tag-clf

README.md

@@ -0,0 +1,56 @@
+---
+base_model: microsoft/codebert-base
+tags:
+- generated_from_trainer
+model-index:
+- name: tag_clf
+  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. -->
+
+# tag_clf
+
+This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0173
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0189        | 1.0   | 3000 | 0.0173          |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "microsoft/codebert-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": "2-sat",
+    "1": "binary search",
+    "2": "bitmasks",
+    "3": "brute force",
+    "4": "combinatorics",
+    "5": "constructive algorithms",
+    "6": "data structures",
+    "7": "dfs and similar",
+    "8": "divide and conquer",
+    "9": "dp",
+    "10": "dsu",
+    "11": "expression parsing",
+    "12": "games",
+    "13": "geometry",
+    "14": "graphs",
+    "15": "greedy",
+    "16": "hashing",
+    "17": "implementation",
+    "18": "math",
+    "19": "matrices",
+    "20": "meet-in-the-middle",
+    "21": "none",
+    "22": "number theory",
+    "23": "probabilities",
+    "24": "schedules",
+    "25": "shortest paths",
+    "26": "sortings",
+    "27": "strings",
+    "28": "trees",
+    "29": "two pointers"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "2-sat": 0,
+    "binary search": 1,
+    "bitmasks": 2,
+    "brute force": 3,
+    "combinatorics": 4,
+    "constructive algorithms": 5,
+    "data structures": 6,
+    "dfs and similar": 7,
+    "divide and conquer": 8,
+    "dp": 9,
+    "dsu": 10,
+    "expression parsing": 11,
+    "games": 12,
+    "geometry": 13,
+    "graphs": 14,
+    "greedy": 15,
+    "hashing": 16,
+    "implementation": 17,
+    "math": 18,
+    "matrices": 19,
+    "meet-in-the-middle": 20,
+    "none": 21,
+    "number theory": 22,
+    "probabilities": 23,
+    "schedules": 24,
+    "shortest paths": 25,
+    "sortings": 26,
+    "strings": 27,
+    "trees": 28,
+    "two pointers": 29
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "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 sha256:8bca49a71b790f31546506fdf22c6c51beb2befa539041e397273903c3ccd33b
+size 498698952

runs/May22_20-01-06_6ad0e15f0760/events.out.tfevents.1716408067.6ad0e15f0760.193.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c09ed342d78b2b70101c85138b7cad726cfaf831f003119df58767b555f0ab
+size 8160

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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:c848197294ca5a6246631297ebbcec7f32f964e78fb62aef98682743f8b86871
+size 5112