End of training

README.md

@@ -1,10 +1,10 @@
 ---
 license: apache-2.0
-base_model: HooshvareLab/roberta-fa-zwnj-base
+base_model: makhataei/qa-persian-roberta-fa-zwnj-base
 tags:
 - generated_from_trainer
 datasets:
-- pquad
+- parsinlu_reading_comprehension
 model-index:
 - name: qa-persian-roberta-fa-zwnj-base
   results: []
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qa-persian-roberta-fa-zwnj-base
 
-This model is a fine-tuned version of [HooshvareLab/roberta-fa-zwnj-base](https://huggingface.co/HooshvareLab/roberta-fa-zwnj-base) on the pquad dataset.
+This model is a fine-tuned version of [makhataei/qa-persian-roberta-fa-zwnj-base](https://huggingface.co/makhataei/qa-persian-roberta-fa-zwnj-base) on the parsinlu_reading_comprehension dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2626
+- Loss: 3.4236
 
 ## Model description
 
@@ -37,23 +37,32 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 18
-- eval_batch_size: 18
+- train_batch_size: 14
+- eval_batch_size: 14
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2999        | 1.0   | 3556 | 1.2626          |
+| 2.6831        | 1.0   | 44   | 2.5986          |
+| 2.0606        | 2.0   | 88   | 2.6520          |
+| 1.6621        | 3.0   | 132  | 2.7014          |
+| 1.3046        | 4.0   | 176  | 2.8586          |
+| 1.0776        | 5.0   | 220  | 3.0320          |
+| 0.8849        | 6.0   | 264  | 3.1554          |
+| 0.7257        | 7.0   | 308  | 3.2424          |
+| 0.6213        | 8.0   | 352  | 3.3210          |
+| 0.5633        | 9.0   | 396  | 3.3986          |
+| 0.52          | 10.0  | 440  | 3.4236          |
 
 
 ### 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/roberta-fa-zwnj-base",
+  "_name_or_path": "makhataei/qa-persian-roberta-fa-zwnj-base",
   "architectures": [
     "RobertaForQuestionAnswering"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cbf6d4c45366e6e77c83fbbefef7b5c3ffdaad5697f2a6d72ef062e14b5a729
+oid sha256:4ed20757d2e2f046672834193fafb61347ba9629488ae86b5bdbbb06c659d6e3
 size 470860152

runs/Feb20_16-47-33_Software-AI/events.out.tfevents.1708435054.Software-AI.303590.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c16ac4630d0e350c5a6801a7c5884dfc170721768e6f4eeb072f7a7e637ffb
+size 9052

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "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,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "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

@@ -96,10 +96,14 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "stride": 256,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
+  "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 sha256:979e4820604ba1cb0e47fe5b4b472f7416568afce1f05f45723e295dd2029865
-size 4600
+oid sha256:6f7f3f9959d1c075a7b2bd9a704a3797764deedd9c5d9224e369c85f910165ae
+size 4219