Run 4. Outer Step 54. Inner Step 92.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580349,
-    5580351,
-    5580354,
-    5580357,
-    5580359,
-    5580361
+    5580363,
+    5580365,
+    5580368,
+    5580369,
+    5580372
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 91,
+  "inner_step": 92,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fbe929dcdaf838c8b3cec4e16adc35ef7342aae9b7484431fb4567256621211
+oid sha256:1940b9f398726b3606954bcc213f0c6a8a9486296ecef4590b177d4904a16c58
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec4b9a24addce3550ddb5550e3513f9b26e3a237acd7a7d5e588afef3475954
+oid sha256:4aa46b413cb251cb39123f169583bd8812070bef81217ddf3d27cb64d4aceb09
 size 4040701744