ts_tg

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: ts_tg
+  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. -->
+
+# ts_tg
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0516
+- Accuracy: 0.8517
+- F1: 0.8759
+- Precision: 0.8996
+- Recall: 0.8533
+
+## 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: 64
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 202  | 0.1370          | 0.5242   | 0.6378 | 0.8129    | 0.5248 |
+| No log        | 2.0   | 404  | 0.0857          | 0.6877   | 0.7700 | 0.8749    | 0.6875 |
+| 0.1567        | 3.0   | 606  | 0.0667          | 0.7810   | 0.8331 | 0.8929    | 0.7809 |
+| 0.1567        | 4.0   | 808  | 0.0593          | 0.8145   | 0.8525 | 0.8947    | 0.8142 |
+| 0.0566        | 5.0   | 1010 | 0.0554          | 0.8406   | 0.8668 | 0.8926    | 0.8425 |
+| 0.0566        | 6.0   | 1212 | 0.0529          | 0.8437   | 0.8718 | 0.8994    | 0.8459 |
+| 0.0566        | 7.0   | 1414 | 0.0522          | 0.8474   | 0.8737 | 0.8992    | 0.8496 |
+| 0.0383        | 8.0   | 1616 | 0.0516          | 0.8517   | 0.8759 | 0.8996    | 0.8533 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Access Control and Security",
+    "1": "Asset Management",
+    "2": "CCTV Admin",
+    "3": "Common Area Team",
+    "4": "Network Design Team",
+    "5": "NOC",
+    "6": "NOC Systems",
+    "7": "On-Site Support",
+    "8": "Product Development",
+    "9": "Service Desk",
+    "10": "SOC",
+    "11": "Technical Project Management",
+    "12": "TS Managers",
+    "13": "TS Procurement",
+    "14": "Voice and Email"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Access Control and Security": 0,
+    "Asset Management": 1,
+    "CCTV Admin": 2,
+    "Common Area Team": 3,
+    "NOC": 5,
+    "NOC Systems": 6,
+    "Network Design Team": 4,
+    "On-Site Support": 7,
+    "Product Development": 8,
+    "SOC": 10,
+    "Service Desk": 9,
+    "TS Managers": 12,
+    "TS Procurement": 13,
+    "Technical Project Management": 11,
+    "Voice and Email": 14
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f865c05647511d433b90d7db51bf625617f02bb75693a629617c99d424403ab5
+size 567638548

runs/Aug05_10-39-53_b17c6402ee66/events.out.tfevents.1722854402.b17c6402ee66.2440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc2664dca1df716eb76e673ea2803baeb6dcd935884162505cdc83a8c6f73f2
+size 10607

runs/Aug05_10-39-53_b17c6402ee66/events.out.tfevents.1722856213.b17c6402ee66.2440.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655f837d6b3c1f40594c88e711f77e9c078f64fa5e58128180004f2b925c413b
+size 560

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3598928be43f721f4edf44017dbb07962ab20f4acd76dcc85be2d6bbc0c17bff
+size 5112