Outer Step 0. Inner Step 182. Batch Size 0

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5156399,
-    5156404,
-    5156409,
-    5156415,
-    5156419,
-    5156425,
-    5156430,
-    5156435,
-    5156441,
-    5156445
+    5156479,
+    5156483,
+    5156488,
+    5156493,
+    5156498,
+    5156503,
+    5156508,
+    5156513,
+    5156516,
+    5156523
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 173,
+  "inner_step": 182,
   "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:e73d37d6f25f23f2485b9509919feaf83f54bd33a9716b64e059b372eea80492
+oid sha256:4ce30e603838baf2f0fb0943d7556e23a16c91419f1750df8c76a2aa5e38040c
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca75f1987edc7aafceb94eab895921e845d90f0b72ed7a97eff7343c92069f6d
+oid sha256:45ead8f3da2c7fc70721c4b5d9e22a75b7c87453c6101bea8f3e15c4291cd82a
 size 4040701744