End of training

README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+base_model: microsoft/deberta-base-mnli
+tags:
+- generated_from_trainer
+model-index:
+- name: deberta_base_all
+  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. -->
+
+# deberta_base_all
+
+This model is a fine-tuned version of [microsoft/deberta-base-mnli](https://huggingface.co/microsoft/deberta-base-mnli) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4071
+
+## 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: 8
+- eval_batch_size: 8
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.5695        | 1.0   | 1949  | 0.4123          |
+| 0.1587        | 2.0   | 3898  | 0.3700          |
+| 0.0671        | 3.0   | 5847  | 0.3963          |
+| 0.1556        | 4.0   | 7796  | 0.3373          |
+| 0.103         | 5.0   | 9745  | 0.3485          |
+| 0.1483        | 6.0   | 11694 | 0.4014          |
+| 0.166         | 7.0   | 13643 | 0.3890          |
+| 0.0515        | 8.0   | 15592 | 0.3875          |
+| 0.0664        | 9.0   | 17541 | 0.4162          |
+| 0.0321        | 10.0  | 19490 | 0.4071          |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "microsoft/deberta-base-mnli",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Cold outreach/promotional emails",
+    "1": "Value Proposition Emails",
+    "2": "Prospecting emails",
+    "3": "Introduction emails",
+    "4": "Appointment request emails",
+    "5": "Appointment Reminder Emails",
+    "6": "Follow up emails",
+    "7": "Thank you emails",
+    "8": "Upselling, cross-selling, and abandoned cart emails",
+    "9": "Quotation Emails",
+    "10": "Sales Order Emails",
+    "11": "Order Confirmation Emails",
+    "12": "Purchase Order Emails",
+    "13": "Invoice Email",
+    "14": "Discount  Emails",
+    "15": "Renewal Reminder Emails",
+    "16": "Feedback/Survey Emails",
+    "17": "Event Invitation Emails",
+    "18": "Contract/Agreement Emails",
+    "19": "Customer Testimonial Request Emails",
+    "20": "Product Recall or Issue Notification Emails",
+    "21": "Competitor Comparison Emails",
+    "22": "Warranty Information Emails",
+    "23": "Case Study/Success Story Emails",
+    "24": "Onboarding Emails",
+    "25": "Inquiry Emails",
+    "26": "Request for Quotation",
+    "27": "Support request emails",
+    "28": "Order Placement Emails",
+    "29": "Order modification emails.",
+    "30": "Order cancellation emails.",
+    "31": "Exchange/Return request emails.",
+    "32": "Refund request",
+    "33": "Appointment scheduling",
+    "34": "Appointment postpone",
+    "35": "Referral emails",
+    "36": "Product upgrade emails",
+    "37": "Warranty claim emails",
+    "38": "Service renewal emails",
+    "39": "Complaint or Issue Reporting Emails",
+    "40": "Feedback Emails",
+    "41": "Request for Meeting or Demo",
+    "42": "Negotiation Emails",
+    "43": "Customer Success or Testimonial Emails"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "CONTRADICTION": 0,
+    "ENTAILMENT": 2,
+    "NEUTRAL": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1719987662.152610336ae8.4301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3230d635ee23ef49d120d4bc027b5fca61d7e3abee6990333fe632bc44e4f07
+size 422185

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e7c74c8d3d0a0ed8f784a548d6286b7ca5fa080d2130b70db2bc02a514f71c
+size 556928768

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "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]",
+  "errors": "replace",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "gpt2"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988c9deb7057f81981e060ebb413ce70804a9724d2ebbcbe7dd66e9bc9d8c14f
+size 5176