Run 2. Outer Step 4. Inner Step 2.

config.json

@@ -23,7 +23,7 @@
     "114": "NON_PARTICIPATING",
     "115": "NON_PARTICIPATING",
     "116": "NON_PARTICIPATING",
-    "117": "NON_PARTICIPATING",
+    "117": "SUCCESS",
     "118": "NON_PARTICIPATING",
     "119": "NON_PARTICIPATING",
     "12": "NON_PARTICIPATING",
@@ -85,7 +85,7 @@
     "170": "NON_PARTICIPATING",
     "171": "NON_PARTICIPATING",
     "172": "NON_PARTICIPATING",
-    "173": "SUCCESS",
+    "173": "NON_PARTICIPATING",
     "174": "NON_PARTICIPATING",
     "175": "NON_PARTICIPATING",
     "176": "NON_PARTICIPATING",
@@ -106,7 +106,7 @@
     "19": "NON_PARTICIPATING",
     "190": "NON_PARTICIPATING",
     "191": "NON_PARTICIPATING",
-    "192": "NON_PARTICIPATING",
+    "192": "SUCCESS",
     "193": "NON_PARTICIPATING",
     "194": "NON_PARTICIPATING",
     "195": "NON_PARTICIPATING",
@@ -114,9 +114,9 @@
     "197": "NON_PARTICIPATING",
     "198": "NON_PARTICIPATING",
     "199": "NON_PARTICIPATING",
-    "2": "NON_PARTICIPATING",
+    "2": "SUCCESS",
     "20": "NON_PARTICIPATING",
-    "200": "NON_PARTICIPATING",
+    "200": "SUCCESS",
     "201": "NON_PARTICIPATING",
     "202": "NON_PARTICIPATING",
     "203": "NON_PARTICIPATING",
@@ -141,7 +141,7 @@
     "220": "NON_PARTICIPATING",
     "221": "NON_PARTICIPATING",
     "222": "NON_PARTICIPATING",
-    "223": "SUCCESS",
+    "223": "NON_PARTICIPATING",
     "224": "NON_PARTICIPATING",
     "225": "NON_PARTICIPATING",
     "226": "NON_PARTICIPATING",
@@ -268,20 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5331615,
-    5331619,
-    5331623,
-    5331628,
-    5331632
+    5331680,
+    5331694,
+    5331698,
+    5331702,
+    5331706
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 125,
+  "inner_step": 2,
   "inner_steps": 0,
-  "last_allreduce_block": 5330632,
+  "last_allreduce_block": 5331536,
   "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:d098d0e8d55cdc13b11446855563ac0b9409aae072bd067e98c478392e308ac5
+oid sha256:4d579e4f6176d025c86a463f23fe1c9726f35632ff7029ca736c39a809ad2b15
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef99c0b6d143844d15e15c9d9a3ae86650d1936db005075b34b03ae024bb766
+oid sha256:ebffc26721231e4d42588d6261cb3be29310f378e238468ce159669a0767ee65
 size 4040701744