End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: HooshvareLab/bert-fa-base-uncased
+base_model: SajjadAyoubi/xlm-roberta-large-fa-qa
 tags:
 - generated_from_trainer
 datasets:
@@ -15,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qa-persian
 
-This model is a fine-tuned version of [HooshvareLab/bert-fa-base-uncased](https://huggingface.co/HooshvareLab/bert-fa-base-uncased) on the persian_qa dataset.
+This model is a fine-tuned version of [SajjadAyoubi/xlm-roberta-large-fa-qa](https://huggingface.co/SajjadAyoubi/xlm-roberta-large-fa-qa) on the persian_qa dataset.
 
 ## Model description
 
@@ -42,13 +41,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 1
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 23   | 4.2373          |
-
-
 ### Framework versions
 
 - Transformers 4.33.2

config.json

@@ -1,25 +1,31 @@
 {
-  "_name_or_path": "HooshvareLab/bert-fa-base-uncased",
+  "_name_or_path": "SajjadAyoubi/xlm-roberta-large-fa-qa",
   "architectures": [
-    "BertForQuestionAnswering"
+    "XLMRobertaForQuestionAnswering"
   ],
   "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,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "intermediate_size": 4096,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "name": "XLMRoberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.33.2",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 100000
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce70f52a1a6ad9b0f7a04594e1b43853d560596d4f68205f977fd9101c9390e
-size 649074089
+oid sha256:04ec0b9f0507f421e44e6a1ddf3eeb05026f19ffccb868c9457b25b90a03b613
+size 2235501033

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48096ce61002631def21f37d7ef65e21c1e868c00120c2f12f69a7b804582c44
+oid sha256:657e88082dbbe9be483a93a21f6ef5ce11e7b0fc0c8c486a8ae936f4ef4c794d
 size 4027