End of training

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+base_model: livinNector/m-minilm-l12-h384-dra-tam-mal-aw-setfit-finetune
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: m-minilm-l12-h384-dra-tam-mal-aw-setfit-double-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-setfit-double-finetune
+
+This model is a fine-tuned version of [livinNector/m-minilm-l12-h384-dra-tam-mal-aw-setfit-finetune](https://huggingface.co/livinNector/m-minilm-l12-h384-dra-tam-mal-aw-setfit-finetune) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5252
+- Accuracy: 0.7759
+- F1: 0.7752
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
+| 0.6682        | 0.4444 | 20   | 0.6228          | 0.6659   | 0.6625 |
+| 0.6171        | 0.8889 | 40   | 0.6035          | 0.6789   | 0.6756 |
+| 0.5673        | 1.3333 | 60   | 0.5673          | 0.7188   | 0.7155 |
+| 0.5481        | 1.7778 | 80   | 0.5864          | 0.6993   | 0.6937 |
+| 0.5137        | 2.2222 | 100  | 0.5245          | 0.7465   | 0.7440 |
+| 0.4527        | 2.6667 | 120  | 0.5279          | 0.7522   | 0.7506 |
+| 0.4596        | 3.1111 | 140  | 0.5172          | 0.7579   | 0.7576 |
+| 0.3943        | 3.5556 | 160  | 0.5366          | 0.7514   | 0.7514 |
+| 0.3836        | 4.0    | 180  | 0.5387          | 0.7628   | 0.7627 |
+| 0.3627        | 4.4444 | 200  | 0.5802          | 0.7490   | 0.7480 |
+| 0.3302        | 4.8889 | 220  | 0.5616          | 0.7563   | 0.7563 |
+| 0.2999        | 5.3333 | 240  | 0.5745          | 0.7620   | 0.7598 |
+| 0.3061        | 5.7778 | 260  | 0.5651          | 0.7694   | 0.7689 |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "livinNector/m-minilm-l12-h384-dra-tam-mal-aw-setfit-finetune",
+  "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": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

default/head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "embedding_size": 768,
+    "head_type": "masked_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": false,
+    "vocab_size": 250000
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "ai4bharat/IndicBERTv2-MLM-only",
+  "model_type": "bert",
+  "name": "default",
+  "version": "adapters.1.0.1"
+}

default/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ade58fc9df9dbd31f6b4dfb0ec3bcafffbd5f20b8f19438fbadbddf6688352
+size 771371254

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84451016f0ccc71fabdf2ec6403cf5057b0539307ad6903b30d3e18da7f1c0d2
+size 470641664

tam_mal_ai_aw_classification_adapter/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "config": {
+    "alpha": 8,
+    "architecture": "lora",
+    "attn_matrices": [
+      "q",
+      "v"
+    ],
+    "composition_mode": "add",
+    "dropout": 0.1,
+    "init_weights": "lora",
+    "intermediate_lora": false,
+    "leave_out": [],
+    "output_lora": false,
+    "r": 12,
+    "selfattn_lora": true,
+    "use_gating": false
+  },
+  "config_id": "a0c8452a4cfb970e",
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "ai4bharat/IndicBERTv2-MLM-only",
+  "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 sha256:5b924cc8d8ea3bb7be73459cf3bc217f1dda9e5607a9be79faa037f4ca483f54
+size 1788390

tam_mal_ai_aw_classification_head/head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "ReLU",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "Abusive": 1,
+      "Non-Abusive": 0
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "ai4bharat/IndicBERTv2-MLM-only",
+  "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 sha256:0e7d8c1397bae7f2d2c0043913999e01f2c1a6cf0c1f88a37c663f5ab7f3ae94
+size 2370792

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97774b1ccd25c8504004565111a922efc61ed6eddc008185418a7686ba03239e
+size 5432