SIRIS-Lab/acty2de-roberta_lvl1_ctx

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta_lvl2_ctx
+  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. -->
+
+# roberta_lvl2_ctx
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8983
+- Accuracy: 0.7565
+- F1 Macro: 0.5022
+
+## 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: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| No log        | 1.0   | 388  | 1.1432          | 0.6551   | 0.3238   |
+| 1.506         | 2.0   | 776  | 0.8958          | 0.7435   | 0.4554   |
+| 0.783         | 3.0   | 1164 | 0.8896          | 0.7522   | 0.4774   |
+| 0.5372        | 4.0   | 1552 | 0.8983          | 0.7565   | 0.5022   |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,83 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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": {
+    "0": "EDU.primary",
+    "1": "EDU.secondary",
+    "2": "EDU.vocational",
+    "3": "HEA.hospital",
+    "4": "HEA.network",
+    "5": "HEA.non_hospital_care",
+    "6": "HEA.other",
+    "7": "HEI.institution",
+    "8": "HEI.other",
+    "9": "Individual",
+    "10": "OTH.general",
+    "11": "OTH.learned_society",
+    "12": "OTH.museum",
+    "13": "OTH.network",
+    "14": "OTH.oth",
+    "15": "PRC.large",
+    "16": "PRC.sme",
+    "17": "PUB.intl",
+    "18": "PUB.local",
+    "19": "PUB.national",
+    "20": "PUB.regional",
+    "21": "REC.facility",
+    "22": "REC.institute",
+    "23": "REC.lab",
+    "24": "REC.other",
+    "25": "Unknown"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "EDU.primary": 0,
+    "EDU.secondary": 1,
+    "EDU.vocational": 2,
+    "HEA.hospital": 3,
+    "HEA.network": 4,
+    "HEA.non_hospital_care": 5,
+    "HEA.other": 6,
+    "HEI.institution": 7,
+    "HEI.other": 8,
+    "Individual": 9,
+    "OTH.general": 10,
+    "OTH.learned_society": 11,
+    "OTH.museum": 12,
+    "OTH.network": 13,
+    "OTH.oth": 14,
+    "PRC.large": 15,
+    "PRC.sme": 16,
+    "PUB.intl": 17,
+    "PUB.local": 18,
+    "PUB.national": 19,
+    "PUB.regional": 20,
+    "REC.facility": 21,
+    "REC.institute": 22,
+    "REC.lab": 23,
+    "REC.other": 24,
+    "Unknown": 25
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88fb73760f5e0ea192b1d3108c234fce9fea98a672fb8aac1a19817a271f5e6
+size 498686648

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "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:f4a5975ca660c22426f0679946e19096fb5d17fce2ed99944acd1b5472a88812
+size 5777