Run 4. Outer Step 18. Inner Step 43.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5522264,
-    5522268,
-    5522271,
-    5522275,
-    5522278,
-    5522282
+    5522285,
+    5522289,
+    5522293,
+    5522296,
+    5522300,
+    5522303,
+    5522307
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5509976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aaa6787531571c8a63925421705b9994a2cbe59eeb7df8ce7bce6ef5cdd5f9e
+oid sha256:c4d66445ebbf607e60dc560e2578de146e05cfa15440859568baf8a9f82fc3a9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2c3dc63977e91d2d9c01b567ff9ade2ae35415cd4009b27c62d0a5dcc1d05e
+oid sha256:4639af19ea375877a87215fa8ac9495c050a1a53fb98053981de432808c1928f
 size 4040701744