Outer Step 0. Inner Step 68. Batch Size 472

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155319,
-    5155324,
-    5155329,
-    5155334,
-    5155339,
-    5155345,
-    5155349,
-    5155353,
-    5155357,
-    5155361
+    5155394,
+    5155398,
+    5155403,
+    5155407,
+    5155411,
+    5155415,
+    5155418,
+    5155423,
+    5155427,
+    5155430
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 60,
+  "inner_step": 68,
   "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:b614fe9d3601bdd722ef05844b005bb66066152d895f7837c1e8e92414a508a2
+oid sha256:f29e08327dc48eca5642de15d6e2dcc7e731a6a5724e5c503f834059908b30dc
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2704546bf3ce0cca028680acc0a6388cc5bf1375033d1835528632f5fd961ef3
+oid sha256:227d9c1976dc004898d539347bf240578cb03683f8161fd42b947fd156377f29
 size 4040701744