Run 4. Outer Step 50. Inner Step 48.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5573072,
-    5573077,
-    5573082,
-    5573086,
-    5573091,
-    5573096
+    5573101,
+    5573105,
+    5573110,
+    5573115,
+    5573120
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 47,
+  "inner_step": 48,
   "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 sha256:4c24701263bb14f24f9408b1acf24ef70cd3abae653189c9fa72bb79f103d255
+oid sha256:4ab028ad087518df83eb00af045942e184e4b4dccf123b15e4f0cc2d232e5a88
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed769607f0905ce52df1a2cf94103350ddf5e1fedf0c6592f2b0e8793e0d57e
+oid sha256:bc86a82118bbbf06a844927e2b1500d7cec5e2a33053dbf956e5a22353cb7edc
 size 4040701744