Run 4. Outer Step 52. Inner Step 29.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5575886,
-    5575888,
-    5575891,
-    5575894,
-    5575897,
-    5575899
+    5575903,
+    5575906,
+    5575908,
+    5575910,
+    5575912
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a551b62dde7d6bb6e3c76e3821c0f2094395cacb44e31bd7d4ac35b939ceec7c
+oid sha256:c918bd342bbc0cf03a344167088a965095b8aa1d021ae0314db0e854a35d8275
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7651d82abadce606617093a7ba241023c57068c234979f92b2ee175f13ccda9
+oid sha256:023f9a77264a5ef1a7fc80f4012fa70f48ccaea09b928f41dc894d75f731c3ee
 size 4040701744