ops_subcate

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: ops_subcate
+  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. -->
+
+# ops_subcate
+
+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: 0.1325
+- Accuracy: 0.7228
+- F1: 0.7556
+- Precision: 0.7866
+- Recall: 0.7270
+
+## 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: 5e-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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 49   | 0.6030          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 98   | 0.3307          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 3.0   | 147  | 0.3022          | 0.0      | 0.0    | 0.0       | 0.0    |
+| No log        | 4.0   | 196  | 0.2354          | 0.3121   | 0.4343 | 0.7171    | 0.3114 |
+| No log        | 5.0   | 245  | 0.1831          | 0.5306   | 0.6169 | 0.7313    | 0.5335 |
+| No log        | 6.0   | 294  | 0.1580          | 0.6355   | 0.6895 | 0.7504    | 0.6377 |
+| No log        | 7.0   | 343  | 0.1408          | 0.6779   | 0.7257 | 0.7702    | 0.6861 |
+| No log        | 8.0   | 392  | 0.1325          | 0.7228   | 0.7556 | 0.7866    | 0.7270 |
+
+
+### 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 +1,60 @@
+{
+  "_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": "Invoice Posting",
+    "1": "PO Processing Only",
+    "2": "New - Item / Service",
+    "3": "Delivery Documents",
+    "4": "Warehouse-to-Site Transfer",
+    "5": "Canvassing + PO Processing",
+    "6": "Site-to-Warehouse Transfer",
+    "7": "New vendor accreditation",
+    "8": "Delivery Dates",
+    "9": "Asset reservation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Asset reservation": 9,
+    "Canvassing + PO Processing": 5,
+    "Delivery Dates": 8,
+    "Delivery Documents": 3,
+    "Invoice Posting": 0,
+    "New - Item / Service": 2,
+    "New vendor accreditation": 7,
+    "PO Processing Only": 1,
+    "Site-to-Warehouse Transfer": 6,
+    "Warehouse-to-Site Transfer": 4
+  },
+  "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:dc7d27e8d6283f1d9f33396b4b4a29522ae82f30172446951fa1abd5fdedab42
+size 567623168

runs/Jul30_07-01-47_06a218ada6c5/events.out.tfevents.1722322915.06a218ada6c5.1464.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d6c6e0ae3e8f330770f851554e47e7c374b1058c38901ef0b3f74ff43520d6
+size 9816

runs/Jul30_07-01-47_06a218ada6c5/events.out.tfevents.1722323357.06a218ada6c5.1464.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1525b0fcaec39cd6e5fb70db78126fe2252ff3b5b84d3c914c3ffa12cecf32
+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 sha256:896f9174ac52523b621e6c5da94f0b93c1f4e2f3c1b72d4dbbd63e25a6f9ce35
+size 5112