Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0928ac4457983c6f1b13aa59ad6920d32877f28240eafd9dbe5bea016c536c0b
+oid sha256:258313340fe2f13b9df1c0ac9a519aca505be460badb60e9d263a5faef77b85a
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd0b1d2c476604ebfaffad1d9cd0fbcd5b71e750cbddbf3dfbe868482b9416f
+oid sha256:8027a09dae2de8cc0ee95e0199071df2a229dde616a2d7dcb8a8576d3d2d114d
 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": 11.924012184143066,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.03139224611520954,
+  "epoch": 0.047088369172814316,
   "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": 94.709,
       "eval_steps_per_second": 23.686,
       "step": 50
+    },
+    {
+      "epoch": 0.032020091037513736,
+      "grad_norm": 0.08443606644868851,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 11.9236,
+      "step": 51
+    },
+    {
+      "epoch": 0.03264793595981792,
+      "grad_norm": 0.125528022646904,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 11.9254,
+      "step": 52
+    },
+    {
+      "epoch": 0.033275780882122116,
+      "grad_norm": 0.08672455698251724,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9215,
+      "step": 53
+    },
+    {
+      "epoch": 0.03390362580442631,
+      "grad_norm": 0.07923948019742966,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 11.9247,
+      "step": 54
+    },
+    {
+      "epoch": 0.0345314707267305,
+      "grad_norm": 0.07594846189022064,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 11.9233,
+      "step": 55
+    },
+    {
+      "epoch": 0.03515931564903469,
+      "grad_norm": 0.0686110109090805,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 11.9232,
+      "step": 56
+    },
+    {
+      "epoch": 0.03578716057133888,
+      "grad_norm": 0.08526276051998138,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 11.9256,
+      "step": 57
+    },
+    {
+      "epoch": 0.03641500549364307,
+      "grad_norm": 0.07757719606161118,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 11.9213,
+      "step": 58
+    },
+    {
+      "epoch": 0.03704285041594726,
+      "grad_norm": 0.08641009032726288,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 11.9248,
+      "step": 59
+    },
+    {
+      "epoch": 0.03767069533825145,
+      "grad_norm": 0.09379945695400238,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 11.9224,
+      "step": 60
+    },
+    {
+      "epoch": 0.038298540260555645,
+      "grad_norm": 0.07984328269958496,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 11.9233,
+      "step": 61
+    },
+    {
+      "epoch": 0.03892638518285983,
+      "grad_norm": 0.079765185713768,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 11.9233,
+      "step": 62
+    },
+    {
+      "epoch": 0.039554230105164026,
+      "grad_norm": 0.06862898170948029,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 11.9237,
+      "step": 63
+    },
+    {
+      "epoch": 0.04018207502746821,
+      "grad_norm": 0.07996665686368942,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9191,
+      "step": 64
+    },
+    {
+      "epoch": 0.04080991994977241,
+      "grad_norm": 0.07772701978683472,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 11.9224,
+      "step": 65
+    },
+    {
+      "epoch": 0.0414377648720766,
+      "grad_norm": 0.06042219698429108,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 11.9217,
+      "step": 66
+    },
+    {
+      "epoch": 0.04206560979438079,
+      "grad_norm": 0.07889144122600555,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 11.9256,
+      "step": 67
+    },
+    {
+      "epoch": 0.04269345471668498,
+      "grad_norm": 0.16606417298316956,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 11.9278,
+      "step": 68
+    },
+    {
+      "epoch": 0.04332129963898917,
+      "grad_norm": 0.05187804624438286,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 11.9209,
+      "step": 69
+    },
+    {
+      "epoch": 0.04394914456129336,
+      "grad_norm": 0.060179345309734344,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 11.9248,
+      "step": 70
+    },
+    {
+      "epoch": 0.04457698948359755,
+      "grad_norm": 0.07308786362409592,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 11.9221,
+      "step": 71
+    },
+    {
+      "epoch": 0.04520483440590174,
+      "grad_norm": 0.05937618017196655,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 11.9224,
+      "step": 72
+    },
+    {
+      "epoch": 0.045832679328205936,
+      "grad_norm": 0.0707944706082344,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 11.9222,
+      "step": 73
+    },
+    {
+      "epoch": 0.04646052425051012,
+      "grad_norm": 0.056737788021564484,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 11.9212,
+      "step": 74
+    },
+    {
+      "epoch": 0.047088369172814316,
+      "grad_norm": 0.06692962348461151,
+      "learning_rate": 0.0,
+      "loss": 11.9188,
+      "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": 488108851200.0,
+  "total_flos": 729150259200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null