End of training

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: cf-bert-finetuned1
+  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. -->
+
+# cf-bert-finetuned1
+
+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: 0.4093
+- F1: 0.4801
+- Roc Auc: 0.6612
+- Accuracy: 0.2225
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| 0.4423        | 1.0   | 908  | 0.4344          | 0.3345 | 0.5977  | 0.1278   |
+| 0.4329        | 2.0   | 1816 | 0.4131          | 0.4700 | 0.6574  | 0.1927   |
+| 0.3924        | 3.0   | 2724 | 0.4041          | 0.4819 | 0.6630  | 0.2148   |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,51 @@
+{
+  "_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,
+  "id2label": {
+    "0": "math",
+    "1": "greedy",
+    "2": "implementation",
+    "3": "dp",
+    "4": "data structures",
+    "5": "constructive algorithms",
+    "6": "brute force",
+    "7": "binary search",
+    "8": "sortings",
+    "9": "graphs"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "binary search": 7,
+    "brute force": 6,
+    "constructive algorithms": 5,
+    "data structures": 4,
+    "dp": 3,
+    "graphs": 9,
+    "greedy": 1,
+    "implementation": 2,
+    "math": 0,
+    "sortings": 8
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "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 sha256:149b5aba73bd3ea67b2766ca29333d6cf463ecc5f9681488dd19a967cee1c803
+size 437983256

runs/Dec04_04-46-20_f1c855df4247/events.out.tfevents.1733287598.f1c855df4247.1049.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d02cd4642cefe38b700e3eb1bc55072ef4d32d026282b957e95a00f15b7525
+size 64543

runs/Dec04_04-46-20_f1c855df4247/events.out.tfevents.1733289892.f1c855df4247.1049.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455cdce16dfb18b44bdfbe719e1a6628a652cae26f85a8d7ee91e50c7262610f
+size 508

runs/Dec04_05-33-05_f1c855df4247/events.out.tfevents.1733290389.f1c855df4247.13023.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e651c817850c7d98df7a3a07c50c7534d1a9bd6b98007dbdaaaf2a972ed8cedb
+size 64543

runs/Dec04_05-33-05_f1c855df4247/events.out.tfevents.1733292644.f1c855df4247.13023.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed68aeb5a4288b3172ac457a50dc642220359fe996e23fcf9012be831868b75
+size 508

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 +1,55 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 sha256:940eb07e7f58c07a0c73df24897e620ac2e4ea9696ed8daeec8dd56692c23124
+size 5304