Outer Step 0. Inner Step 181. Batch Size 280

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156346,
-    5156351,
-    5156355,
-    5156360,
-    5156365,
-    5156370,
-    5156373,
-    5156379,
-    5156384,
-    5156389
+    5156425,
+    5156431,
+    5156436,
+    5156441,
+    5156446,
+    5156451,
+    5156455,
+    5156460,
+    5156466,
+    5156471
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 172,
+  "inner_step": 181,
   "inner_steps": 0,
   "last_allreduce_block": 4016775,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ea946f3cc96878847a6c877e8598c3d8e138922f54d898499d448f34f19fe5
+oid sha256:10a8789f48c3acc1b55f5bd460f43737604b2fcac4ec44627c2bd61f1c05a451
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e3ec9acce16e6ca5e9f4a693c6a7d3c7e4400e10b095cc22675408e2696e08
+oid sha256:60099e719aebce19b47ca65c79592079f95169a0ba8b9e194886bd5d9d7ab1d6
 size 4040701744