End of training

.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

README.md

@@ -0,0 +1,84 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+datasets:
+- massive
+metrics:
+- accuracy
+- f1
+model-index:
+- name: xlm-roberta-base-finetuned-massive
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: massive
+      type: massive
+      config: ja-JP
+      split: validation
+      args: ja-JP
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8327594687653713
+    - name: F1
+      type: f1
+      value: 0.8192120367052886
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# xlm-roberta-base-finetuned-massive
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the massive dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7539
+- Accuracy: 0.8328
+- F1: 0.8192
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.06
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 2.9836        | 0.69  | 500  | 1.6188          | 0.6257   | 0.5524 |
+| 1.4569        | 1.39  | 1000 | 1.0347          | 0.7575   | 0.7251 |
+| 1.0211        | 2.08  | 1500 | 0.8186          | 0.8205   | 0.8024 |
+| 0.7799        | 2.78  | 2000 | 0.7539          | 0.8328   | 0.8192 |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,153 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": "datetime_query",
+    "1": "iot_hue_lightchange",
+    "2": "transport_ticket",
+    "3": "takeaway_query",
+    "4": "qa_stock",
+    "5": "general_greet",
+    "6": "recommendation_events",
+    "7": "music_dislikeness",
+    "8": "iot_wemo_off",
+    "9": "cooking_recipe",
+    "10": "qa_currency",
+    "11": "transport_traffic",
+    "12": "general_quirky",
+    "13": "weather_query",
+    "14": "audio_volume_up",
+    "15": "email_addcontact",
+    "16": "takeaway_order",
+    "17": "email_querycontact",
+    "18": "iot_hue_lightup",
+    "19": "recommendation_locations",
+    "20": "play_audiobook",
+    "21": "lists_createoradd",
+    "22": "news_query",
+    "23": "alarm_query",
+    "24": "iot_wemo_on",
+    "25": "general_joke",
+    "26": "qa_definition",
+    "27": "social_query",
+    "28": "music_settings",
+    "29": "audio_volume_other",
+    "30": "calendar_remove",
+    "31": "iot_hue_lightdim",
+    "32": "calendar_query",
+    "33": "email_sendemail",
+    "34": "iot_cleaning",
+    "35": "audio_volume_down",
+    "36": "play_radio",
+    "37": "cooking_query",
+    "38": "datetime_convert",
+    "39": "qa_maths",
+    "40": "iot_hue_lightoff",
+    "41": "iot_hue_lighton",
+    "42": "transport_query",
+    "43": "music_likeness",
+    "44": "email_query",
+    "45": "play_music",
+    "46": "audio_volume_mute",
+    "47": "social_post",
+    "48": "alarm_set",
+    "49": "qa_factoid",
+    "50": "calendar_set",
+    "51": "play_game",
+    "52": "alarm_remove",
+    "53": "lists_remove",
+    "54": "transport_taxi",
+    "55": "recommendation_movies",
+    "56": "iot_coffee",
+    "57": "music_query",
+    "58": "play_podcasts",
+    "59": "lists_query"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "alarm_query": 23,
+    "alarm_remove": 52,
+    "alarm_set": 48,
+    "audio_volume_down": 35,
+    "audio_volume_mute": 46,
+    "audio_volume_other": 29,
+    "audio_volume_up": 14,
+    "calendar_query": 32,
+    "calendar_remove": 30,
+    "calendar_set": 50,
+    "cooking_query": 37,
+    "cooking_recipe": 9,
+    "datetime_convert": 38,
+    "datetime_query": 0,
+    "email_addcontact": 15,
+    "email_query": 44,
+    "email_querycontact": 17,
+    "email_sendemail": 33,
+    "general_greet": 5,
+    "general_joke": 25,
+    "general_quirky": 12,
+    "iot_cleaning": 34,
+    "iot_coffee": 56,
+    "iot_hue_lightchange": 1,
+    "iot_hue_lightdim": 31,
+    "iot_hue_lightoff": 40,
+    "iot_hue_lighton": 41,
+    "iot_hue_lightup": 18,
+    "iot_wemo_off": 8,
+    "iot_wemo_on": 24,
+    "lists_createoradd": 21,
+    "lists_query": 59,
+    "lists_remove": 53,
+    "music_dislikeness": 7,
+    "music_likeness": 43,
+    "music_query": 57,
+    "music_settings": 28,
+    "news_query": 22,
+    "play_audiobook": 20,
+    "play_game": 51,
+    "play_music": 45,
+    "play_podcasts": 58,
+    "play_radio": 36,
+    "qa_currency": 10,
+    "qa_definition": 26,
+    "qa_factoid": 49,
+    "qa_maths": 39,
+    "qa_stock": 4,
+    "recommendation_events": 6,
+    "recommendation_locations": 19,
+    "recommendation_movies": 55,
+    "social_post": 47,
+    "social_query": 27,
+    "takeaway_order": 16,
+    "takeaway_query": 3,
+    "transport_query": 42,
+    "transport_taxi": 54,
+    "transport_ticket": 2,
+    "transport_traffic": 11,
+    "weather_query": 13
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbd6aa7df0dd20860717ac15f387bdc0792074565c3dcace55ffe04c10f33db
+size 1112425265

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 sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 256,
+  "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 sha256:55e603f6173090b5498f44ac768f33c93d8f991b5dbda7b4a0e7184aa1c936db
+size 4027