Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6163ed6798299a880454e0d595b1ea72fa8c7b5ab7f9187758519cc47bcf362d
+oid sha256:71d947cb79a728694bb63f7a85a5bb2461ae686bed5e57dc6bf7e8c65b2b1b61
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc1479738a7d2ccff2a2a149b75d56c5819ebe12fed72ce3d7bcd3a4952eed0
+oid sha256:d3238f70c4557b5e9559b878d19d27c51df75fd68db8f9401f7012e994e86c24
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8ae7795446675a073d921f9debfe2f695a779b336b5bafaeaa9e3a977c1500
+oid sha256:179f25ffbc30df400dcdf0e9f32996e239bbd6b78c367ae3011013cae7f746e3
 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": 0.050220850855112076,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.9324009324009324,
+  "epoch": 1.400932400932401,
   "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": 6.141,
       "eval_steps_per_second": 1.552,
       "step": 50
+    },
+    {
+      "epoch": 0.951048951048951,
+      "grad_norm": 0.13983112573623657,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0631,
+      "step": 51
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.1023995652794838,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0313,
+      "step": 52
+    },
+    {
+      "epoch": 0.9883449883449883,
+      "grad_norm": 0.08331304788589478,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0426,
+      "step": 53
+    },
+    {
+      "epoch": 1.0093240093240092,
+      "grad_norm": 0.12266716361045837,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0565,
+      "step": 54
+    },
+    {
+      "epoch": 1.027972027972028,
+      "grad_norm": 0.055081456899642944,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0395,
+      "step": 55
+    },
+    {
+      "epoch": 1.0466200466200466,
+      "grad_norm": 0.08440406620502472,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0375,
+      "step": 56
+    },
+    {
+      "epoch": 1.0652680652680653,
+      "grad_norm": 0.08142155408859253,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0374,
+      "step": 57
+    },
+    {
+      "epoch": 1.083916083916084,
+      "grad_norm": 0.0638071596622467,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0448,
+      "step": 58
+    },
+    {
+      "epoch": 1.1025641025641026,
+      "grad_norm": 0.07102889567613602,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.038,
+      "step": 59
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.06918191909790039,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0398,
+      "step": 60
+    },
+    {
+      "epoch": 1.1398601398601398,
+      "grad_norm": 0.06793826073408127,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.037,
+      "step": 61
+    },
+    {
+      "epoch": 1.1585081585081585,
+      "grad_norm": 0.060138434171676636,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0412,
+      "step": 62
+    },
+    {
+      "epoch": 1.1771561771561772,
+      "grad_norm": 0.06100895628333092,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0391,
+      "step": 63
+    },
+    {
+      "epoch": 1.1958041958041958,
+      "grad_norm": 0.08120011538267136,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0377,
+      "step": 64
+    },
+    {
+      "epoch": 1.2144522144522145,
+      "grad_norm": 0.05974452942609787,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0496,
+      "step": 65
+    },
+    {
+      "epoch": 1.2331002331002332,
+      "grad_norm": 0.06714749336242676,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0411,
+      "step": 66
+    },
+    {
+      "epoch": 1.2517482517482517,
+      "grad_norm": 0.06198333948850632,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0394,
+      "step": 67
+    },
+    {
+      "epoch": 1.2703962703962703,
+      "grad_norm": 0.08504387736320496,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0353,
+      "step": 68
+    },
+    {
+      "epoch": 1.289044289044289,
+      "grad_norm": 0.12137630581855774,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0452,
+      "step": 69
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.06834172457456589,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0434,
+      "step": 70
+    },
+    {
+      "epoch": 1.3263403263403264,
+      "grad_norm": 0.05725034326314926,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0462,
+      "step": 71
+    },
+    {
+      "epoch": 1.3449883449883449,
+      "grad_norm": 0.06547888368368149,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0408,
+      "step": 72
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.060845568776130676,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0457,
+      "step": 73
+    },
+    {
+      "epoch": 1.3822843822843822,
+      "grad_norm": 0.05932041257619858,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0422,
+      "step": 74
+    },
+    {
+      "epoch": 1.400932400932401,
+      "grad_norm": 0.0670986920595169,
+      "learning_rate": 0.0,
+      "loss": 0.0386,
+      "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": 1.508513578745856e+17,
+  "total_flos": 2.262770368118784e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null