haspeech_ita

.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

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: bert-base-uncased
+license: gpl-3.0
+base_model: MilaNLProc/hate-ita-xlm-r-large
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # haspeech_ita
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [MilaNLProc/hate-ita-xlm-r-large](https://huggingface.co/MilaNLProc/hate-ita-xlm-r-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0790
-- Accuracy: 0.9864
+- Loss: 0.0030
+- Accuracy: 0.9973
 
 ## Model description
 
@@ -38,29 +38,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 24
-- eval_batch_size: 8
+- 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_steps: 500
-- num_epochs: 8
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6234        | 0.72  | 100  | 0.5780          | 0.7154   |
-| 0.5659        | 1.44  | 200  | 0.4837          | 0.7561   |
-| 0.3889        | 2.16  | 300  | 0.3320          | 0.8699   |
-| 0.2578        | 2.88  | 400  | 0.3299          | 0.8916   |
-| 0.1668        | 3.6   | 500  | 0.1727          | 0.9512   |
-| 0.0941        | 4.32  | 600  | 0.2214          | 0.9485   |
-| 0.0698        | 5.04  | 700  | 0.0750          | 0.9864   |
-| 0.0305        | 5.76  | 800  | 0.0386          | 0.9919   |
-| 0.0145        | 6.47  | 900  | 0.1088          | 0.9783   |
-| 0.0094        | 7.19  | 1000 | 0.0591          | 0.9892   |
-| 0.0014        | 7.91  | 1100 | 0.0790          | 0.9864   |
+| 0.3538        | 0.48  | 100  | 0.2109          | 0.9241   |
+| 0.18          | 0.96  | 200  | 0.1058          | 0.9783   |
+| 0.0924        | 1.44  | 300  | 0.0618          | 0.9892   |
+| 0.0948        | 1.92  | 400  | 0.0382          | 0.9892   |
+| 0.0475        | 2.4   | 500  | 0.0607          | 0.9919   |
+| 0.0572        | 2.88  | 600  | 0.0030          | 0.9973   |
 
 
 ### Framework versions

config.json

@@ -1,27 +1,43 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "MilaNLProc/hate-ita-xlm-r-large",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
   "architectures": [
-    "BertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "non-hateful",
+    "1": "hateful"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "intermediate_size": 4096,
+  "label2id": {
+    "hateful": 1,
+    "non-hateful": 0
+  },
+  "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",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5983859e0efccf64d7cf7c4aaeee363180336560d190a4b54b50d7acea7af970
-size 437958648
+oid sha256:8b7a8ed7787c22cfde40788bc207bc776c4e37f112c84d875a3cc9aad59bf1e1
+size 2239618672

runs/Nov27_13-02-24_13035cb65e56/events.out.tfevents.1701090147.13035cb65e56.29582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4105d4f9c3e8f135112d3fc3d99c1ed9a397921c7d47126628e53670eecbf3c
+size 4591

runs/Nov27_13-03-09_13035cb65e56/events.out.tfevents.1701090191.13035cb65e56.30115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d38535abd1b6b11603f087b1b6d30a23b805a72f8d80c3bb426fe63dd64cff
+size 4591

runs/Nov27_13-12-33_d9cf46c62339/events.out.tfevents.1701090758.d9cf46c62339.647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd5e9f470a016461a9e01e26a1f1a9005f64a604a2beb0af58319af727b3976
+size 4591

runs/Nov27_13-13-38_d9cf46c62339/events.out.tfevents.1701090819.d9cf46c62339.1210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6330678cbb04a0ca7d1410901b9371cee927fd37e6d831cfc1ec12a2cb84ad5c
+size 6981

runs/Nov27_13-27-17_d9cf46c62339/events.out.tfevents.1701091638.d9cf46c62339.3722.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f9f9a7626710dc947cad52804dbc73ba3b98cc2978a23402a5404b3d404252
+size 7815

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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_config.json

@@ -1,55 +1,54 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5235dc938f86bee540aac50fdf1bd36503e8f8559981eab08855a47c2cad384
+oid sha256:201dea1895347b307260a950849cfc370b8f145200ab86273d0963a5b019a9c8
 size 4155