End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,8 +1,10 @@
 ---
-license: apache-2.0
-base_model: HooshvareLab/roberta-fa-zwnj-base
+license: mit
+base_model: xlm-roberta-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: test-trainer
   results: []
@@ -13,9 +15,10 @@ 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.
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1195
+- Loss: 0.2337
+- Accuracy: 0.9169
 
 ## Model description
 
@@ -34,21 +37,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- 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: 3.0
+- num_epochs: 3
 
 ### 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          |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3629        | 1.0   | 14391 | 0.3249          | 0.8866   |
+| 0.313         | 2.0   | 28782 | 0.2640          | 0.9067   |
+| 0.2723        | 3.0   | 43173 | 0.2337          | 0.9169   |
 
 
 ### Framework versions

config.json

@@ -1,49 +1,35 @@
 {
-  "_name_or_path": "HooshvareLab/roberta-fa-zwnj-base",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "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"
+    "0": "Informational",
+    "1": "Navigational",
+    "2": "Commercial",
+    "3": "Transactional"
   },
   "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
+    "Commercial": 2,
+    "Informational": 0,
+    "Navigational": 1,
+    "Transactional": 3
   },
-  "layer_norm_eps": 1e-12,
+  "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
@@ -51,5 +37,5 @@
   "transformers_version": "4.34.1",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 42000
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81fa5e96a3b79e806da81e6d08fece86a1d7479839c938581dfe38f7af0231c
-size 473295662
+oid sha256:8b4f373c53a41c7694f6a430177a6652ccb17a25394f2930e3b2ce7ac020a9a7
+size 1112256302

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer_config.json

@@ -1,10 +1,9 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -12,7 +11,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,7 +19,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -28,78 +27,28 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
+    "250001": {
       "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,
+  "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9af448e481c60b8267d5fb6f94fbf71561e7ddc4cf490becba32c6daa8aef9
-size 4536
+oid sha256:02193c4ffd326bad233479da4b3d24acd0c32fa98a5519f6ddcc815963520083
+size 4472