Run 4. Outer Step 56. Inner Step 48.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5600914,
-    5600916,
-    5600918,
-    5600921,
-    5600923,
-    5600926
+    5600929,
+    5600932,
+    5600935,
+    5600937,
+    5600940
   ],
   "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": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8eab899ef5e9aa7fdcf24568c27e8456eaedacdfc87d3c1ef664af6b930981b
+oid sha256:9eeac3c5f06f0a446aacf50fddf14b5ff38f18d98fb741ced4799a7e17ccdbe3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df4b830547c6709428731d690c386e5546c1af46dcf3707cc954d026cf755d5
+oid sha256:98b0b1dc65244f3980a28c899b6e70d18ca89ca020c9d376ce0345657f085b51
 size 4040701744