End of training

README.md

@@ -1,10 +1,10 @@
 ---
 license: apache-2.0
-base_model: HooshvareLab/distilbert-fa-zwnj-base
+base_model: makhataei/qa-persian-distilbert-fa-zwnj-base
 tags:
 - generated_from_trainer
 datasets:
-- pquad
+- parsinlu_reading_comprehension
 model-index:
 - name: qa-persian-distilbert-fa-zwnj-base
   results: []
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qa-persian-distilbert-fa-zwnj-base
 
-This model is a fine-tuned version of [HooshvareLab/distilbert-fa-zwnj-base](https://huggingface.co/HooshvareLab/distilbert-fa-zwnj-base) on the pquad dataset.
+This model is a fine-tuned version of [makhataei/qa-persian-distilbert-fa-zwnj-base](https://huggingface.co/makhataei/qa-persian-distilbert-fa-zwnj-base) on the parsinlu_reading_comprehension dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1780
+- Loss: 3.2461
 
 ## Model description
 
@@ -37,27 +37,32 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 24
-- eval_batch_size: 24
+- train_batch_size: 13
+- eval_batch_size: 13
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 1.3681        | 1.0   | 2667  | 1.3271          |
-| 1.0698        | 2.0   | 5334  | 1.1736          |
-| 0.8977        | 3.0   | 8001  | 1.1519          |
-| 0.778         | 4.0   | 10668 | 1.1591          |
-| 0.7164        | 5.0   | 13335 | 1.1780          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.665         | 1.0   | 47   | 2.5329          |
+| 1.983         | 2.0   | 94   | 2.5824          |
+| 1.6365        | 3.0   | 141  | 2.6814          |
+| 1.329         | 4.0   | 188  | 2.7567          |
+| 1.067         | 5.0   | 235  | 2.8691          |
+| 0.9063        | 6.0   | 282  | 3.0056          |
+| 0.7492        | 7.0   | 329  | 3.0976          |
+| 0.6718        | 8.0   | 376  | 3.1850          |
+| 0.5637        | 9.0   | 423  | 3.2335          |
+| 0.5525        | 10.0  | 470  | 3.2461          |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- Pytorch 2.1.0+cu118
+- Pytorch 2.0.1+cu117
 - Datasets 2.15.0
 - Tokenizers 0.15.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "HooshvareLab/distilbert-fa-zwnj-base",
+  "_name_or_path": "makhataei/qa-persian-distilbert-fa-zwnj-base",
   "activation": "gelu",
   "architectures": [
     "DistilBertForQuestionAnswering"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c1a9feb84620cfbd7e7202ee4407c858dffba5881c304d09f8c974e483cd2c
+oid sha256:e436193be3b34fff225749ef196b2e9ca4d95827cf62fa8688f7afec9fd9b33b
 size 300730456

runs/Feb20_11-56-51_Software-AI/events.out.tfevents.1708417612.Software-AI.146186.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4389ef7f2ece7bde1417c3d6d67e630a4fe35639262991d60cd3ab172f89b498
+size 8921

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "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

@@ -885,11 +885,15 @@
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 256,
   "strip_accents": false,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f474506421abbab84dd9bfba1010726ffeefb25eeefdbf7cfcf781a0f4c2bf
-size 4600
+oid sha256:5bbd443e7b7609c7811a393247520a00e5b7cfa82473ce9ae3a563699ca7e4c3
+size 4219