Run 4. Outer Step 52. Inner Step 42.

config.json

@@ -268,18 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576271,
-    5576275,
-    5576278,
-    5576281,
-    5576283
+    5576286,
+    5576289,
+    5576291,
+    5576294,
+    5576296,
+    5576298,
+    5576300
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380b5c636a8b1902c933d0120c13da60e1095d562ec9bad8acdcb76cc5c4bd92
+oid sha256:5de7a8f19d740f21cb754405d3822e49354e959390bed5d43f2007fd825d3a84
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb754026ef238ebdebd44a3b99ca46184da2aa249e264fb7c7b769830649f75
+oid sha256:21a901fd5ed7fb189d4d53ece10689e21f77566484be1ce69e91c1586b69970e
 size 4040701744