Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:954d4eeb910644e5ce6263bb8aa0b97e996e085e5f14fe06a73a13b1ce646624
+oid sha256:52291fddf3e05fb01ec23ae208a4ad21b3c0b39b8977a8e06d5bd9f549c56c3f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af42308d2cf387aecd7454c34f2f84cf3a247ce4ffad8dced7bd6921cb9794ca
+oid sha256:9f1dbd4978694e3b335e954c62c3247e5206ffdfaf9610526f40dd68dd7d1869
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0b9b1e5abb37c62966cbef7926f0c56f977b762667ca3eba8a96608ea717dd
+oid sha256:20d40164920f6b8818936e4b7cb889479755457714b011381db7bfc1f8a11258
 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": 0.05362105742096901,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.3147128245476003,
+  "epoch": 0.47206923682140045,
   "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": 6.288,
       "eval_steps_per_second": 0.786,
       "step": 50
+    },
+    {
+      "epoch": 0.3210070810385523,
+      "grad_norm": 3.1018424034118652,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0904,
+      "step": 51
+    },
+    {
+      "epoch": 0.32730133752950435,
+      "grad_norm": 2.7917895317077637,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0776,
+      "step": 52
+    },
+    {
+      "epoch": 0.33359559402045635,
+      "grad_norm": 1.141679048538208,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0297,
+      "step": 53
+    },
+    {
+      "epoch": 0.33988985051140835,
+      "grad_norm": 1.4085471630096436,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0158,
+      "step": 54
+    },
+    {
+      "epoch": 0.34618410700236035,
+      "grad_norm": 2.6473264694213867,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0374,
+      "step": 55
+    },
+    {
+      "epoch": 0.35247836349331235,
+      "grad_norm": 2.7476418018341064,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0185,
+      "step": 56
+    },
+    {
+      "epoch": 0.35877261998426435,
+      "grad_norm": 1.146089792251587,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0159,
+      "step": 57
+    },
+    {
+      "epoch": 0.36506687647521635,
+      "grad_norm": 1.5934761762619019,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0249,
+      "step": 58
+    },
+    {
+      "epoch": 0.37136113296616835,
+      "grad_norm": 1.0182127952575684,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0249,
+      "step": 59
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "grad_norm": 1.0180975198745728,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0168,
+      "step": 60
+    },
+    {
+      "epoch": 0.3839496459480724,
+      "grad_norm": 1.1062073707580566,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.0155,
+      "step": 61
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.5176264643669128,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0067,
+      "step": 62
+    },
+    {
+      "epoch": 0.3965381589299764,
+      "grad_norm": 0.4311802387237549,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0103,
+      "step": 63
+    },
+    {
+      "epoch": 0.4028324154209284,
+      "grad_norm": 0.7234724760055542,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.011,
+      "step": 64
+    },
+    {
+      "epoch": 0.4091266719118804,
+      "grad_norm": 0.7512171864509583,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0119,
+      "step": 65
+    },
+    {
+      "epoch": 0.4154209284028324,
+      "grad_norm": 0.8448026180267334,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0143,
+      "step": 66
+    },
+    {
+      "epoch": 0.4217151848937844,
+      "grad_norm": 0.37998679280281067,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.004,
+      "step": 67
+    },
+    {
+      "epoch": 0.42800944138473646,
+      "grad_norm": 0.6252229809761047,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0072,
+      "step": 68
+    },
+    {
+      "epoch": 0.43430369787568845,
+      "grad_norm": 0.4169199466705322,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0064,
+      "step": 69
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "grad_norm": 0.2969546318054199,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.005,
+      "step": 70
+    },
+    {
+      "epoch": 0.44689221085759245,
+      "grad_norm": 0.6241343021392822,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0097,
+      "step": 71
+    },
+    {
+      "epoch": 0.45318646734854445,
+      "grad_norm": 0.4060995578765869,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0054,
+      "step": 72
+    },
+    {
+      "epoch": 0.45948072383949645,
+      "grad_norm": 0.5652337670326233,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0094,
+      "step": 73
+    },
+    {
+      "epoch": 0.46577498033044845,
+      "grad_norm": 0.6753122806549072,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0068,
+      "step": 74
+    },
+    {
+      "epoch": 0.47206923682140045,
+      "grad_norm": 0.3501550257205963,
+      "learning_rate": 0.0,
+      "loss": 0.004,
+      "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": 2.967600673849344e+17,
+  "total_flos": 4.451401010774016e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null