Outer Step 8. Inner Step 0. Batch Size 0

config.json

@@ -146,7 +146,7 @@
     "225": "NON_PARTICIPATING",
     "226": "NON_PARTICIPATING",
     "227": "NON_PARTICIPATING",
-    "228": "SUCCESS",
+    "228": "NON_PARTICIPATING",
     "229": "NON_PARTICIPATING",
     "23": "NON_PARTICIPATING",
     "230": "NON_PARTICIPATING",
@@ -160,7 +160,7 @@
     "238": "NON_PARTICIPATING",
     "239": "NON_PARTICIPATING",
     "24": "NON_PARTICIPATING",
-    "240": "SUCCESS",
+    "240": "NON_PARTICIPATING",
     "241": "NON_PARTICIPATING",
     "242": "NON_PARTICIPATING",
     "243": "NON_PARTICIPATING",
@@ -267,26 +267,15 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5277036,
-    5277041,
-    5277045,
-    5277049,
-    5277053,
-    5277058,
-    5277062,
-    5277066,
-    5277071,
-    5277075
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 652,
+  "inner_step": 0,
   "inner_steps": 0,
-  "last_allreduce_block": 5272223,
+  "last_allreduce_block": 5283755,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt_optimized",
   "n_embd": 1280,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c2134b2f6ad916bf2ed8451e7cbd555ecc0684caf6d4189a9416414d53a388a
-size 8081782026
+oid sha256:492d06eeccafd6003662b45a8cb312d2adc5edf92fda9ed4fc27f30b35362c6a
+size 2944

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba86dc5655643ab04088a5e1a9b60aadfe8bb2275359501066f74906c19da4a0
+oid sha256:c933a9ed1f5f7c6efadfcb8d1009c01cfbc8fb83615528124ae7a9849a72cf46
 size 4040701744