "36": "event_name",
+    "37": "transport_agency",
+    "38": "transport_name",
+    "39": "cooking_type",
+    "4": "song_name",
+    "40": "personal_info",
+    "41": "business_type",
+    "42": "general_frequency",
+    "43": "app_name",
+    "44": "color_type",
+    "45": "music_descriptor",
+    "46": "order_type",
+    "47": "weather_descriptor",
+    "48": "drink_type",
+    "49": "ingredient",
+    "5": "audiobook_author",
+    "50": "email_address",
+    "51": "movie_type",
+    "52": "game_name",
+    "53": "joke_type",
+    "54": "change_amount",
+    "55": "transport_descriptor",
+    "6": "news_topic",
+    "7": "list_name",
+    "8": "currency_name",
+    "9": "artist_name"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": "0",
+    "alarm_type": "3",
+    "app_name": "43",
+    "artist_name": "9",
+    "audiobook_author": "5",
+    "audiobook_name": "19",
+    "business_name": "15",
+    "business_type": "41",
+    "change_amount": "54",
+    "coffee_type": "10",
+    "color_type": "44",
+    "cooking_type": "39",
+    "currency_name": "8",
+    "date": "1",
+    "definition_word": "30",
+    "device_type": "24",
+    "drink_type": "48",
+    "email_address": "50",
+    "email_folder": "34",
+    "event_name": "36",
+    "food_type": "32",
+    "game_name": "52",
+    "game_type": "14",
+    "general_frequency": "42",
+    "house_place": "29",
+    "ingredient": "49",
+    "joke_type": "53",
+    "list_name": "7",
+    "meal_type": "2",
+    "media_type": "22",
+    "movie_name": "20",
+    "movie_type": "51",
+    "music_album": "12",
+    "music_descriptor": "45",
+    "music_genre": "26",
+    "news_topic": "6",
+    "order_type": "46",
+    "person": "27",
+    "personal_info": "40",
+    "place_name": "28",
+    "player_setting": "33",
+    "playlist_name": "23",
+    "podcast_descriptor": "21",
+    "podcast_name": "25",
+    "radio_name": "13",
+    "relation": "16",
+    "song_name": "4",
+    "sport_type": "18",
+    "time": "11",
+    "time_zone": "17",
+    "timeofday": "31",
+    "transport_agency": "37",
+    "transport_descriptor": "55",
+    "transport_name": "38",
+    "transport_type": "35",
+    "weather_descriptor": "47"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "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:b352b7be4244d54926926166d7bad400ad2a34389bf6922566c8bb4fe1ec8a4a
+size 1110008536

runs/May24_10-30-18_b37c2f13a272/events.out.tfevents.1716546642.b37c2f13a272.567.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e46677f85809cd3a125f1682cbde23aa73913530f216bd4b43271053dc8a05d6
+size 8434

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 +1,15 @@
+{
+  "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 sha256:49bfdee26ed7a4f61acd970cff9bf5062639fa3d3155584e58b842247ec7271b
+size 5176