Outer Step 0. Inner Step 86. Batch Size 144

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5140022,
-    5140025,
-    5140029,
-    5140033,
-    5140038,
-    5140042,
-    5140046,
-    5140050,
-    5140053,
-    5140057
+    5140083,
+    5140086,
+    5140090,
+    5140093,
+    5140099,
+    5140104,
+    5140110,
+    5140114,
+    5140120,
+    5140126
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 76,
+  "inner_step": 86,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e00509504999ac1fc72f25ad6ef69caceffd331c352b34f89e0aef685ce293
+oid sha256:7bf26a9af40bca6d7ec3f9d4011ff41867c7fc2b9c69fb967b86b47883eea606
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f598a2e0a2d4112d5c9db225b083759681ffbf031410589d30fb2dfc6b158fa6
+oid sha256:179e1c451372328bcbe8a9018326c79195ae6c4b3ef8270ab8f31019aead8508
 size 4040701744