afaji/summerschool-2layer-irony

README.md

@@ -0,0 +1,74 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: summerschool-2layer-irony
+  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. -->
+
+# summerschool-2layer-irony
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6777
+- Accuracy: 0.5765
+
+## 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: 2e-05
+- 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
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.7183        | 0.2793 | 50   | 0.6864          | 0.5581   |
+| 0.6948        | 0.5587 | 100  | 0.7066          | 0.5068   |
+| 0.6915        | 0.8380 | 150  | 0.6904          | 0.5403   |
+| 0.686         | 1.1173 | 200  | 0.6764          | 0.5623   |
+| 0.6511        | 1.3966 | 250  | 0.6981          | 0.5623   |
+| 0.6752        | 1.6760 | 300  | 0.7057          | 0.5351   |
+| 0.661         | 1.9553 | 350  | 0.6755          | 0.5686   |
+| 0.6343        | 2.2346 | 400  | 0.6735          | 0.5874   |
+| 0.6507        | 2.5140 | 450  | 0.6700          | 0.5895   |
+| 0.6408        | 2.7933 | 500  | 0.6734          | 0.5738   |
+| 0.6337        | 3.0726 | 550  | 0.6697          | 0.5843   |
+| 0.6013        | 3.3520 | 600  | 0.6694          | 0.5927   |
+| 0.6139        | 3.6313 | 650  | 0.6667          | 0.6031   |
+| 0.6037        | 3.9106 | 700  | 0.6676          | 0.6168   |
+| 0.592         | 4.1899 | 750  | 0.6691          | 0.5832   |
+| 0.5791        | 4.4693 | 800  | 0.6707          | 0.5864   |
+| 0.5884        | 4.7486 | 850  | 0.6599          | 0.6042   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64e30a72b26c0c51b459df995bc5ca386f1e3fbb5825cb0f9930c1234c70933
+size 154424904

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f908cfdd006a3ebd5ea4d4896861d52852246628ad7ae0e0820e5dd8faca4d1
+size 5048