End of training

README.md

@@ -0,0 +1,77 @@
+---
+license: mit
+base_model: xlnet/xlnet-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: xlnet-base-cased-airlines-news-multi-label
+  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. -->
+
+# xlnet-base-cased-airlines-news-multi-label
+
+This model is a fine-tuned version of [xlnet/xlnet-base-cased](https://huggingface.co/xlnet/xlnet-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2822
+- F1: 0.6647
+- Roc Auc: 0.8080
+- Accuracy: 0.6116
+
+## 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: 12
+- eval_batch_size: 12
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| No log        | 1.0   | 150  | 0.2088          | 0.5979 | 0.7399  | 0.6027   |
+| No log        | 2.0   | 300  | 0.1928          | 0.6596 | 0.7725  | 0.6562   |
+| No log        | 3.0   | 450  | 0.2049          | 0.6327 | 0.7653  | 0.5982   |
+| 0.2167        | 4.0   | 600  | 0.2226          | 0.6506 | 0.8007  | 0.6027   |
+| 0.2167        | 5.0   | 750  | 0.2280          | 0.6288 | 0.7666  | 0.5893   |
+| 0.2167        | 6.0   | 900  | 0.2418          | 0.6295 | 0.7709  | 0.5938   |
+| 0.0812        | 7.0   | 1050 | 0.2610          | 0.6258 | 0.7722  | 0.5982   |
+| 0.0812        | 8.0   | 1200 | 0.2756          | 0.6098 | 0.7606  | 0.5804   |
+| 0.0812        | 9.0   | 1350 | 0.2822          | 0.6647 | 0.8080  | 0.6116   |
+| 0.0325        | 10.0  | 1500 | 0.2908          | 0.6378 | 0.7873  | 0.5938   |
+| 0.0325        | 11.0  | 1650 | 0.3050          | 0.6319 | 0.7860  | 0.5938   |
+| 0.0325        | 12.0  | 1800 | 0.3044          | 0.6277 | 0.7830  | 0.5804   |
+| 0.0325        | 13.0  | 1950 | 0.3030          | 0.6254 | 0.7804  | 0.5804   |
+| 0.015         | 14.0  | 2100 | 0.3057          | 0.6319 | 0.7860  | 0.5848   |
+| 0.015         | 15.0  | 2250 | 0.3013          | 0.6168 | 0.7744  | 0.5670   |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "xlnet/xlnet-base-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "id2label": {
+    "0": "capacity expansion",
+    "1": "market expansion",
+    "2": "marketing",
+    "3": "merger & acquisition and finance investments",
+    "4": "outsourcing and alliance",
+    "5": "product introductions and improvements"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "capacity expansion": 0,
+    "market expansion": 1,
+    "marketing": 2,
+    "merger & acquisition and finance investments": 3,
+    "outsourcing and alliance": 4,
+    "product introductions and improvements": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "problem_type": "multi_label_classification",
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c3e83a8939069735380c5bb3cf438be2650f510119289a418fcf972f8969ae
+size 469276904

runs/May25_02-53-35_4143bc31bc8d/events.out.tfevents.1716605626.4143bc31bc8d.1728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc64de47f0a982fdd083e72eb016646df0558c06ff4412919c9bfc89dca840a6
+size 13184

runs/May25_02-53-35_4143bc31bc8d/events.out.tfevents.1716612635.4143bc31bc8d.1728.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a75ec9f8e06ebb3bb729f2f7abd0ba4a2f948b88ee9e55460a1e14a624f5e9
+size 508

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tokenizer_config.json

@@ -0,0 +1,93 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "keep_accents": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c56e9a4108b26fcbbd6f2f21dda216d61cb5818760fd016bc2ff52ed66660b2
+size 5176