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:d5be1b0d5a97da24d87fc9a6768b0a0c7fce7bf20ac4816236220d118fa3c35a
+oid sha256:e74ad873291c84af59f91e339185ac1a6572fdb22c911707696985213c418f1d
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edab1a588534cc32c17c58a7b6050d315de6c66ceeb9cd109b1daf37c843776d
+oid sha256:25c1996bc69066c37c95138e3fe52320752839d8b8d4be39f80568733d9e8b88
 size 1279641042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4484af7dfd7b1b75a5816aedd29aea08aa1608d0abded1b9dc2d38b28304e6
+oid sha256:2d688037a274bbb79323d3904f753e8f6ee3693343897dd5a73234dbf7f4b06e
 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": 2.2149920653191657e-07,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.07809449433814916,
+  "epoch": 0.11714174150722374,
   "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": 8.104,
       "eval_steps_per_second": 1.015,
       "step": 50
+    },
+    {
+      "epoch": 0.07965638422491214,
+      "grad_norm": 7.894937880337238e-05,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 6.547181692440063e-05,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.08278016399843811,
+      "grad_norm": 8.983476436696947e-05,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.0843420538852011,
+      "grad_norm": 8.567280747229233e-05,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.08590394377196407,
+      "grad_norm": 7.29016974219121e-05,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.08746583365872707,
+      "grad_norm": 7.546821871073917e-05,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.08902772354549005,
+      "grad_norm": 8.067455200944096e-05,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.09058961343225302,
+      "grad_norm": 8.359667845070362e-05,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.092151503319016,
+      "grad_norm": 7.18247247277759e-05,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.093713393205779,
+      "grad_norm": 6.643526285188273e-05,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.09527528309254198,
+      "grad_norm": 8.725138468435034e-05,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.09683717297930496,
+      "grad_norm": 8.253858686657622e-05,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.09839906286606795,
+      "grad_norm": 8.31460565677844e-05,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.09996095275283093,
+      "grad_norm": 7.785527122905478e-05,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.10152284263959391,
+      "grad_norm": 8.430494926869869e-05,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.10308473252635689,
+      "grad_norm": 8.321902714669704e-05,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.10464662241311988,
+      "grad_norm": 0.0001040767747326754,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.10620851229988286,
+      "grad_norm": 7.150931196520105e-05,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.10777040218664584,
+      "grad_norm": 0.00010513537563383579,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.10933229207340882,
+      "grad_norm": 9.533106640446931e-05,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11089418196017181,
+      "grad_norm": 6.648513954132795e-05,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.11245607184693479,
+      "grad_norm": 9.498356666881591e-05,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.11401796173369777,
+      "grad_norm": 8.942888234741986e-05,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.11557985162046076,
+      "grad_norm": 7.500114588765427e-05,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.11714174150722374,
+      "grad_norm": 8.365325629711151e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "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": 1.350466289050583e+17,
+  "total_flos": 2.015720618632151e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null