Run 2. Outer Step 3. Inner Step 0.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "crypt0trading/c66-h13",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "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",
@@ -85,7 +85,7 @@
     "170": "NON_PARTICIPATING",
     "171": "NON_PARTICIPATING",
     "172": "NON_PARTICIPATING",
-    "173": "NON_PARTICIPATING",
+    "173": "SUCCESS",
     "174": "NON_PARTICIPATING",
     "175": "NON_PARTICIPATING",
     "176": "NON_PARTICIPATING",
@@ -94,10 +94,10 @@
     "179": "NON_PARTICIPATING",
     "18": "NON_PARTICIPATING",
     "180": "NON_PARTICIPATING",
-    "181": "SUCCESS",
+    "181": "NON_PARTICIPATING",
     "182": "NON_PARTICIPATING",
     "183": "NON_PARTICIPATING",
-    "184": "SUCCESS",
+    "184": "NON_PARTICIPATING",
     "185": "NON_PARTICIPATING",
     "186": "NON_PARTICIPATING",
     "187": "NON_PARTICIPATING",
@@ -114,9 +114,9 @@
     "197": "NON_PARTICIPATING",
     "198": "NON_PARTICIPATING",
     "199": "NON_PARTICIPATING",
-    "2": "SUCCESS",
+    "2": "NON_PARTICIPATING",
     "20": "NON_PARTICIPATING",
-    "200": "SUCCESS",
+    "200": "NON_PARTICIPATING",
     "201": "NON_PARTICIPATING",
     "202": "NON_PARTICIPATING",
     "203": "NON_PARTICIPATING",
@@ -141,12 +141,12 @@
     "220": "NON_PARTICIPATING",
     "221": "NON_PARTICIPATING",
     "222": "NON_PARTICIPATING",
-    "223": "NON_PARTICIPATING",
+    "223": "SUCCESS",
     "224": "NON_PARTICIPATING",
     "225": "NON_PARTICIPATING",
     "226": "NON_PARTICIPATING",
     "227": "NON_PARTICIPATING",
-    "228": "NON_PARTICIPATING",
+    "228": "SUCCESS",
     "229": "NON_PARTICIPATING",
     "23": "SUCCESS",
     "230": "NON_PARTICIPATING",
@@ -188,17 +188,17 @@
     "33": "NON_PARTICIPATING",
     "34": "NON_PARTICIPATING",
     "35": "NON_PARTICIPATING",
-    "36": "NON_PARTICIPATING",
+    "36": "SUCCESS",
     "37": "NON_PARTICIPATING",
     "38": "NON_PARTICIPATING",
-    "39": "NON_PARTICIPATING",
+    "39": "SUCCESS",
     "4": "NON_PARTICIPATING",
     "40": "NON_PARTICIPATING",
     "41": "NON_PARTICIPATING",
     "42": "NON_PARTICIPATING",
     "43": "NON_PARTICIPATING",
     "44": "NON_PARTICIPATING",
-    "45": "NON_PARTICIPATING",
+    "45": "SUCCESS",
     "46": "NON_PARTICIPATING",
     "47": "NON_PARTICIPATING",
     "48": "NON_PARTICIPATING",
@@ -212,7 +212,7 @@
     "55": "NON_PARTICIPATING",
     "56": "NON_PARTICIPATING",
     "57": "NON_PARTICIPATING",
-    "58": "NON_PARTICIPATING",
+    "58": "SUCCESS",
     "59": "NON_PARTICIPATING",
     "6": "NON_PARTICIPATING",
     "60": "NON_PARTICIPATING",
@@ -234,7 +234,7 @@
     "75": "NON_PARTICIPATING",
     "76": "NON_PARTICIPATING",
     "77": "NON_PARTICIPATING",
-    "78": "SUCCESS",
+    "78": "NON_PARTICIPATING",
     "79": "NON_PARTICIPATING",
     "8": "NON_PARTICIPATING",
     "80": "NON_PARTICIPATING",
@@ -267,21 +267,15 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [
-    5330554,
-    5330558,
-    5330562,
-    5330566,
-    5330570
-  ],
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 117,
+  "inner_step": 0,
   "inner_steps": 0,
-  "last_allreduce_block": 5323221,
+  "last_allreduce_block": 5330632,
   "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 sha256:1fa75e0b8e6d0c03acf813da2644fd9b5ad7fb336d9ad77229c48875555f1ce3
+oid sha256:898b0a36c2505d6758769a80676b4795fcab5f81ef52c3f9a1e115538eec578d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958310cb9221d13f6559c726d2fa5a78d892f8cee3799e4940b87e877bee47be
+oid sha256:9d627d8a20903d8137d02511fb1a23ea4261d41dc04f46a5426df8e48bcd8f67
 size 4040701744