Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cd523c5bffa5d3dd693bd664f027db6f66c7e3b02b2e39251fab0811854a54
+oid sha256:31685432d6e30687da280d6ea52a6036a36a97dd6871d8e1be0acded96b61547
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788b75bf766e5d0bfef67d329c73f07b2873805255844a8af6723792272ff312
+oid sha256:5241501150c331414e46d869e6533b98237341ed4f853bdf927abc92351a4015
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912547e3439c087a494b30d9f86b186e0f5dd1b1bc4e41596aeb4a26e2e169e9
+oid sha256:ce2bcb6a2431c614d3776633abf23306ba0fe8eee56da5a86b408d372333e6b8
 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": 11.923681259155273,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.24783147459727387,
+  "epoch": 0.37174721189591076,
   "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": 98.419,
       "eval_steps_per_second": 24.605,
       "step": 50
+    },
+    {
+      "epoch": 0.2527881040892193,
+      "grad_norm": 0.06785538047552109,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 11.9238,
+      "step": 51
+    },
+    {
+      "epoch": 0.2577447335811648,
+      "grad_norm": 0.06856627762317657,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 11.9219,
+      "step": 52
+    },
+    {
+      "epoch": 0.26270136307311026,
+      "grad_norm": 0.08525048196315765,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9235,
+      "step": 53
+    },
+    {
+      "epoch": 0.26765799256505574,
+      "grad_norm": 0.06322482973337173,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 11.9243,
+      "step": 54
+    },
+    {
+      "epoch": 0.27261462205700127,
+      "grad_norm": 0.07685398310422897,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 11.9228,
+      "step": 55
+    },
+    {
+      "epoch": 0.27757125154894674,
+      "grad_norm": 0.06677208840847015,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 11.9268,
+      "step": 56
+    },
+    {
+      "epoch": 0.2825278810408922,
+      "grad_norm": 0.06735136359930038,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 11.9235,
+      "step": 57
+    },
+    {
+      "epoch": 0.2874845105328377,
+      "grad_norm": 0.0659952163696289,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 11.9245,
+      "step": 58
+    },
+    {
+      "epoch": 0.29244114002478316,
+      "grad_norm": 0.08097010850906372,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 11.9218,
+      "step": 59
+    },
+    {
+      "epoch": 0.29739776951672864,
+      "grad_norm": 0.07043331116437912,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 11.9238,
+      "step": 60
+    },
+    {
+      "epoch": 0.3023543990086741,
+      "grad_norm": 0.07436829805374146,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 11.9221,
+      "step": 61
+    },
+    {
+      "epoch": 0.3073110285006196,
+      "grad_norm": 0.07238686829805374,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 11.9243,
+      "step": 62
+    },
+    {
+      "epoch": 0.31226765799256506,
+      "grad_norm": 0.06303081661462784,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 11.924,
+      "step": 63
+    },
+    {
+      "epoch": 0.31722428748451054,
+      "grad_norm": 0.050584156066179276,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9225,
+      "step": 64
+    },
+    {
+      "epoch": 0.322180916976456,
+      "grad_norm": 0.06821806728839874,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 11.9226,
+      "step": 65
+    },
+    {
+      "epoch": 0.3271375464684015,
+      "grad_norm": 0.07609910517930984,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 11.9227,
+      "step": 66
+    },
+    {
+      "epoch": 0.33209417596034696,
+      "grad_norm": 0.09269632399082184,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 11.9239,
+      "step": 67
+    },
+    {
+      "epoch": 0.33705080545229243,
+      "grad_norm": 0.07459668070077896,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 11.9219,
+      "step": 68
+    },
+    {
+      "epoch": 0.3420074349442379,
+      "grad_norm": 0.054816748946905136,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 11.9238,
+      "step": 69
+    },
+    {
+      "epoch": 0.3469640644361834,
+      "grad_norm": 0.07526088505983353,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 11.9224,
+      "step": 70
+    },
+    {
+      "epoch": 0.35192069392812886,
+      "grad_norm": 0.06288407742977142,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 11.9252,
+      "step": 71
+    },
+    {
+      "epoch": 0.35687732342007433,
+      "grad_norm": 0.07722307741641998,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 11.9235,
+      "step": 72
+    },
+    {
+      "epoch": 0.3618339529120198,
+      "grad_norm": 0.0703897774219513,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 11.9213,
+      "step": 73
+    },
+    {
+      "epoch": 0.3667905824039653,
+      "grad_norm": 0.06519778072834015,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 11.9269,
+      "step": 74
+    },
+    {
+      "epoch": 0.37174721189591076,
+      "grad_norm": 0.05321093648672104,
+      "learning_rate": 0.0,
+      "loss": 11.9229,
+      "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": 482082816000.0,
+  "total_flos": 723124224000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null