Outer Step 5. Inner Step 642. Batch Size 48

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5276888,
-    5276892,
-    5276897,
-    5276901,
-    5276905,
-    5276910,
-    5276914,
-    5276918,
-    5276922,
-    5276927
+    5276962,
+    5276966,
+    5276970,
+    5276975,
+    5276979,
+    5276983,
+    5276988,
+    5276992,
+    5276996,
+    5277000
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 631,
+  "inner_step": 642,
   "inner_steps": 0,
   "last_allreduce_block": 5272223,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6128ca9b7a831d252b54aa9f7937ecc1191aca390e68a04e1f091c5f3e300bd9
+oid sha256:3b9a22c3eb1162b6bb2d79ba81826da20bee137bcec0c71ea5cc60a3cc88db1d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:386b73dabfa832505d6bf0bda4ae4ae20977593d68e3f0ea29766500aaf39df1
+oid sha256:fe63b5edca711cc7af9bec4ccd225dd56e9b3414cf93e40abda292b7b51862b0
 size 4040701744