Outer Step 2. Inner Step 147. Batch Size 208

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5147906,
-    5147910,
-    5147914,
-    5147918,
-    5147922,
-    5147926,
-    5147930,
-    5147934,
-    5147938,
-    5147943
+    5147977,
+    5147981,
+    5147985,
+    5147989,
+    5147993,
+    5147996,
+    5148002,
+    5148006,
+    5148010,
+    5148014
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 137,
+  "inner_step": 147,
   "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 sha256:2bd9b55fe10047d77b01491839d04a778c2c1de735e73706689342d22b764819
+oid sha256:90bf9485ba91196acd7689989f9ae1b4a91cf5beaf9fd1ed9fd44419db31aaa2
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca15574b98da9fd861e2034fb49e0d4095c5bfa4558868f23d96bd9615c8734d
+oid sha256:825feb284d0f668b17be474b92bb654155a6c62c158be04cbdbffdc7014eac5c
 size 4040701744