End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: albert/albert-base-v2
+base_model: hadsag/TinyBERT_General_4L_312D-finetuned-squad
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # albert-base-v2-finetuned-squad
 
-This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.9798
+This model is a fine-tuned version of [hadsag/TinyBERT_General_4L_312D-finetuned-squad](https://huggingface.co/hadsag/TinyBERT_General_4L_312D-finetuned-squad) on an unknown dataset.
 
 ## Model description
 
@@ -42,15 +39,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3
 
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.8718        | 1.0   | 8248  | 0.8569          |
-| 0.6549        | 2.0   | 16496 | 0.8389          |
-| 0.4521        | 3.0   | 24744 | 0.9798          |
-
-
 ### Framework versions
 
 - Transformers 4.37.2

config.json

@@ -1,33 +1,29 @@
 {
-  "_name_or_path": "albert/albert-base-v2",
+  "_name_or_path": "hadsag/TinyBERT_General_4L_312D-finetuned-squad",
   "architectures": [
-    "AlbertForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
-  "hidden_size": 768,
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
+  "intermediate_size": 1200,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
-  "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "structure": [],
   "torch_dtype": "float32",
   "transformers_version": "4.37.2",
   "type_vocab_size": 2,
-  "vocab_size": 30000
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde4817961433b536203173875c6a15d6c9c0fee1ccdee5d2b4ee56a55d1afc5
-size 44381360
+oid sha256:e315d8533371570ebe7d4439e57411e8544cde1e55be394b3408d7c2b6a98b12
+size 57020992