Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:515eb657087ddabfdc0f9bfdb77ea5d7cfd470d286be3243f27012276de046e0
+oid sha256:469e61eb1db5bbb632d3b11f25c18d220c9d1961f775b1e07b367b9d93428410
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5293207f65a2b9dae5b712b46361475dd73123ea830d2049215ee02dfe01fb93
+oid sha256:a8af00db66bbe8b1de4a672cc0b5776c3cb88244ce8ea7a077fbc9ecffe9ad2f
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ffaa87dbdd9880a8874fb8cf222a04af149eb6c4d2739069414a243173ab637
+oid sha256:14d34e9eee1b4333bd3edeece18e08e964526022e26677749f1e47a3c8289317
 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": 0.8565043210983276,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.00661031374201598,
+  "epoch": 0.009915470613023971,
   "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": 2.538,
       "eval_steps_per_second": 0.634,
       "step": 50
+    },
+    {
+      "epoch": 0.0067425200168563,
+      "grad_norm": 4.067450046539307,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 12.9902,
+      "step": 51
+    },
+    {
+      "epoch": 0.006874726291696619,
+      "grad_norm": 4.162344455718994,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 14.1395,
+      "step": 52
+    },
+    {
+      "epoch": 0.007006932566536939,
+      "grad_norm": 3.732872486114502,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 14.143,
+      "step": 53
+    },
+    {
+      "epoch": 0.007139138841377259,
+      "grad_norm": 3.6808900833129883,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 12.1621,
+      "step": 54
+    },
+    {
+      "epoch": 0.007271345116217578,
+      "grad_norm": 4.079517841339111,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 14.2904,
+      "step": 55
+    },
+    {
+      "epoch": 0.007403551391057898,
+      "grad_norm": 3.8573484420776367,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 11.8412,
+      "step": 56
+    },
+    {
+      "epoch": 0.007535757665898217,
+      "grad_norm": 4.240724086761475,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 15.1161,
+      "step": 57
+    },
+    {
+      "epoch": 0.007667963940738537,
+      "grad_norm": 4.519715785980225,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 12.7284,
+      "step": 58
+    },
+    {
+      "epoch": 0.007800170215578857,
+      "grad_norm": 3.937958240509033,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 13.8901,
+      "step": 59
+    },
+    {
+      "epoch": 0.007932376490419177,
+      "grad_norm": 4.240633010864258,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 16.1377,
+      "step": 60
+    },
+    {
+      "epoch": 0.008064582765259495,
+      "grad_norm": 3.8049137592315674,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 12.7364,
+      "step": 61
+    },
+    {
+      "epoch": 0.008196789040099815,
+      "grad_norm": 4.874120235443115,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 13.4756,
+      "step": 62
+    },
+    {
+      "epoch": 0.008328995314940135,
+      "grad_norm": 3.806867837905884,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 14.6096,
+      "step": 63
+    },
+    {
+      "epoch": 0.008461201589780455,
+      "grad_norm": 3.8149616718292236,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 13.8567,
+      "step": 64
+    },
+    {
+      "epoch": 0.008593407864620775,
+      "grad_norm": 3.4338436126708984,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 12.3285,
+      "step": 65
+    },
+    {
+      "epoch": 0.008725614139461093,
+      "grad_norm": 3.7605013847351074,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 12.8175,
+      "step": 66
+    },
+    {
+      "epoch": 0.008857820414301413,
+      "grad_norm": 3.6850969791412354,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 14.5401,
+      "step": 67
+    },
+    {
+      "epoch": 0.008990026689141733,
+      "grad_norm": 3.94093656539917,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 14.2592,
+      "step": 68
+    },
+    {
+      "epoch": 0.009122232963982053,
+      "grad_norm": 4.350830554962158,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 15.4778,
+      "step": 69
+    },
+    {
+      "epoch": 0.009254439238822373,
+      "grad_norm": 4.318081855773926,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 16.1385,
+      "step": 70
+    },
+    {
+      "epoch": 0.009386645513662693,
+      "grad_norm": 4.209683418273926,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 13.5816,
+      "step": 71
+    },
+    {
+      "epoch": 0.009518851788503011,
+      "grad_norm": 3.6689677238464355,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 13.6826,
+      "step": 72
+    },
+    {
+      "epoch": 0.009651058063343331,
+      "grad_norm": 3.67459774017334,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 12.583,
+      "step": 73
+    },
+    {
+      "epoch": 0.009783264338183651,
+      "grad_norm": 4.068629741668701,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 13.2489,
+      "step": 74
+    },
+    {
+      "epoch": 0.009915470613023971,
+      "grad_norm": 4.4557976722717285,
+      "learning_rate": 0.0,
+      "loss": 12.7368,
+      "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": 5.15209445769216e+17,
+  "total_flos": 7.72814168653824e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null