Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d037a5fd594e18370fa3e4c4c9446889ec6794a832208349942a5ee53b8f865e
+oid sha256:a8e09a125a509adbfcdc7deaef49153246bbceea60f34a5b539a7781b2624acb
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1157d27dce2dcecce45248d3e13fbeed0132d6326173a8b19bd68a0fc44b2915
+oid sha256:de67efb49eeb0cd60dd9f379af798cd40c1503e02cb34d3293f97d54c2e636a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.4592422502870264,
+  "epoch": 0.6888633754305397,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 48.912,
       "eval_steps_per_second": 6.131,
       "step": 50
+    },
+    {
+      "epoch": 0.46842709529276694,
+      "grad_norm": NaN,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": NaN,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.48679678530424797,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.49598163030998854,
+      "grad_norm": NaN,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.505166475315729,
+      "grad_norm": NaN,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.5143513203214696,
+      "grad_norm": NaN,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.5235361653272101,
+      "grad_norm": NaN,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.5327210103329506,
+      "grad_norm": NaN,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.5419058553386912,
+      "grad_norm": NaN,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.5510907003444316,
+      "grad_norm": NaN,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.5602755453501722,
+      "grad_norm": NaN,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.5694603903559128,
+      "grad_norm": NaN,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.5786452353616532,
+      "grad_norm": NaN,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.5878300803673938,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": NaN,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.6061997703788748,
+      "grad_norm": NaN,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": NaN,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.6245694603903559,
+      "grad_norm": NaN,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.6337543053960965,
+      "grad_norm": NaN,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.642939150401837,
+      "grad_norm": NaN,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.6521239954075775,
+      "grad_norm": NaN,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.661308840413318,
+      "grad_norm": NaN,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.6704936854190585,
+      "grad_norm": NaN,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.6796785304247991,
+      "grad_norm": NaN,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.6888633754305397,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -396,12 +571,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 246625075200.0,
+  "total_flos": 369937612800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null