Training in progress, step 75, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1917ae1869cc83071bfa93239745e9805757c8c82bb8b00a37591429120b8565
+oid sha256:c7bef7f6ecf1be3fdde00ddc0d0e4381549a20ee8c8104b773c962f13697fb26
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8ae7795446675a073d921f9debfe2f695a779b336b5bafaeaa9e3a977c1500
+oid sha256:2aac992802a1f33b22a8280d7fe5a822a850ad6f4cbf47f64bd611e64dfc8998
 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": 0.15904572564612326,
+  "epoch": 0.23856858846918488,
   "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": 6.966,
       "eval_steps_per_second": 1.748,
       "step": 50
+    },
+    {
+      "epoch": 0.16222664015904573,
+      "grad_norm": NaN,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.1654075546719682,
+      "grad_norm": NaN,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.16858846918489065,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.1717693836978131,
+      "grad_norm": NaN,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.1749502982107356,
+      "grad_norm": NaN,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.17813121272365806,
+      "grad_norm": NaN,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.18131212723658052,
+      "grad_norm": NaN,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.18449304174950298,
+      "grad_norm": NaN,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.18767395626242545,
+      "grad_norm": NaN,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.1908548707753479,
+      "grad_norm": NaN,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.19403578528827037,
+      "grad_norm": NaN,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.19721669980119283,
+      "grad_norm": NaN,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.20039761431411532,
+      "grad_norm": NaN,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.20357852882703778,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.20675944333996024,
+      "grad_norm": NaN,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.2099403578528827,
+      "grad_norm": NaN,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.21312127236580516,
+      "grad_norm": NaN,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.21630218687872763,
+      "grad_norm": NaN,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.2194831013916501,
+      "grad_norm": NaN,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.22266401590457258,
+      "grad_norm": NaN,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.22584493041749504,
+      "grad_norm": NaN,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.2290258449304175,
+      "grad_norm": NaN,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.23220675944333996,
+      "grad_norm": NaN,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.23538767395626242,
+      "grad_norm": NaN,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.23856858846918488,
+      "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": 1.431616484278272e+17,
+  "total_flos": 2.147424726417408e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null