Outer Step 4. Inner Step 63. Batch Size 236

config.json

@@ -268,23 +268,30 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5149345,
-    5149349,
-    5149354,
-    5149358,
-    5149362,
-    5149366,
-    5149370,
-    5149374,
-    5149378,
-    5149383
+    5149417,
+    5149421,
+    5149425,
+    5149429,
+    5149433,
+    5149437,
+    5149441,
+    5149445,
+    5149449,
+    5149453,
+    5149458,
+    5149462,
+    5149466,
+    5149471,
+    5149475,
+    5149479,
+    5149483
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 53,
+  "inner_step": 67,
   "inner_steps": 0,
   "last_allreduce_block": 5148895,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a9903d4acef45c5d3e9a882c30eefad7abd8fa31a51961897704b9830843c0
+oid sha256:7fe507b7413d976371f8b3e11070cdbe16b4d4552d5cdc3b0bffb833c2b40031
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793ff689b2c368981f0d1db395556735adf48058ef2f8d1e3748283132282663
+oid sha256:6544b45730ddc5acccb9fd0927702767d15e595451639bdb82657aafe03ce1df
 size 4040701744