haryoaw
/

scenario-TCR-XLMV-4_data-AmazonScience_massive_all_1_1

+---
+license: mit
+base_model: facebook/xlm-v-base
+tags:
+- generated_from_trainer
+datasets:
+- massive
+metrics:
+- accuracy
+- f1
+model-index:
+- name: scenario-TCR-XLMV-4_data-AmazonScience_massive_all_1_1
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: massive
+      type: massive
+      config: all_1.1
+      split: validation
+      args: all_1.1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.846210601990238
+    - name: F1
+      type: f1
+      value: 0.8244135214839245
+---
+<!-- 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. -->
+# scenario-TCR-XLMV-4_data-AmazonScience_massive_all_1_1
+This model is a fine-tuned version of [facebook/xlm-v-base](https://huggingface.co/facebook/xlm-v-base) on the massive dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8322
+- Accuracy: 0.8462
+- F1: 0.8244
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 777
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 500
+### Training results
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
+| 0.595         | 0.27  | 5000  | 0.7040          | 0.8241   | 0.7720 |
+| 0.4654        | 0.53  | 10000 | 0.6468          | 0.8410   | 0.8027 |
+| 0.3838        | 0.8   | 15000 | 0.6802          | 0.8399   | 0.7994 |
+| 0.2831        | 1.07  | 20000 | 0.7290          | 0.8471   | 0.8206 |
+| 0.274         | 1.34  | 25000 | 0.7192          | 0.8471   | 0.8141 |
+| 0.2598        | 1.6   | 30000 | 0.7145          | 0.8440   | 0.8215 |
+| 0.2501        | 1.87  | 35000 | 0.7347          | 0.8500   | 0.8245 |
+| 0.2022        | 2.14  | 40000 | 0.7809          | 0.8503   | 0.8223 |
+| 0.2164        | 2.41  | 45000 | 0.7481          | 0.8533   | 0.8280 |
+| 0.2008        | 2.67  | 50000 | 0.7684          | 0.8467   | 0.8252 |
+| 0.2015        | 2.94  | 55000 | 0.8170          | 0.8422   | 0.8160 |
+| 0.1716        | 3.21  | 60000 | 0.8603          | 0.8433   | 0.8186 |
+| 0.1643        | 3.47  | 65000 | 0.8221          | 0.8514   | 0.8279 |
+| 0.1816        | 3.74  | 70000 | 0.8322          | 0.8462   | 0.8244 |
+### Framework versions
+- Transformers 4.33.3
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json ADDED Viewed

	@@ -0,0 +1,152 @@

+{
+  "_name_or_path": "facebook/xlm-v-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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 901629
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bc2a105f1f436185f5e5c693fedb88737b8b1ecfd047d39dd09bf7232adaf2
+size 3114226670

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:574f60f39432eeee3a2b7a322fbc1dbe5c7196ab6d25a1cccfdb8781f62313c1
+size 4600