End of training

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: allenai/specter2_base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [allenai/specter2_base](https://huggingface.co/allenai/specter2_base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0598
+- Accuracy: 0.8310
+- Precision Micro: 0.8310
+- Precision Macro: 0.8290
+- Recall Micro: 0.8310
+- Recall Macro: 0.8276
+- F1 Micro: 0.8310
+- F1 Macro: 0.8263
+
+## 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: 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Micro | Precision Macro | Recall Micro | Recall Macro | F1 Micro | F1 Macro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:------------:|:------------:|:--------:|:--------:|
+| 0.2603        | 1.0   | 1094 | 0.6733          | 0.8243   | 0.8243          | 0.8315          | 0.8243       | 0.8198       | 0.8243   | 0.8222   |
+| 0.1779        | 2.0   | 2188 | 0.6955          | 0.8240   | 0.8240          | 0.8198          | 0.8240       | 0.8203       | 0.8240   | 0.8176   |
+| 0.1628        | 3.0   | 3282 | 0.8130          | 0.8315   | 0.8315          | 0.8296          | 0.8315       | 0.8265       | 0.8315   | 0.8269   |
+| 0.1136        | 4.0   | 4376 | 0.9842          | 0.8227   | 0.8227          | 0.8254          | 0.8227       | 0.8192       | 0.8227   | 0.8205   |
+| 0.0666        | 5.0   | 5470 | 1.0598          | 0.8310   | 0.8310          | 0.8290          | 0.8310       | 0.8276       | 0.8310   | 0.8263   |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,73 @@
+{
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Art",
+    "1": "Biology",
+    "2": "Business",
+    "3": "Chemistry",
+    "4": "Computer science",
+    "5": "Economics",
+    "6": "Engineering",
+    "7": "Environmental science",
+    "8": "Geography",
+    "9": "Geology",
+    "10": "History",
+    "11": "Materials science",
+    "12": "Mathematics",
+    "13": "Medicine",
+    "14": "Philosophy",
+    "15": "Physics",
+    "16": "Political science",
+    "17": "Psychology",
+    "18": "Sociology"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Art": 0,
+    "Biology": 1,
+    "Business": 2,
+    "Chemistry": 3,
+    "Computer science": 4,
+    "Economics": 5,
+    "Engineering": 6,
+    "Environmental science": 7,
+    "Geography": 8,
+    "Geology": 9,
+    "History": 10,
+    "Materials science": 11,
+    "Mathematics": 12,
+    "Medicine": 13,
+    "Philosophy": 14,
+    "Physics": 15,
+    "Political science": 16,
+    "Psychology": 17,
+    "Sociology": 18
+  },
+  "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": "single_label_classification",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57e8fe5fa7ecf696f166d24140cae759a8fd6512d6e187ee2a2fa26ddd86969
+size 439755836

runs/Nov15_16-00-20_28f611a14971/events.out.tfevents.1763222436.28f611a14971.1704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde07b39df12b6d35a67236640bc169f4db2f1008e2a10ae0215e1ad035c8524
+size 7487

runs/Nov15_16-15-25_28f611a14971/events.out.tfevents.1763223326.28f611a14971.1704.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7776776d31e205d1da076e02ab3526ab8af8807efdc5fe03f54eed3a46cc35d9
+size 11805

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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 sha256:8e5ff2c3b36264a240744cc543c33b39885931f3788862d4de04671bcb71d9f8
+size 5841