Model save

README.md

@@ -0,0 +1,49 @@
+---
+license: cc-by-4.0
+base_model: deepset/minilm-uncased-squad2
+tags:
+- generated_from_trainer
+model-index:
+- name: qa_finetuned
+  results: []
+---
+
+<!-- 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. -->
+
+# qa_finetuned
+
+This model is a fine-tuned version of [deepset/minilm-uncased-squad2](https://huggingface.co/deepset/minilm-uncased-squad2) on the None dataset.
+
+## 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: 2e-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: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "deepset/minilm-uncased-squad2",
   "architectures": [
     "BertForQuestionAnswering"
   ],
@@ -8,9 +8,9 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f212bffb8242b06dbae543e3aa6641e35bc2ef7fd5e54f8141cb6d899892853d
-size 435596088
+oid sha256:588733eba6f8458a138cefa233691fcbdf6f75882f378087e6cb45cb16f4cf92
+size 132874824