Model save

README.md

@@ -2,10 +2,7 @@
 license: apache-2.0
 base_model: albert-base-v2
 tags:
-- question-answering
 - generated_from_trainer
-datasets:
-- squad
 model-index:
 - name: out
   results: []
@@ -16,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # out
 
-This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
 
 ## Model description
 
@@ -36,12 +33,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
+- train_batch_size: 256
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 100.0
+- num_epochs: 3.0
 
 ### Training results
 

pruning_config.json

@@ -18,7 +18,7 @@
   },
   "pruning_fn": "unstructured_magnitude",
   "pruning_fn_default_kwargs": {
-    "target_sparsity": 0.85
+    "target_sparsity": 0.9
   },
   "pruning_frequency": 100,
   "scheduler": "iterative",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df755bb7d3a003887de39c845c728e017b329952a7a7043a5c2540d125a1d55
+oid sha256:59c8b45d58cc16f8be68b58c766c18149b106ba6c63923e4e660069e34e7fff0
 size 44387257

raw_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe9ea9534800be7b7f4f059b33e2602f707179dc37b65a376b377d0972ec5bd
+oid sha256:990d6dcf19e7b47d49c419810e1b5a77fcafce7f87a95dd98a00357b924f9eda
 size 73096798

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cae6e1933ab45584c40bf04f75bdfef187715d3cfa2e859856496066d604f6b
+oid sha256:d91e7435e117072be6cef8843ef6dd83b7578bbe597136fc05eb6c1986903100
 size 4664