Outer Step 0. Inner Step 39. Batch Size 144

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5139699,
-    5139713,
-    5139727,
-    5139736,
-    5139746,
-    5139753,
-    5139760,
-    5139766,
-    5139772,
-    5139779
+    5139816,
+    5139823,
+    5139831,
+    5139838,
+    5139849,
+    5139857,
+    5139862,
+    5139868,
+    5139873,
+    5139880
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 32,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f389d0093eab69d20ae4e03e352182802183d681ddabc13dcdb7971614fdea
+oid sha256:d1b5cc11a72412077b9f18a27b3e57e293109a24553b35f4472225dee07889ed
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:073f099eddd0c0b28ed7c21a4bd4f66c1e0497fb3d5471f7db3d2c108b94e49f
+oid sha256:9de7f5d758d5b1b65f153991413e5c6d31466f0e4feaa09ceeb5cc5789275bbd
 size 4040701744