End of training

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/Multilingual-MiniLM-L12-H384
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: m-minilm-l12-h384-dra-tam-mal-aw-classification-finetune
+  results: []
+---
+
+<!-- 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. -->
+
+# m-minilm-l12-h384-dra-tam-mal-aw-classification-finetune
+
+This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5902
+- Accuracy: 0.7441
+- F1: 0.7577
+
+## 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: 0.0001
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
+| 0.6813        | 0.4444 | 20   | 0.6168          | 0.6903   | 0.7027 |
+| 0.6418        | 0.8889 | 40   | 0.5810          | 0.7058   | 0.7058 |
+| 0.5704        | 1.3333 | 60   | 0.5545          | 0.7205   | 0.6946 |
+| 0.5575        | 1.7778 | 80   | 0.5344          | 0.7359   | 0.7457 |
+| 0.5107        | 2.2222 | 100  | 0.5341          | 0.7498   | 0.7256 |
+| 0.4649        | 2.6667 | 120  | 0.5298          | 0.7506   | 0.7528 |
+| 0.4559        | 3.1111 | 140  | 0.5420          | 0.7522   | 0.7185 |
+| 0.4031        | 3.5556 | 160  | 0.5952          | 0.7253   | 0.7524 |
+| 0.3834        | 4.0    | 180  | 0.5535          | 0.7596   | 0.7476 |
+| 0.3359        | 4.4444 | 200  | 0.5902          | 0.7441   | 0.7577 |
+| 0.3423        | 4.8889 | 220  | 0.5629          | 0.7563   | 0.7498 |
+| 0.2728        | 5.3333 | 240  | 0.5906          | 0.7588   | 0.7513 |
+| 0.289         | 5.7778 | 260  | 0.6064          | 0.7555   | 0.7496 |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01511a6e89ea33d7585e564bf220682b516ecdbc71b2624f47750b27eb956905
+size 470641664

tam_mal_ai_aw_classification_adapter/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "architecture": "reft",
+    "dropout": 0.05,
+    "layers": "all",
+    "non_linearity": null,
+    "orthogonality": true,
+    "output_reft": true,
+    "prefix_positions": 3,
+    "r": 1,
+    "suffix_positions": 0,
+    "tied_weights": false
+  },
+  "config_id": "141e29e6c21f7261",
+  "hidden_size": 384,
+  "model_class": "BertAdapterModel",
+  "model_name": "microsoft/Multilingual-MiniLM-L12-H384",
+  "model_type": "bert",
+  "name": "tam_mal_ai_aw_classification_adapter",
+  "version": "adapters.1.0.1"
+}

tam_mal_ai_aw_classification_adapter/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdf86f79a6bcce775e3b892b942fcc5cdc2babe31794ac1d2bb383654cfaef1
+size 14269270

tam_mal_ai_aw_classification_head/head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "Abusive": 1,
+      "Non-Abusive": 0
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 384,
+  "model_class": "BertAdapterModel",
+  "model_name": "microsoft/Multilingual-MiniLM-L12-H384",
+  "model_type": "bert",
+  "name": "tam_mal_ai_aw_classification_head",
+  "version": "adapters.1.0.1"
+}

tam_mal_ai_aw_classification_head/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181eff46642ee9182bc0e90a75c404bbbd4739e0b73b589fd6e5fc5a2dcf60ac
+size 596712

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b877ef47f17cf8f7d106413ede14183e5f1ea631a0b48b57136b5f3afe70910a
+size 5304