End of training

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: my_awesome_model
+  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. -->
+
+# my_awesome_model
+
+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: 0.0808
+- Accuracy: 0.8289
+- F1: 0.8595
+- Precision: 0.8864
+- Recall: 0.8342
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 47   | 0.1056          | 0.7059   | 0.7788 | 0.8684    | 0.7059 |
+| No log        | 2.0   | 94   | 0.0961          | 0.7219   | 0.7895 | 0.8710    | 0.7219 |
+| No log        | 3.0   | 141  | 0.1042          | 0.7594   | 0.8045 | 0.8554    | 0.7594 |
+| No log        | 4.0   | 188  | 0.0899          | 0.8021   | 0.8427 | 0.8876    | 0.8021 |
+| No log        | 5.0   | 235  | 0.0911          | 0.8182   | 0.8540 | 0.8807    | 0.8289 |
+| No log        | 6.0   | 282  | 0.0808          | 0.8289   | 0.8595 | 0.8864    | 0.8342 |
+| No log        | 7.0   | 329  | 0.0885          | 0.8503   | 0.8689 | 0.8883    | 0.8503 |
+| No log        | 8.0   | 376  | 0.0873          | 0.8396   | 0.8634 | 0.8827    | 0.8449 |
+| No log        | 9.0   | 423  | 0.0926          | 0.8342   | 0.8579 | 0.8771    | 0.8396 |
+| No log        | 10.0  | 470  | 0.0904          | 0.8342   | 0.8603 | 0.8820    | 0.8396 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

added_tokens.json

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

config.json

@@ -0,0 +1,62 @@
+{
+  "_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": "Technology Services",
+    "1": "Finance",
+    "2": "Projects & Design",
+    "3": "Engineering",
+    "4": "HR",
+    "5": "Customer Success",
+    "6": "Document Controller",
+    "7": "Legal & Compliance",
+    "8": "Marketing",
+    "9": "Service Delivery External",
+    "10": "Operations Team"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Customer Success": 5,
+    "Document Controller": 6,
+    "Engineering": 3,
+    "Finance": 1,
+    "HR": 4,
+    "Legal & Compliance": 7,
+    "Marketing": 8,
+    "Operations Team": 10,
+    "Projects & Design": 2,
+    "Service Delivery External": 9,
+    "Technology Services": 0
+  },
+  "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": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2fbd0f0b3cc22a013361a2b3758d1e2795ea01c19feb3c63a441cf48d0bd37
+size 567626244

runs/Jun11_06-39-18_61fd5dd2b663/events.out.tfevents.1718087964.61fd5dd2b663.3156.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9296ba8ba92b7447ca5e4e72755ae790469334fb5c46a6c2a1e0a524ad83248
+size 8326

runs/Jun11_06-39-18_61fd5dd2b663/events.out.tfevents.1718088425.61fd5dd2b663.3156.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fcaff1857d0553b7e3e45993f9695f778bd015b7cc8a7c1feb30f72dad1c47
+size 560

runs/Jun11_06-48-16_61fd5dd2b663/events.out.tfevents.1718088502.61fd5dd2b663.3156.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c0bf90212ca82b76dd310afb8b060dac35efccf04c601ff01971993fdf8831
+size 8414

runs/Jun11_06-48-16_61fd5dd2b663/events.out.tfevents.1718089107.61fd5dd2b663.3156.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86408d04f1b1d0fe76ff35b74ef50d9aa094cdcbd55393c650fc5bc80777826e
+size 560

runs/Jun11_06-59-01_61fd5dd2b663/events.out.tfevents.1718089151.61fd5dd2b663.3156.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4446ebafdce7ba861b2d16a6378da9498b33af0e8219283c42f2bcae400ac0e1
+size 10775

runs/Jun11_06-59-01_61fd5dd2b663/events.out.tfevents.1718090353.61fd5dd2b663.3156.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aff5af817e6dbb1578bd4d4ed13a1aa31c75af9ecdf2d070c81b2565e0e449d
+size 1032

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 sha256:530fbefcd404168ebd737f464ab03a7a8e2bef8d2727c859acbf5700d475fad2
+size 5112