End of training

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: HooshvareLab/roberta-fa-zwnj-base
+tags:
+- generated_from_trainer
+model-index:
+- name: test-trainer
+  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. -->
+
+# test-trainer
+
+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: 0.1195
+
+## 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
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.561         | 1.0   | 4473  | 0.3579          |
+| 0.3881        | 2.0   | 8946  | 0.2016          |
+| 0.1966        | 3.0   | 13419 | 0.1195          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,55 @@
+{
+  "_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": "\u0627\u062f\u0628\u06cc\u0627\u062a",
+    "1": "\u062f\u06cc\u0646",
+    "2": "\u06af\u0641\u062a\u06af\u0648",
+    "3": "\u0639\u0644\u0645",
+    "4": "\u0641\u0631\u0647\u0646\u06af",
+    "5": "\u0642\u0627\u0646\u0648\u0646",
+    "6": "\u0647\u0646\u0631",
+    "7": "\u0633\u06cc\u0627\u0633\u06cc",
+    "8": "\u062f\u0627\u0631\u0648",
+    "9": "\u0627\u0642\u062a\u0635\u0627\u062f",
+    "10": "\u0641\u0631\u0647\u0646\u06af\u06cc"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u0627\u062f\u0628\u06cc\u0627\u062a": 0,
+    "\u0627\u0642\u062a\u0635\u0627\u062f": 9,
+    "\u062f\u0627\u0631\u0648": 8,
+    "\u062f\u06cc\u0646": 1,
+    "\u0633\u06cc\u0627\u0633\u06cc": 7,
+    "\u0639\u0644\u0645": 3,
+    "\u0641\u0631\u0647\u0646\u06af": 4,
+    "\u0641\u0631\u0647\u0646\u06af\u06cc": 10,
+    "\u0642\u0627\u0646\u0648\u0646": 5,
+    "\u0647\u0646\u0631": 6,
+    "\u06af\u0641\u062a\u06af\u0648": 2
+  },
+  "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": "4.34.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 42000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81fa5e96a3b79e806da81e6d08fece86a1d7479839c938581dfe38f7af0231c
+size 473295662

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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": false,
+      "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 sha256:9f9af448e481c60b8267d5fb6f94fbf71561e7ddc4cf490becba32c6daa8aef9
+size 4536