your_username/bert-emotion

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: summerschool-2layer-copa
+  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-copa
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8767
+- Accuracy: 0.7015
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.6792        | 0.2793 | 50   | 0.6678          | 0.5759   |
+| 0.6489        | 0.5587 | 100  | 0.6514          | 0.6147   |
+| 0.6282        | 0.8380 | 150  | 0.6360          | 0.6461   |
+| 0.5746        | 1.1173 | 200  | 0.6596          | 0.6492   |
+| 0.5325        | 1.3966 | 250  | 0.6253          | 0.6785   |
+| 0.5431        | 1.6760 | 300  | 0.6226          | 0.6712   |
+| 0.5058        | 1.9553 | 350  | 0.5896          | 0.6869   |
+| 0.3982        | 2.2346 | 400  | 0.6467          | 0.6859   |
+| 0.3837        | 2.5140 | 450  | 0.7012          | 0.6785   |
+| 0.3714        | 2.7933 | 500  | 0.7326          | 0.6586   |
+| 0.347         | 3.0726 | 550  | 0.7592          | 0.6702   |
+| 0.247         | 3.3520 | 600  | 0.7466          | 0.6942   |
+| 0.2382        | 3.6313 | 650  | 0.7514          | 0.6953   |
+| 0.2304        | 3.9106 | 700  | 0.8268          | 0.6838   |
+| 0.1716        | 4.1899 | 750  | 0.8822          | 0.6806   |
+| 0.1631        | 4.4693 | 800  | 0.8698          | 0.6932   |
+| 0.1435        | 4.7486 | 850  | 0.9178          | 0.6838   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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": 12,
+  "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:c5fda52742d6c6fdfbf5dc0960f8629bcaf5e6d842334f394fc409e2dfb3ca61
+size 437958648

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 sha256:96e43ee0d2f00f0aa361bb1f7794a3317a597d40c28f571a30a2fd65141a2b33
+size 5048