Run 4. Outer Step 42. Inner Step 39.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5560839,
-    5560843,
-    5560847,
-    5560851,
-    5560855,
-    5560860
+    5560865,
+    5560869,
+    5560873,
+    5560878,
+    5560882
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "inner_steps": 0,
   "last_allreduce_block": 5559633,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3231ceed0e47ea2ccab52754c9ef06f49058935b2455de28b0893a2e092af16e
+oid sha256:d8312b444e82c2dea7e56f5746751d731247ed4a5c9780d9c5437e1b40f459e6
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478866c267706f69a7b30fc1f73590536bb5a596b4bfa0bf1ee2bee69ebe7b06
+oid sha256:0af87713d2d24a464d099793e6a05ff203f146ff21a3363b653cfdefa597cf44
 size 4040701744