Run 4. Outer Step 3. Inner Step 0.

config.json

@@ -20,17 +20,17 @@
     "111": "NON_PARTICIPATING",
     "112": "NON_PARTICIPATING",
     "113": "NON_PARTICIPATING",
-    "114": "NON_PARTICIPATING",
-    "115": "NON_PARTICIPATING",
+    "114": "SUCCESS",
+    "115": "SUCCESS",
     "116": "NON_PARTICIPATING",
     "117": "SUCCESS",
-    "118": "NON_PARTICIPATING",
+    "118": "SUCCESS",
     "119": "NON_PARTICIPATING",
     "12": "NON_PARTICIPATING",
     "120": "NON_PARTICIPATING",
     "121": "NON_PARTICIPATING",
-    "122": "SUCCESS",
-    "123": "NON_PARTICIPATING",
+    "122": "FAIL",
+    "123": "SUCCESS",
     "124": "NON_PARTICIPATING",
     "125": "SUCCESS",
     "126": "NON_PARTICIPATING",
@@ -43,7 +43,7 @@
     "132": "SUCCESS",
     "133": "NON_PARTICIPATING",
     "134": "NON_PARTICIPATING",
-    "135": "NON_PARTICIPATING",
+    "135": "SUCCESS",
     "136": "NON_PARTICIPATING",
     "137": "NON_PARTICIPATING",
     "138": "NON_PARTICIPATING",
@@ -64,7 +64,7 @@
     "151": "NON_PARTICIPATING",
     "152": "NON_PARTICIPATING",
     "153": "NON_PARTICIPATING",
-    "154": "NON_PARTICIPATING",
+    "154": "SUCCESS",
     "155": "NON_PARTICIPATING",
     "156": "SUCCESS",
     "157": "NON_PARTICIPATING",
@@ -84,14 +84,14 @@
     "17": "SUCCESS",
     "170": "NON_PARTICIPATING",
     "171": "NON_PARTICIPATING",
-    "172": "NON_PARTICIPATING",
+    "172": "SUCCESS",
     "173": "NON_PARTICIPATING",
     "174": "NON_PARTICIPATING",
     "175": "NON_PARTICIPATING",
     "176": "NON_PARTICIPATING",
     "177": "SUCCESS",
     "178": "SUCCESS",
-    "179": "NON_PARTICIPATING",
+    "179": "FAIL",
     "18": "NON_PARTICIPATING",
     "180": "NON_PARTICIPATING",
     "181": "NON_PARTICIPATING",
@@ -116,11 +116,11 @@
     "199": "NON_PARTICIPATING",
     "2": "SUCCESS",
     "20": "SUCCESS",
-    "200": "NON_PARTICIPATING",
+    "200": "SUCCESS",
     "201": "NON_PARTICIPATING",
     "202": "NON_PARTICIPATING",
     "203": "SUCCESS",
-    "204": "NON_PARTICIPATING",
+    "204": "SUCCESS",
     "205": "NON_PARTICIPATING",
     "206": "NON_PARTICIPATING",
     "207": "NON_PARTICIPATING",
@@ -169,12 +169,12 @@
     "246": "NON_PARTICIPATING",
     "247": "SUCCESS",
     "248": "NON_PARTICIPATING",
-    "249": "NON_PARTICIPATING",
+    "249": "SUCCESS",
     "25": "SUCCESS",
-    "250": "SUCCESS",
+    "250": "NON_PARTICIPATING",
     "251": "NON_PARTICIPATING",
     "252": "NON_PARTICIPATING",
-    "253": "NON_PARTICIPATING",
+    "253": "SUCCESS",
     "254": "NON_PARTICIPATING",
     "255": "SUCCESS",
     "26": "SUCCESS",
@@ -193,13 +193,13 @@
     "38": "NON_PARTICIPATING",
     "39": "SUCCESS",
     "4": "NON_PARTICIPATING",
-    "40": "NON_PARTICIPATING",
+    "40": "SUCCESS",
     "41": "SUCCESS",
     "42": "NON_PARTICIPATING",
     "43": "SUCCESS",
     "44": "SUCCESS",
     "45": "SUCCESS",
-    "46": "NON_PARTICIPATING",
+    "46": "SUCCESS",
     "47": "NON_PARTICIPATING",
     "48": "NON_PARTICIPATING",
     "49": "SUCCESS",
@@ -208,16 +208,16 @@
     "51": "SUCCESS",
     "52": "NON_PARTICIPATING",
     "53": "SUCCESS",
-    "54": "NON_PARTICIPATING",
+    "54": "SUCCESS",
     "55": "SUCCESS",
-    "56": "FAIL",
+    "56": "SUCCESS",
     "57": "NON_PARTICIPATING",
     "58": "SUCCESS",
     "59": "NON_PARTICIPATING",
-    "6": "NON_PARTICIPATING",
+    "6": "SUCCESS",
     "60": "SUCCESS",
     "61": "NON_PARTICIPATING",
-    "62": "NON_PARTICIPATING",
+    "62": "SUCCESS",
     "63": "SUCCESS",
     "64": "NON_PARTICIPATING",
     "65": "NON_PARTICIPATING",
@@ -268,25 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5480456,
-    5480459,
-    5480461,
-    5480463,
-    5480465,
-    5480468,
-    5480470,
-    5480473,
-    5480476,
-    5480478
+    5480607,
+    5480608,
+    5480611,
+    5480613,
+    5480615
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 12,
+  "inner_step": 0,
   "inner_steps": 0,
-  "last_allreduce_block": 5477809,
+  "last_allreduce_block": 5480541,
   "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 sha256:075499803a1c2d22764ff97dc8acaf3cf2ceea01535c9a437f917fbb21b420f7
+oid sha256:c6af5949be955c3ddd28294841340631f54e620679da969262eff86288c7003f
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c9d8e00c2120cd861117ca7d05cc278ef1b907cca265124e53a8529d65a07d
+oid sha256:712e598b78200841652fe175a4a9507ccf6781224c0066a2c46b2fc0b2643d29
 size 4040701744