Outer Step 0. Inner Step 33. Batch Size 12

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155017,
-    5155022,
-    5155027,
-    5155031,
-    5155035,
-    5155039,
-    5155044,
-    5155048,
-    5155050,
-    5155056
+    5155092,
+    5155096,
+    5155101,
+    5155105,
+    5155110,
+    5155115,
+    5155119,
+    5155123,
+    5155127,
+    5155131
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 23,
+  "inner_step": 33,
   "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 sha256:7adaef9fa447c3bcbc827e2683e864105b3efc53e7e3962282d432c2154b814f
+oid sha256:bfea392393cd5f517e017f8a72d909644d37d990e3633685e62534cf30c826a2
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7316354d8097086aecac138461df59dabac9b69ad4850d0fdb1eddbbab37296
+oid sha256:6db772ee528af920c4bbeebfc3b26b99dea4fde44ee5c2858afcd9fe4e79e30b
 size 4040701744