Run 4. Outer Step 48. Inner Step 104.

config.json

@@ -268,33 +268,39 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5570128,
-    5570129,
-    5570130,
-    5570130,
-    5570131,
-    5570132,
-    5570134,
-    5570134,
-    5570136,
-    5570137,
-    5570137,
-    5570138,
-    5570139,
-    5570139,
-    5570141,
-    5570142,
-    5570143,
-    5570144,
-    5570145,
-    5570147
+    5570148,
+    5570148,
+    5570149,
+    5570149,
+    5570150,
+    5570151,
+    5570151,
+    5570152,
+    5570152,
+    5570153,
+    5570153,
+    5570154,
+    5570155,
+    5570156,
+    5570157,
+    5570158,
+    5570159,
+    5570160,
+    5570161,
+    5570161,
+    5570162,
+    5570163,
+    5570165,
+    5570166,
+    5570167,
+    5570168
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 102,
+  "inner_step": 104,
   "inner_steps": 0,
   "last_allreduce_block": 5568918,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ba64b99e4b3ee9d7e282cc1a87dfbe15404b4301dee3e1c44e1a1c40c61bd7
+oid sha256:5ed35926843f55a7746c5b7997d606fbf7b7bd1920dce5d554e2b9af77f2b3c3
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8794352080ef7a350ca2c9cba824b1ff528576690d4232b9fe25e0385b4c93ab
+oid sha256:04277608fcef10fca133aa882ed1afb134d8d4d96cfd6b5b174a5cafb5a848e4
 size 4040701744