Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ee6e204de5fcae00778eb2eb084109506a627ac053aae3f79b63cf93f9afd4
+oid sha256:6ef0ce47faeedfd14ae2d6ae4fee755ac9a8a3986c05aa0c5412d869524629a8
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e5e65d2f0f03ed0daf341574f22ef6430207df63479d547a1b5570495d74de
+oid sha256:4116cf736db9d9f6bb39642eaa342ef2efae22b6a4ab451700ea80f427b3599b
 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": 0.29985007496251875,
+  "epoch": 0.4497751124437781,
   "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": 17.969,
       "eval_steps_per_second": 4.54,
       "step": 50
+    },
+    {
+      "epoch": 0.3058470764617691,
+      "grad_norm": NaN,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.3118440779610195,
+      "grad_norm": NaN,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.31784107946026985,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.3238380809595202,
+      "grad_norm": NaN,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.32983508245877063,
+      "grad_norm": NaN,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.335832083958021,
+      "grad_norm": NaN,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.34182908545727136,
+      "grad_norm": NaN,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": NaN,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.3538230884557721,
+      "grad_norm": NaN,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.3598200899550225,
+      "grad_norm": NaN,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.3658170914542729,
+      "grad_norm": NaN,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.37181409295352325,
+      "grad_norm": NaN,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.3778110944527736,
+      "grad_norm": NaN,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.383808095952024,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.38980509745127434,
+      "grad_norm": NaN,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.39580209895052476,
+      "grad_norm": NaN,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.4017991004497751,
+      "grad_norm": NaN,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.4077961019490255,
+      "grad_norm": NaN,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": NaN,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.4197901049475262,
+      "grad_norm": NaN,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.4257871064467766,
+      "grad_norm": NaN,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.431784107946027,
+      "grad_norm": NaN,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.43778110944527737,
+      "grad_norm": NaN,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.44377811094452774,
+      "grad_norm": NaN,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.4497751124437781,
+      "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": 2.7214473068544e+16,
+  "total_flos": 4.0821709602816e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null