Run 4. Outer Step 43. Inner Step 62.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5562674,
-    5562678,
-    5562683,
-    5562687,
-    5562692,
-    5562696
+    5562701,
+    5562706,
+    5562710,
+    5562714,
+    5562720
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 61,
+  "inner_step": 62,
   "inner_steps": 0,
   "last_allreduce_block": 5556551,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d26f4ff962a2f39c6ba9fb430d7ea7b1e675c5a2f906d96c054642b9bbd3b095
+oid sha256:1de1bdd5e3549338724c38ec6a7b4c134d00a8f625fef923e062f504eb39457f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d61b2b527075f271b69bc579c8697d655d1bea552ff2b3867f67b1c17bd60d4
+oid sha256:ac982f304cb087db2520fb944123f268a8b76e5aee1fc25f03c4f9ab69655600
 size 4040701744