End of training

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: mit
+base_model: castorini/afriberta_large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+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 [castorini/afriberta_large](https://huggingface.co/castorini/afriberta_large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1577
+- Accuracy: 0.9647
+- F1: 0.9648
+
+## 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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 213  | 0.2605          | 0.9387   | 0.9385 |
+| No log        | 2.0   | 426  | 0.1656          | 0.9646   | 0.9645 |
+| 0.4036        | 3.0   | 639  | 0.1491          | 0.9646   | 0.9644 |
+| 0.4036        | 4.0   | 852  | 0.1510          | 0.9693   | 0.9691 |
+| 0.0483        | 5.0   | 1065 | 0.1407          | 0.9693   | 0.9691 |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "castorini/afriberta_large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "business",
+    "1": "entertainment",
+    "2": "health",
+    "3": "politics",
+    "4": "religion",
+    "5": "sports",
+    "6": "technology"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "business": 0,
+    "entertainment": 1,
+    "health": 2,
+    "politics": 3,
+    "religion": 4,
+    "sports": 5,
+    "technology": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_length": 512,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 10,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 70006
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2faeaf844f83b235d96a3d08e0f377ff98544f21140db0d561e86047612acb
+size 502565684

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6419b3044bff45e94e0553cbb81425fd06046e9294b33555e23fdc69377dba6f
+size 1554839

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 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70005": {
+      "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbf23fea3e1246781cef73613fd604f79156a59faab2fa30e19377389f6b5ac
+size 5304