Outer Step 2. Inner Step 137. Batch Size 248

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5147838,
-    5147843,
-    5147847,
-    5147851,
-    5147855,
-    5147859,
-    5147863,
-    5147868,
-    5147872,
-    5147876
+    5147906,
+    5147910,
+    5147914,
+    5147918,
+    5147922,
+    5147926,
+    5147930,
+    5147934,
+    5147938,
+    5147943
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 128,
+  "inner_step": 137,
   "inner_steps": 0,
   "last_allreduce_block": 5146835,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bdd49a2c092c101fbc8270033b9c85ba7a9e0ae5ef837b4e6332dcb0e62a3e
+oid sha256:2bd9b55fe10047d77b01491839d04a778c2c1de735e73706689342d22b764819
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d66e2d8d69a444a2c1b2cea0e041966c890ff8bd7bab5cbfbe22229472ab6d
+oid sha256:ca15574b98da9fd861e2034fb49e0d4095c5bfa4558868f23d96bd9615c8734d
 size 4040701744