Outer Step 2. Inner Step 4889. Batch Size 300

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5117903,
-    5117909,
-    5117913,
-    5117918,
-    5117923
+    5117948,
+    5117953,
+    5117958,
+    5117963,
+    5117967
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 4884,
+  "inner_step": 4889,
   "inner_steps": 0,
   "last_allreduce_block": 5072405,
   "layer_norm_epsilon": 1e-05,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05acddbd193b469cfce1b0a9392718dceef78a7f05223e27a2e7efed8f5f8a6c
+oid sha256:bfa6797dfa8eca248c1e683e5853bcb7ac3d49c12a3881c954a7b73593a94c85
 size 4040701744