End of training

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: HooshvareLab/roberta-fa-zwnj-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+model-index:
+- name: roberta-fa-zwnj-base_v1
+  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. -->
+
+# roberta-fa-zwnj-base_v1
+
+This model is a fine-tuned version of [HooshvareLab/roberta-fa-zwnj-base](https://huggingface.co/HooshvareLab/roberta-fa-zwnj-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3797
+- Accuracy: 0.6288
+- F1: 0.6282
+- Precision: 0.6299
+
+## 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: 1e-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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|
+| No log        | 1.0   | 221  | 1.1404          | 0.5176   | 0.4956 | 0.5475    |
+| No log        | 2.0   | 442  | 0.9659          | 0.6163   | 0.6136 | 0.6169    |
+| 1.0628        | 3.0   | 663  | 0.9516          | 0.6436   | 0.6405 | 0.6456    |
+| 1.0628        | 4.0   | 884  | 0.9857          | 0.6470   | 0.6462 | 0.6530    |
+| 0.6388        | 5.0   | 1105 | 1.0326          | 0.6481   | 0.6483 | 0.6490    |
+| 0.6388        | 6.0   | 1326 | 1.1403          | 0.6652   | 0.6647 | 0.6664    |
+| 0.3767        | 7.0   | 1547 | 1.2419          | 0.6356   | 0.6362 | 0.6383    |
+| 0.3767        | 8.0   | 1768 | 1.3099          | 0.6402   | 0.6394 | 0.6398    |
+| 0.3767        | 9.0   | 1989 | 1.3632          | 0.6300   | 0.6298 | 0.6297    |
+| 0.2179        | 10.0  | 2210 | 1.3797          | 0.6288   | 0.6282 | 0.6299    |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "HooshvareLab/roberta-fa-zwnj-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "b2c",
+    "1": "adsl/sales",
+    "2": "b2b/res",
+    "3": "b2b/ent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "adsl/sales": 1,
+    "b2b/ent": 3,
+    "b2b/res": 2,
+    "b2c": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 42000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27be9b1566cbdcc379e559b775f529d1507c2abe1cb48054386d04d2c23728b
+size 473228896

runs/Mar12_09-09-47_8619f9c8195e/events.out.tfevents.1710234588.8619f9c8195e.93.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34064e92cc83b7108f98c1586e51e31304ef09982fb619cf3b3d32dfbf108e6d
+size 4847

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,105 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<nl>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<hs>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657caf198d15c4bec4eca9d0b47e7873454513cb4263f0a227faa3398c61f012
+size 4920