AmirlyPhd/final_V1-roberta-text-classification-model

README.md

@@ -0,0 +1,94 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: final_V1-roberta-text-classification-model
+  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. -->
+
+# final_V1-roberta-text-classification-model
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2223
+- Accuracy: 0.9595
+- F1: 0.8274
+- Precision: 0.8263
+- Recall: 0.8294
+
+## 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: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.6161        | 0.11  | 50   | 1.5152          | 0.4668   | 0.2435 | 0.2538    | 0.2617 |
+| 0.6416        | 0.22  | 100  | 0.8046          | 0.7383   | 0.4474 | 0.4688    | 0.4675 |
+| 0.3606        | 0.33  | 150  | 0.4826          | 0.8917   | 0.6667 | 0.6578    | 0.6789 |
+| 0.3063        | 0.44  | 200  | 0.4505          | 0.8923   | 0.6638 | 0.6562    | 0.6752 |
+| 0.2098        | 0.55  | 250  | 0.5294          | 0.8934   | 0.6602 | 0.6443    | 0.6769 |
+| 0.2269        | 0.66  | 300  | 0.3460          | 0.8977   | 0.6702 | 0.6626    | 0.6784 |
+| 0.1874        | 0.76  | 350  | 0.5650          | 0.8715   | 0.6497 | 0.6302    | 0.6719 |
+| 0.2914        | 0.87  | 400  | 0.5704          | 0.8901   | 0.6608 | 0.6433    | 0.6798 |
+| 0.1799        | 0.98  | 450  | 0.6265          | 0.8482   | 0.6321 | 0.7509    | 0.6583 |
+| 0.1625        | 1.09  | 500  | 0.3098          | 0.9144   | 0.7058 | 0.8019    | 0.7080 |
+| 0.0929        | 1.2   | 550  | 0.3927          | 0.9147   | 0.7113 | 0.7939    | 0.7122 |
+| 0.096         | 1.31  | 600  | 0.2251          | 0.9497   | 0.8113 | 0.8129    | 0.8112 |
+| 0.0862        | 1.42  | 650  | 0.1522          | 0.9655   | 0.8264 | 0.8235    | 0.8297 |
+| 0.0943        | 1.53  | 700  | 0.2669          | 0.9480   | 0.8207 | 0.8184    | 0.8240 |
+| 0.0799        | 1.64  | 750  | 0.2508          | 0.9532   | 0.8208 | 0.8155    | 0.8287 |
+| 0.1052        | 1.75  | 800  | 0.1721          | 0.9653   | 0.8300 | 0.8291    | 0.8313 |
+| 0.0867        | 1.86  | 850  | 0.1813          | 0.9658   | 0.8290 | 0.8262    | 0.8326 |
+| 0.0616        | 1.97  | 900  | 0.2174          | 0.9590   | 0.8255 | 0.8216    | 0.8313 |
+| 0.0704        | 2.07  | 950  | 0.1680          | 0.9672   | 0.8305 | 0.8245    | 0.8376 |
+| 0.0436        | 2.18  | 1000 | 0.2169          | 0.9601   | 0.8264 | 0.8243    | 0.8299 |
+| 0.0603        | 2.29  | 1050 | 0.1769          | 0.9634   | 0.8272 | 0.8220    | 0.8338 |
+| 0.0638        | 2.4   | 1100 | 0.1431          | 0.9699   | 0.8300 | 0.8230    | 0.8380 |
+| 0.017         | 2.51  | 1150 | 0.1741          | 0.9658   | 0.8294 | 0.8243    | 0.8358 |
+| 0.0025        | 2.62  | 1200 | 0.2140          | 0.9623   | 0.8270 | 0.8218    | 0.8340 |
+| 0.0427        | 2.73  | 1250 | 0.1680          | 0.9680   | 0.8293 | 0.8227    | 0.8372 |
+| 0.0421        | 2.84  | 1300 | 0.1580          | 0.9691   | 0.8297 | 0.8231    | 0.8375 |
+| 0.0292        | 2.95  | 1350 | 0.1597          | 0.9699   | 0.8315 | 0.8260    | 0.8381 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "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": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c564c1367fc100ea394ddf282d7ef6e64584c46c1ab06f60e5ea9662e3671054
+size 498628204

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_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea2dbc54ce6382641896ebb0ade8be662f5ce514c3d87f68305e96327447bad
+size 4920