Training in progress, step 500

config.json

@@ -16,7 +16,7 @@
   "max_position_embeddings": 512,
   "model_type": "squeezebert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 10,
+  "num_hidden_layers": 2,
   "output_groups": 4,
   "pad_token_id": 0,
   "post_attention_groups": 1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc799c54a189a498c50162491cc4c24c85f00e616fa7e1f51642eef16bd0ad9
-size 189170407
+oid sha256:6db5aaf8e140b00bf4bbac5553f10960427f253af71b2d55c95b9fcc17de1799
+size 118017246

runs/Mar09_16-48-30_d59e2229e41d/1646844612.2426162/events.out.tfevents.1646844612.d59e2229e41d.78.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0c1369de2063928f5302f991caf5e8642577ccea9a24d8ae364b8e967d206a
+size 4758

runs/Mar09_16-48-30_d59e2229e41d/events.out.tfevents.1646844612.d59e2229e41d.78.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a228f78c10ddc051fde7e1f160d73b3a37fdc8f6efd502a1626727a9993552c
+size 3454

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497115be3850f40e353e0524a11867b43d93208d5907118e1bf1cf61e11c9bb7
+oid sha256:f6d7fd0ff77ffa7ef8ffbe92932b29e7f75dd51c19c5f2f382ee16594282a7aa
 size 3055