Run 4. Outer Step 62. Inner Step 28.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5611473,
-    5611477,
-    5611481,
-    5611485,
-    5611487
+    5611493,
+    5611497,
+    5611500,
+    5611504,
+    5611508,
+    5611511
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 27,
+  "inner_step": 28,
   "inner_steps": 0,
   "last_allreduce_block": 5610584,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15006e82bbbd8fbcf05cdfc0d886783408f2e918c89bc4160f02aa9c0435b32
+oid sha256:5f4b263371828829621f0a18178980ce3915e139d44b0c285b6a417838bc24d6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b12ccb1ea2b3a0b5e35c9bc51c2f82954a15d350d7b8655b26d0c08455af0773
+oid sha256:e07a267c64acef589aae4c6b5203307dadb2ede5f254065f465ecbb5b529d50c
 size 4040701744