Zlovoblachko/roberta-base-binary-ged

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: roberta-base_binary
+  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-base_binary
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1729
+- Precision: 0.8178
+- Recall: 0.6136
+- F1: 0.7012
+- F0.5: 0.7668
+- Macro Precision: 0.8824
+- Macro Recall: 0.7971
+- Macro F1: 0.8323
+- Macro F0.5: 0.8602
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.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: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | F0.5   | Macro Precision | Macro Recall | Macro F1 | Macro F0.5 |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:------:|:---------------:|:------------:|:--------:|:----------:|
+| 0.1963        | 1.0    | 1926 | 0.1702          | 0.8148    | 0.6179 | 0.7028 | 0.7660 | 0.8814          | 0.7991       | 0.8333   | 0.8601     |
+| 0.1621        | 1.9992 | 3850 | 0.1698          | 0.8027    | 0.6472 | 0.7166 | 0.7659 | 0.8772          | 0.8124       | 0.8405   | 0.8613     |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "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:bfd804acac23fb1fd70af6c73ea64ff1d34128c05f934f99edf9ef1f3df0d22d
+size 496250232

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>"
+}

test_results.json

@@ -0,0 +1,15 @@
+{
+  "eval_loss": 0.1729455292224884,
+  "eval_precision": 0.8178217821782178,
+  "eval_recall": 0.6136416399684265,
+  "eval_f1": 0.7011698543650688,
+  "eval_f0.5": 0.7667939241328893,
+  "eval_macro_precision": 0.8824056575716628,
+  "eval_macro_recall": 0.7971105450356671,
+  "eval_macro_f1": 0.832330838039707,
+  "eval_macro_f0.5": 0.8601580350033708,
+  "eval_runtime": 55.7132,
+  "eval_samples_per_second": 138.226,
+  "eval_steps_per_second": 8.651,
+  "epoch": 1.9992209815632305
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "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 sha256:7c5e97b4b8cb1fee58d94ebebfe18d75d7b2839f8564f7aed314fc5fa2450569
+size 5368