Fine-tuned BART model for League of Legends biographies classification

README.md

@@ -0,0 +1,71 @@
+---
+license: mit
+base_model: facebook/bart-large-mnli
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: short-stories-lol-fine-tuned
+  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. -->
+
+# short-stories-lol-fine-tuned
+
+This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.7862
+- F1: 0.1353
+
+## 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: 3
+- eval_batch_size: 3
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 12
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 1.0   | 44   | 1.7573          | 0.0698 |
+| No log        | 2.0   | 88   | 1.7508          | 0.0569 |
+| No log        | 3.0   | 132  | 1.8932          | 0.0569 |
+| No log        | 4.0   | 176  | 1.9888          | 0.1432 |
+| No log        | 5.0   | 220  | 2.4816          | 0.0702 |
+| No log        | 6.0   | 264  | 2.8377          | 0.0859 |
+| No log        | 7.0   | 308  | 3.3364          | 0.1256 |
+| No log        | 8.0   | 352  | 3.2681          | 0.1017 |
+| No log        | 9.0   | 396  | 3.5178          | 0.1179 |
+| No log        | 10.0  | 440  | 3.7246          | 0.1548 |
+| No log        | 11.0  | 484  | 3.7577          | 0.1353 |
+| 0.6317        | 12.0  | 528  | 3.7862          | 0.1353 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "facebook/bart-large-mnli",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "Fighter",
+    "1": "Mage",
+    "2": "Assassin",
+    "3": "Marksman",
+    "4": "Tank",
+    "5": "Support"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Assassin": 2,
+    "Fighter": 0,
+    "Mage": 1,
+    "Marksman": 3,
+    "Support": 5,
+    "Tank": 4
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "normalize_before": false,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ff4aa62ebe328a6157dce8b6efaeadc78bb77f1e9f84ddec0c34791d7b4b84
+size 1629449264

runs/Mar24_08-50-12_0b90d47c90c2/events.out.tfevents.1711270281.0b90d47c90c2.2734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7283959a1eaa2321a0bedce7443a3bd4c82f661f844ef4f02264393bfb17aa9a
+size 7802

runs/Mar24_12-57-56_0b90d47c90c2/events.out.tfevents.1711285082.0b90d47c90c2.2734.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e3b7f0557cd31d415527dc03ac40b564dc69e06f8624fc37e6281a9341c3ad
+size 9676

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c04ca4347af570009835aeffc3ddf1d226ddf4dafeb49ef77db9640e41e0d9
+size 4920