End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sample_qa_model
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4025
+- Loss: 1.5846
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,9 +46,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.8874        | 1.0   | 500  | 1.7917          |
-| 1.5573        | 2.0   | 1000 | 1.4240          |
-| 1.1898        | 3.0   | 1500 | 1.4025          |
+| No log        | 1.0   | 125  | 2.1583          |
+| No log        | 2.0   | 250  | 1.6478          |
+| No log        | 3.0   | 375  | 1.5846          |
 
 
 ### Framework versions

config.json

@@ -1,24 +1,26 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02378736afb0d2f9e704504654aef5708d7eab8f8f69139b0fa1742a2d161cc3
-size 265470032
+oid sha256:f6b33b97fd97b587807f72446343918427f9225c7bc24b8999398dae24c349a6
+size 435596088

runs/Jul12_09-13-53_612fd39bb34e/events.out.tfevents.1720775633.612fd39bb34e.536.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba511891c1dc967707495c0eee316ebe51406f539b374d7a676df413abbaf6d2
+size 4184

runs/Jul12_09-14-07_612fd39bb34e/events.out.tfevents.1720775647.612fd39bb34e.536.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa37760b5db3e946f674c4e641a7805e58c676280f620ba372363481a33540a
+size 4184

runs/Jul12_09-15-47_612fd39bb34e/events.out.tfevents.1720775748.612fd39bb34e.6543.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f912414462a722a7c02c951c88869df2c2ba74248005290f5f0cd5ee1a265cbf
+size 5957

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f461eb11360de3dcad212018c04313edb4de58e478c102e2b8c1709f5ce2be
+oid sha256:dd35cab08bc8922143b44935d627ae7ce908d82a79d9c2272d62fd7f82e790ca
 size 5112