Outer Step 0. Inner Step 94. Batch Size 468

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5155534,
-    5155538,
-    5155542,
-    5155546,
-    5155550,
-    5155554,
-    5155558,
-    5155563,
-    5155568,
-    5155572
+    5155604,
+    5155608,
+    5155613,
+    5155618,
+    5155623,
+    5155628,
+    5155633,
+    5155637,
+    5155642,
+    5155647
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 86,
+  "inner_step": 94,
   "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:b0c9b6c787d81a5389967f07ae6c692539a551f355c494f5877d759f9a13971e
+oid sha256:23957ca11f66f4b6a190961e83747bfb715eb9c57131cc8a29426eacb4b8fbe7
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34eeb388e8970ea61ba9ec2a33a8e3498411f3ad0d1170116cad9ba3e14c91b
+oid sha256:88e93a28dd11e7613ef678c37b9c8169530df15240487ad5deb31dca9580eea3
 size 4040701744