NLP702-bert-large-uncased_finetuning-distillation_hs768-nh32-nl12

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4513
-- Accuracy: 0.8460
+- Loss: 0.4721
+- Accuracy: 0.8352
 
 ## Model description
 
@@ -50,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.6134        | 1.39  | 500  | 0.6952          | 0.7560   |
-| 0.4746        | 2.78  | 1000 | 0.5133          | 0.8141   |
-| 0.2242        | 4.17  | 1500 | 0.4549          | 0.8490   |
-| 0.1182        | 5.56  | 2000 | 0.4262          | 0.8544   |
+| 1.7395        | 1.39  | 500  | 0.8593          | 0.6847   |
+| 0.6019        | 2.78  | 1000 | 0.5655          | 0.7949   |
+| 0.3085        | 4.17  | 1500 | 0.4899          | 0.8293   |
+| 0.1631        | 5.56  | 2000 | 0.4558          | 0.8475   |
 
 
 ### Framework versions

best/config.json

@@ -136,8 +136,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 8,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

best/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5a78470240484fcf8543ad64573141a6c7a4d65bd1b7bd23107c3e775942b9
-size 324723536
+oid sha256:27c43deb31b602550eff4fab8f503c4750833999e0d5c7c439bda7dcba3c5b7f
+size 438137056

config.json

@@ -136,8 +136,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 8,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5a78470240484fcf8543ad64573141a6c7a4d65bd1b7bd23107c3e775942b9
-size 324723536
+oid sha256:27c43deb31b602550eff4fab8f503c4750833999e0d5c7c439bda7dcba3c5b7f
+size 438137056