test

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+license: mit
+base_model: prajjwal1/bert-tiny
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: test
+  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. -->
+
+# test
+
+This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7072
+- F1: 0.0
+- Roc Auc: 0.5
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- training_steps: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1  | Roc Auc |
+|:-------------:|:-----:|:----:|:---------------:|:---:|:-------:|
+| No log        | 1.0   | 1    | 0.7394          | 0.0 | 0.5     |
+| No log        | 2.0   | 2    | 0.7378          | 0.0 | 0.5     |
+| No log        | 3.0   | 3    | 0.7361          | 0.0 | 0.5     |
+| No log        | 4.0   | 4    | 0.7347          | 0.0 | 0.5     |
+| No log        | 5.0   | 5    | 0.7332          | 0.0 | 0.5     |
+| No log        | 6.0   | 6    | 0.7319          | 0.0 | 0.5     |
+| No log        | 7.0   | 7    | 0.7307          | 0.0 | 0.5     |
+| No log        | 8.0   | 8    | 0.7293          | 0.0 | 0.5     |
+| No log        | 9.0   | 9    | 0.7281          | 0.0 | 0.5     |
+| No log        | 10.0  | 10   | 0.7271          | 0.0 | 0.5     |
+| No log        | 11.0  | 11   | 0.7262          | 0.0 | 0.5     |
+| No log        | 12.0  | 12   | 0.7253          | 0.0 | 0.5     |
+| No log        | 13.0  | 13   | 0.7245          | 0.0 | 0.5     |
+| No log        | 14.0  | 14   | 0.7239          | 0.0 | 0.5     |
+| No log        | 15.0  | 15   | 0.7233          | 0.0 | 0.5     |
+| No log        | 16.0  | 16   | 0.7228          | 0.0 | 0.5     |
+| No log        | 17.0  | 17   | 0.7224          | 0.0 | 0.5     |
+| No log        | 18.0  | 18   | 0.7221          | 0.0 | 0.5     |
+| No log        | 19.0  | 19   | 0.7219          | 0.0 | 0.5     |
+| No log        | 20.0  | 20   | 0.7218          | 0.0 | 0.5     |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cpu
+- Datasets 4.1.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "I/E",
+    "1": "N/S",
+    "2": "T/F",
+    "3": "J/P"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "I/E": 0,
+    "J/P": 3,
+    "N/S": 1,
+    "T/F": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "transformers_version": "4.56.1",
+  "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:bd8b3755624562380827932818839b7f8086f9be7d31bba700264524192e2cbf
+size 17550344

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 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "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:a19110f30334f8abaa29ab07c30dd93748cc5b064ba2674ba143411c862e970c
+size 5713