Outer Step 1. Inner Step 2601. Batch Size 192

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5185781,
-    5185786,
-    5185791,
-    5185798,
-    5185802,
-    5185806,
-    5185811,
-    5185815,
-    5185819,
-    5185824
+    5185854,
+    5185858,
+    5185863,
+    5185867,
+    5185871,
+    5185875,
+    5185880,
+    5185884,
+    5185888,
+    5185893
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 2591,
+  "inner_step": 2601,
   "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 sha256:53049adafc098551d2c13af5c844a196d6556e5afd6ed2526527113b08190c99
+oid sha256:4fc49c654e102ce7c5523aee8029fdfaa43a77cd42363cb427afdcb411efdcaa
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e59c6c6e456811d8fef547c8535fffd0454e6a3859e7ceec61a504b30c4d33
+oid sha256:740caabc8d977562f3cb60841291be421f72a5ef052d6ee0f08cc39adcfcc9ab
 size 4040701744