ModernBERT fine-tuning complete

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: answerdotai/ModernBERT-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: modernbert-web3-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. -->
+
+# modernbert-web3-classification
+
+This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2032
+- Accuracy: 0.7110
+- F1: 0.6925
+
+## 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: 32
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 3.3409        | 1.0   | 681  | 1.3014          | 0.5764   | 0.5315 |
+| 2.4615        | 2.0   | 1362 | 1.1848          | 0.6244   | 0.5946 |
+| 1.2474        | 3.0   | 2043 | 1.1272          | 0.7007   | 0.6732 |
+| 0.4366        | 4.0   | 2724 | 1.3125          | 0.7129   | 0.6896 |
+| 0.2036        | 5.0   | 3405 | 1.4978          | 0.7158   | 0.6990 |
+| 0.027         | 6.0   | 4086 | 1.7242          | 0.7116   | 0.6997 |
+| 0.0179        | 7.0   | 4767 | 1.8611          | 0.7269   | 0.7133 |
+| 0.0155        | 8.0   | 5448 | 2.1055          | 0.7031   | 0.6825 |
+| 0.0093        | 9.0   | 6129 | 2.2032          | 0.7110   | 0.6925 |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,105 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "unknown",
+    "1": "ai-agent",
+    "2": "desci",
+    "3": "depin",
+    "4": "memefi",
+    "5": "runes",
+    "6": "erc314",
+    "7": "dn404",
+    "8": "erc404",
+    "9": "rwa",
+    "10": "ordinals",
+    "11": "inscriptions",
+    "12": "ai",
+    "13": "socialfi",
+    "14": "tool",
+    "15": "gamblefi",
+    "16": "memecoin",
+    "17": "automation",
+    "18": "stablecoin",
+    "19": "other",
+    "20": "infrastructure",
+    "21": "metaverse",
+    "22": "dao",
+    "23": "gamefi",
+    "24": "nftfi",
+    "25": "defi",
+    "26": "nft"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "ai": 12,
+    "ai-agent": 1,
+    "automation": 17,
+    "dao": 22,
+    "defi": 25,
+    "depin": 3,
+    "desci": 2,
+    "dn404": 7,
+    "erc314": 6,
+    "erc404": 8,
+    "gamblefi": 15,
+    "gamefi": 23,
+    "infrastructure": 20,
+    "inscriptions": 11,
+    "memecoin": 16,
+    "memefi": 4,
+    "metaverse": 21,
+    "nft": 26,
+    "nftfi": 24,
+    "ordinals": 10,
+    "other": 19,
+    "runes": 5,
+    "rwa": 9,
+    "socialfi": 13,
+    "stablecoin": 18,
+    "tool": 14,
+    "unknown": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "reference_compile": true,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbd0c6975c425a728490a580973747504cc9fac860057e134fc9934fe5127ae
+size 598516692

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3845c05056871b3cdf085eb3e0ce588e5e789fab7e73d778f56f009926694063
+size 5368