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:a69d627a2aa6e8b7b313ddffa07ce94bdfda71d02bfe9c4628e1ab9f1c6b0a8e
+oid sha256:aed9bfefedf690ca2fb996a0440da43b6ed78c989c28cfbf2621042d3a556f85
 size 2772512088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3dd7695045b6babe4ed8b335cc06c65f50e6a975604b7c1a5e188e2c68e13a
+oid sha256:dee195c0cf86b4715e8c227844bb44324ad2e6e8bed966ae55d4eb2d4170bebe
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:383cbf4e66f7a9d67ae12fcb46ba87ab42958d301baf0b32297cf7b8432fdc2e
+oid sha256:23b753ee3777e8f0a5e932987b2fc668b1580931f801da3d3d91433565ee81e4
 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": 0.24638938903808594,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.18103643358225843,
+  "epoch": 0.27155465037338766,
   "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": 3.988,
       "eval_steps_per_second": 0.998,
       "step": 50
+    },
+    {
+      "epoch": 0.1846571622539036,
+      "grad_norm": 0.1534356325864792,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.2336,
+      "step": 51
+    },
+    {
+      "epoch": 0.18827789092554878,
+      "grad_norm": 0.1455630511045456,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.2266,
+      "step": 52
+    },
+    {
+      "epoch": 0.19189861959719393,
+      "grad_norm": 0.15997833013534546,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2716,
+      "step": 53
+    },
+    {
+      "epoch": 0.1955193482688391,
+      "grad_norm": 0.16611649096012115,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.2594,
+      "step": 54
+    },
+    {
+      "epoch": 0.19914007694048427,
+      "grad_norm": 0.14760734140872955,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.2265,
+      "step": 55
+    },
+    {
+      "epoch": 0.20276080561212945,
+      "grad_norm": 0.14981094002723694,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.2602,
+      "step": 56
+    },
+    {
+      "epoch": 0.20638153428377462,
+      "grad_norm": 0.15253275632858276,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.2395,
+      "step": 57
+    },
+    {
+      "epoch": 0.21000226295541977,
+      "grad_norm": 0.14788293838500977,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.2445,
+      "step": 58
+    },
+    {
+      "epoch": 0.21362299162706494,
+      "grad_norm": 0.14573223888874054,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.2352,
+      "step": 59
+    },
+    {
+      "epoch": 0.2172437202987101,
+      "grad_norm": 0.1522066593170166,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.2466,
+      "step": 60
+    },
+    {
+      "epoch": 0.2208644489703553,
+      "grad_norm": 0.15221665799617767,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.2667,
+      "step": 61
+    },
+    {
+      "epoch": 0.22448517764200046,
+      "grad_norm": 0.15091469883918762,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.2431,
+      "step": 62
+    },
+    {
+      "epoch": 0.22810590631364563,
+      "grad_norm": 0.14665627479553223,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.2503,
+      "step": 63
+    },
+    {
+      "epoch": 0.23172663498529078,
+      "grad_norm": 0.1365693211555481,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.243,
+      "step": 64
+    },
+    {
+      "epoch": 0.23534736365693595,
+      "grad_norm": 0.14656876027584076,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.2269,
+      "step": 65
+    },
+    {
+      "epoch": 0.23896809232858113,
+      "grad_norm": 0.150408074259758,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.2334,
+      "step": 66
+    },
+    {
+      "epoch": 0.2425888210002263,
+      "grad_norm": 0.1671358346939087,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.2789,
+      "step": 67
+    },
+    {
+      "epoch": 0.24620954967187147,
+      "grad_norm": 0.15173529088497162,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.2539,
+      "step": 68
+    },
+    {
+      "epoch": 0.24983027834351662,
+      "grad_norm": 0.13886642456054688,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.2293,
+      "step": 69
+    },
+    {
+      "epoch": 0.2534510070151618,
+      "grad_norm": 0.14482015371322632,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.2467,
+      "step": 70
+    },
+    {
+      "epoch": 0.25707173568680697,
+      "grad_norm": 0.14723734557628632,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.2377,
+      "step": 71
+    },
+    {
+      "epoch": 0.2606924643584521,
+      "grad_norm": 0.16239996254444122,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.2581,
+      "step": 72
+    },
+    {
+      "epoch": 0.2643131930300973,
+      "grad_norm": 0.14651106297969818,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.2307,
+      "step": 73
+    },
+    {
+      "epoch": 0.26793392170174246,
+      "grad_norm": 0.15978926420211792,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.2613,
+      "step": 74
+    },
+    {
+      "epoch": 0.27155465037338766,
+      "grad_norm": 0.1479509025812149,
+      "learning_rate": 0.0,
+      "loss": 0.2537,
+      "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": 3.910823540655391e+17,
+  "total_flos": 5.815322950521324e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null