End of training

README.md

@@ -0,0 +1,72 @@
+---
+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: 1.2011
+- Accuracy: 0.8212
+- Precision Micro: 0.8212
+- Precision Macro: 0.8176
+- Recall Micro: 0.8212
+- Recall Macro: 0.8198
+- F1 Micro: 0.8212
+- F1 Macro: 0.8178
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------------:|:---------------:|:------------:|:------------:|:--------:|:--------:|
+| 0.5662        | 1.0   | 3807  | 0.5312          | 0.8141   | 0.8141          | 0.8121          | 0.8141       | 0.8063       | 0.8141   | 0.8087   |
+| 0.4099        | 2.0   | 7614  | 0.5368          | 0.8182   | 0.8182          | 0.8118          | 0.8182       | 0.8177       | 0.8182   | 0.8141   |
+| 0.2703        | 3.0   | 11421 | 0.6214          | 0.8173   | 0.8173          | 0.8112          | 0.8173       | 0.8176       | 0.8173   | 0.8125   |
+| 0.1604        | 4.0   | 15228 | 0.8681          | 0.8259   | 0.8259          | 0.8265          | 0.8259       | 0.8219       | 0.8259   | 0.8230   |
+| 0.1161        | 5.0   | 19035 | 1.0616          | 0.8229   | 0.8229          | 0.8207          | 0.8229       | 0.8214       | 0.8229   | 0.8205   |
+| 0.0864        | 6.0   | 22842 | 1.2011          | 0.8212   | 0.8212          | 0.8176          | 0.8212       | 0.8198       | 0.8212   | 0.8178   |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,51 @@
+{
+  "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": "Agronomical Sciences",
+    "1": "Applied Social Sciences",
+    "2": "Biological Sciences",
+    "3": "Engineering",
+    "4": "Health Sciences",
+    "5": "Humanities",
+    "6": "Linguistics, Literature and Arts",
+    "7": "Physical Sciences and Mathematics"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Agronomical Sciences": 0,
+    "Applied Social Sciences": 1,
+    "Biological Sciences": 2,
+    "Engineering": 3,
+    "Health Sciences": 4,
+    "Humanities": 5,
+    "Linguistics, Literature and Arts": 6,
+    "Physical Sciences and Mathematics": 7
+  },
+  "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 sha256:97700a17cd25c7d29c1ca28c08670ebfc59d3454c3431d16489323766270afb7
+size 439722000

runs/Nov19_09-30-24_ee977aca4547/events.out.tfevents.1763544640.ee977aca4547.876.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb64d0929b13278aa5963e3d1013295bede81aca377d8045f6c76cb7a4269a4
+size 19512

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:c39437186a1ac9e649384fcbff65ebf8f4ac6d77bdd096b68b3955a4fb25cc68
+size 5841