push

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: mit
+base_model: chandar-lab/NeoBERT
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: NeoBERT_druglib_regression_6ep_5e-06lr
+  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. -->
+
+# NeoBERT_druglib_regression_6ep_5e-06lr
+
+This model is a fine-tuned version of [chandar-lab/NeoBERT](https://huggingface.co/chandar-lab/NeoBERT) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9323
+- Accuracy: 0.6284
+- Macro Precision: 0.6396
+- Macro Recall: 0.5598
+- Macro F1: 0.5573
+
+## 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: 5e-06
+- 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
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 6
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro Precision | Macro Recall | Macro F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|
+| 1.2053        | 1.0   | 311  | 1.0258          | 0.5900   | 0.5546          | 0.4409       | 0.4394   |
+| 0.743         | 2.0   | 622  | 0.8838          | 0.6527   | 0.6404          | 0.5392       | 0.5352   |
+| 0.5941        | 3.0   | 933  | 0.9091          | 0.6624   | 0.6102          | 0.5566       | 0.5674   |
+| 0.4384        | 4.0   | 1244 | 1.0823          | 0.6592   | 0.6108          | 0.5464       | 0.5493   |
+| 0.138         | 5.0   | 1555 | 1.3475          | 0.6543   | 0.5926          | 0.5503       | 0.5600   |
+| 0.0683        | 6.0   | 1866 | 1.4926          | 0.6495   | 0.5865          | 0.5571       | 0.5668   |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "chandar-lab/NeoBERT",
+  "architectures": [
+    "NeoBERTForSequenceClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "chandar-lab/NeoBERT--model.NeoBERTConfig",
+    "AutoModel": "chandar-lab/NeoBERT--model.NeoBERT",
+    "AutoModelForMaskedLM": "chandar-lab/NeoBERT--model.NeoBERTLMHead",
+    "AutoModelForSequenceClassification": "chandar-lab/NeoBERT--model.NeoBERTForSequenceClassification"
+  },
+  "classifier_init_range": 0.02,
+  "decoder_init_range": 0.02,
+  "dim_head": 64,
+  "embedding_init_range": 0.02,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "intermediate_size": 3072,
+  "kwargs": {
+    "_commit_hash": "a4fbc49a61db10ff2db66140ae59c09d96c027f9",
+    "architectures": [
+      "NeoBERTLMHead"
+    ],
+    "attn_implementation": null,
+    "auto_map": {
+      "AutoConfig": "chandar-lab/NeoBERT--model.NeoBERTConfig",
+      "AutoModel": "chandar-lab/NeoBERT--model.NeoBERT",
+      "AutoModelForMaskedLM": "chandar-lab/NeoBERT--model.NeoBERTLMHead",
+      "AutoModelForSequenceClassification": "chandar-lab/NeoBERT--model.NeoBERTForSequenceClassification"
+    },
+    "classifier_init_range": 0.02,
+    "dim_head": 64,
+    "kwargs": {
+      "classifier_init_range": 0.02,
+      "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
+      "trust_remote_code": true
+    },
+    "model_type": "neobert",
+    "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
+    "torch_dtype": "float32",
+    "transformers_version": "4.48.2",
+    "trust_remote_code": true
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "max_length": 4096,
+  "model_type": "neobert",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "pad_token_id": 0,
+  "pretrained_model_name_or_path": "google-bert/bert-base-uncased",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "trust_remote_code": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac01ccad99ef27afdb4b62034f50fc8bad0b0e71d4bb018775daf02b938f21b
+size 889059812

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 4096,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_size": 30522
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718435625e87777a919da05820612c2f6b1d3204a732ac4cf49fc44b7ca19a84
+size 5368