Run 3. Outer Step 1. Inner Step 0. Peers 30.

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "kmfoda/gpt2-1b-miner-1",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
-    "1": "NON_PARTICIPATING",
+    "1": "SUCCESS",
     "10": "NON_PARTICIPATING",
     "100": "NON_PARTICIPATING",
-    "101": "SUCCESS",
+    "101": "NON_PARTICIPATING",
     "102": "SUCCESS",
     "103": "NON_PARTICIPATING",
     "104": "NON_PARTICIPATING",
@@ -14,7 +14,7 @@
     "106": "NON_PARTICIPATING",
     "107": "NON_PARTICIPATING",
     "108": "NON_PARTICIPATING",
-    "109": "NON_PARTICIPATING",
+    "109": "SUCCESS",
     "11": "NON_PARTICIPATING",
     "110": "NON_PARTICIPATING",
     "111": "NON_PARTICIPATING",
@@ -23,7 +23,7 @@
     "114": "NON_PARTICIPATING",
     "115": "NON_PARTICIPATING",
     "116": "NON_PARTICIPATING",
-    "117": "SUCCESS",
+    "117": "NON_PARTICIPATING",
     "118": "NON_PARTICIPATING",
     "119": "NON_PARTICIPATING",
     "12": "NON_PARTICIPATING",
@@ -77,7 +77,7 @@
     "163": "NON_PARTICIPATING",
     "164": "SUCCESS",
     "165": "NON_PARTICIPATING",
-    "166": "NON_PARTICIPATING",
+    "166": "SUCCESS",
     "167": "NON_PARTICIPATING",
     "168": "NON_PARTICIPATING",
     "169": "NON_PARTICIPATING",
@@ -89,7 +89,7 @@
     "174": "NON_PARTICIPATING",
     "175": "NON_PARTICIPATING",
     "176": "NON_PARTICIPATING",
-    "177": "SUCCESS",
+    "177": "NON_PARTICIPATING",
     "178": "NON_PARTICIPATING",
     "179": "NON_PARTICIPATING",
     "18": "NON_PARTICIPATING",
@@ -115,8 +115,8 @@
     "198": "NON_PARTICIPATING",
     "199": "NON_PARTICIPATING",
     "2": "NON_PARTICIPATING",
-    "20": "NON_PARTICIPATING",
-    "200": "NON_PARTICIPATING",
+    "20": "SUCCESS",
+    "200": "SUCCESS",
     "201": "NON_PARTICIPATING",
     "202": "NON_PARTICIPATING",
     "203": "NON_PARTICIPATING",
@@ -141,10 +141,10 @@
     "220": "NON_PARTICIPATING",
     "221": "SUCCESS",
     "222": "NON_PARTICIPATING",
-    "223": "FAIL",
+    "223": "SUCCESS",
     "224": "NON_PARTICIPATING",
-    "225": "NON_PARTICIPATING",
-    "226": "SUCCESS",
+    "225": "SUCCESS",
+    "226": "NON_PARTICIPATING",
     "227": "NON_PARTICIPATING",
     "228": "NON_PARTICIPATING",
     "229": "NON_PARTICIPATING",
@@ -184,11 +184,11 @@
     "3": "NON_PARTICIPATING",
     "30": "NON_PARTICIPATING",
     "31": "NON_PARTICIPATING",
-    "32": "NON_PARTICIPATING",
+    "32": "SUCCESS",
     "33": "NON_PARTICIPATING",
     "34": "NON_PARTICIPATING",
     "35": "NON_PARTICIPATING",
-    "36": "NON_PARTICIPATING",
+    "36": "SUCCESS",
     "37": "NON_PARTICIPATING",
     "38": "NON_PARTICIPATING",
     "39": "NON_PARTICIPATING",
@@ -212,17 +212,17 @@
     "55": "NON_PARTICIPATING",
     "56": "NON_PARTICIPATING",
     "57": "NON_PARTICIPATING",
-    "58": "SUCCESS",
+    "58": "NON_PARTICIPATING",
     "59": "NON_PARTICIPATING",
     "6": "NON_PARTICIPATING",
     "60": "NON_PARTICIPATING",
     "61": "NON_PARTICIPATING",
-    "62": "NON_PARTICIPATING",
+    "62": "SUCCESS",
     "63": "NON_PARTICIPATING",
-    "64": "NON_PARTICIPATING",
+    "64": "SUCCESS",
     "65": "NON_PARTICIPATING",
     "66": "NON_PARTICIPATING",
-    "67": "NON_PARTICIPATING",
+    "67": "SUCCESS",
     "68": "NON_PARTICIPATING",
     "69": "NON_PARTICIPATING",
     "7": "NON_PARTICIPATING",
@@ -238,7 +238,7 @@
     "79": "NON_PARTICIPATING",
     "8": "NON_PARTICIPATING",
     "80": "SUCCESS",
-    "81": "NON_PARTICIPATING",
+    "81": "SUCCESS",
     "82": "NON_PARTICIPATING",
     "83": "NON_PARTICIPATING",
     "84": "NON_PARTICIPATING",
@@ -247,7 +247,7 @@
     "87": "NON_PARTICIPATING",
     "88": "NON_PARTICIPATING",
     "89": "NON_PARTICIPATING",
-    "9": "NON_PARTICIPATING",
+    "9": "SUCCESS",
     "90": "NON_PARTICIPATING",
     "91": "NON_PARTICIPATING",
     "92": "NON_PARTICIPATING",
@@ -275,7 +275,7 @@
   "initializer_range": 0.02,
   "inner_step": 0,
   "inner_steps": 0,
-  "last_allreduce_block": 5363566,
+  "last_allreduce_block": 5366095,
   "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 sha256:50852309c11bba1c68b1fc599de303950b01245d3f8e70c6ec061ebf1229b0c3
+oid sha256:b7debebcd6091553c4fc865a538a768e96dd8cc8a2e3e2ec4737f397ffa275db
 size 2944

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b3e428e98fa30e20e42438a9da3f27f84d804d2b9741a9c840c0dcdc0d9ae6
+oid sha256:35effb7859e9e12b09ef36c9a7703d1e5590acdbc9496d16917dfab7a37957a0
 size 4040701744

outer_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e93dc7617a37533af9fd53bd75e69a0272fe35fdea96597fc44b10deaf7c748
+oid sha256:1901361aab2440a81da5873a57484f0477cd2f96e47f756842f80c55059ff417
 size 4040805354