Model save

README.md

@@ -1,3 +1,61 @@
 ---
-license: apache-2.0
+library_name: transformers
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: math_token_classification
+  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. -->
+
+# math_token_classification
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2459
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- 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
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4177        | 1.0   | 83   | 0.3656          |
+| 0.4853        | 2.0   | 166  | 0.2629          |
+| 0.2995        | 3.0   | 249  | 0.2459          |
+
+
+### Framework versions
+
+- Transformers 5.16.1
+- Pytorch 2.11.0+cu128
+- Datasets 4.8.5
+- Tokenizers 0.23.1

config.json

@@ -0,0 +1,51 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "-100": "SPECIAL_TOKEN",
+    "0": "O",
+    "1": "B-ALGEBRA",
+    "2": "I-ALGEBRA",
+    "3": "B-CALCULUS",
+    "4": "I-CALCULUS",
+    "5": "B-GEOMETRY",
+    "6": "I-GEOMETRY",
+    "7": "B-TRIGONOMETRY",
+    "8": "I-TRIGONOMETRY"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "B-ALGEBRA": 1,
+    "B-CALCULUS": 3,
+    "B-GEOMETRY": 5,
+    "B-TRIGONOMETRY": 7,
+    "I-ALGEBRA": 2,
+    "I-CALCULUS": 4,
+    "I-GEOMETRY": 6,
+    "I-TRIGONOMETRY": 8,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768e54d0330794f5e508204dcdbcba2043808cacb5f14fe66bd1300ae965e09a
+size 496274848

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "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:dd60ea97b38a4623de45aa4a7e25eba5b5a79a4f2a0e6f22336cfa15d569d3c7
+size 5265