bert-fa-QA-v1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- persian_qa
+model_index:
+- name: bert-fa-QA-v1
+  results:
+  - task:
+      name: Question Answering
+      type: question-answering
+    dataset:
+      name: persian_qa
+      type: persian_qa
+      args: persian_qa
+---
+
+<!-- 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. -->
+
+# bert-fa-QA-v1
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 4.4213
+
+## 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: 3e-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: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.237         | 1.0   | 1126 | 3.9892          |
+| 0.1135        | 2.0   | 2252 | 4.4213          |
+
+
+### Framework versions
+
+- Transformers 4.9.0
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "HooshvareLab/bert-fa-base-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d83a5a415b289e5d1698a0efe1fdc73906f1a339fb54b3350e67e945640913d
+size 649092529

runs/Jul25_11-42-32_ea93e63c112a/1627213414.518686/events.out.tfevents.1627213414.ea93e63c112a.61.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30f10b15ddf4fee923910a41a761116dfd92ec221bd4f212cc03719294f4b1a
+size 4189

runs/Jul25_11-42-32_ea93e63c112a/events.out.tfevents.1627213414.ea93e63c112a.61.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7102b8296f0b2ff215a2a891d61ce1392327c2bacdddf974531ecd046597c05
+size 6176

runs/Jul25_12-43-49_ea93e63c112a/1627217249.31351/events.out.tfevents.1627217249.ea93e63c112a.61.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65fb0e47decb829927abad154d1b5dcb9a7a68bd472b7678683e62c334b8d5d7
+size 4189

runs/Jul25_12-43-49_ea93e63c112a/events.out.tfevents.1627217249.ea93e63c112a.61.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b9ecb2ccfe6ec0e146029009106f70116c863a5076c1925a218b73a51d9403
+size 4497

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "HooshvareLab/bert-fa-base-uncased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f65fb6a3c119e90eaa889a03d6f1845acedd842fff5334c7cb6351e49fbb3b
+size 2607