End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: xlnet/xlnet-large-cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: xlnet-large-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-large-cased-airlines-news-multi-label
+
+This model is a fine-tuned version of [xlnet/xlnet-large-cased](https://huggingface.co/xlnet/xlnet-large-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2329
+- F1: 0.9001
+- Roc Auc: 0.6501
+- Hamming: 0.9145
+
+## 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: 9e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 150
+- num_epochs: 12
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Hamming |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:-------:|
+| No log        | 1.0   | 128  | 0.2866          | 0.8594 | 0.5     | 0.9041  |
+| No log        | 2.0   | 256  | 0.2520          | 0.8955 | 0.5943  | 0.9130  |
+| No log        | 3.0   | 384  | 0.2431          | 0.8984 | 0.6493  | 0.9130  |
+| 0.3656        | 4.0   | 512  | 0.2384          | 0.8984 | 0.6622  | 0.9115  |
+| 0.3656        | 5.0   | 640  | 0.2329          | 0.9001 | 0.6501  | 0.9145  |
+| 0.3656        | 6.0   | 768  | 0.2353          | 0.9000 | 0.6699  | 0.9130  |
+| 0.3656        | 7.0   | 896  | 0.2336          | 0.8959 | 0.6735  | 0.9071  |
+| 0.2788        | 8.0   | 1024 | 0.2318          | 0.8957 | 0.6606  | 0.9086  |
+| 0.2788        | 9.0   | 1152 | 0.2327          | 0.8961 | 0.6606  | 0.9086  |
+| 0.2788        | 10.0  | 1280 | 0.2317          | 0.8975 | 0.6545  | 0.9100  |
+| 0.2788        | 11.0  | 1408 | 0.2311          | 0.8975 | 0.6545  | 0.9100  |
+| 0.2659        | 12.0  | 1536 | 0.2309          | 0.8982 | 0.6554  | 0.9115  |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "xlnet/xlnet-large-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 4096,
+  "d_model": 1024,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "id2label": {
+    "0": "capacity expansion",
+    "1": "legal action",
+    "2": "market expansion",
+    "3": "merger & acquisition and finance investments",
+    "4": "outsourcing and alliance",
+    "5": "product introductions and improvements"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "capacity expansion": 0,
+    "legal action": 1,
+    "market expansion": 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": 16,
+  "n_layer": 24,
+  "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": "4.41.1",
+  "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:f16c02b230ef89ec57445eee888180254f4a30e9001bb4a5413eb27613f75bf3
+size 1446131536

runs/Jun05_05-10-33_45fd6a92050d/events.out.tfevents.1717564240.45fd6a92050d.1467.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606f2413160d8b841f6ab6e00fb65e73fffd75a1d0208a2489be309cbaa0af04
+size 10103

runs/Jun05_05-51-49_45fd6a92050d/events.out.tfevents.1717566713.45fd6a92050d.1467.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d2593ce157c4530b52f66cdbde10c30e88ab97c5b8568606a92ea548a0b978
+size 11714

runs/Jun05_05-51-49_45fd6a92050d/events.out.tfevents.1717569953.45fd6a92050d.1467.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95bd01ae78a045366e0b33cf687203db1c45571716f50a47dc35a4147d3b46b
+size 1345

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 sha256:2e2e5e558611e25959bbc543615146d0303cc136334852ab4bd097db5491433a
+size 5176