Run 4. Outer Step 50. Inner Step 4.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5622198,
-    5622201,
-    5622203,
-    5622205,
-    5622207,
-    5622208,
-    5622211
+    5622215,
+    5622218,
+    5622220,
+    5622223,
+    5622226
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 3,
+  "inner_step": 4,
   "inner_steps": 0,
   "last_allreduce_block": 5571611,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca789eeba9881759411db1669cc417c974fb4d742c9cef931f3e429f57547b0
+oid sha256:a61ffb1b8a71677ff616b364d967efbf44fdb6cd48fd17384d2195165d0b2d9b
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bead43953d9960f8862a9c0911b06fdcc05b2010e5e67f41a75161f5188dbf8
+oid sha256:d3b8de5d73bdc80fcf5b8386c056a0f792c8ead26290512557834252170d43ec
 size 4040701744