Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd7f4457c1fed0ab75e710ec4c037e25e68910b692621792051a320e3709285
+oid sha256:a59db3e4434ebdb2c055739fbfc497d4193984e94417e1ef056752ba70a184f8
 size 100690184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99baa93ec18e9d69ea9e60b181526fba03bd2ead335d32174e4fc5f626253e4
+oid sha256:993e389f1929284472f2ab7229af0004eae130c9ad6011c0583f2498ca66eb93
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c7c1a2d9df7762ed596ff4cf1bcff93ba007dbe9aefcb62e6894b768573c96
+oid sha256:b3e77348693ab93014486e58318571069128adf081adfe643fc83e768d147faf
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935feb3a63b37324efd90f0473c874080c886e9eea264139d581d13a208d37c1
+oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8264233469963074,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.19111323459149546,
+  "best_metric": 0.8030063509941101,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.21500238891543239,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 77.078,
       "eval_steps_per_second": 19.313,
       "step": 400
+    },
+    {
+      "epoch": 0.19589106545628285,
+      "grad_norm": 8.18686294555664,
+      "learning_rate": 1.928928356813032e-05,
+      "loss": 1.0687,
+      "step": 410
+    },
+    {
+      "epoch": 0.20066889632107024,
+      "grad_norm": 10.289799690246582,
+      "learning_rate": 1.5347142288200977e-05,
+      "loss": 1.4437,
+      "step": 420
+    },
+    {
+      "epoch": 0.20544672718585763,
+      "grad_norm": 12.29814338684082,
+      "learning_rate": 1.1822293121248375e-05,
+      "loss": 1.6965,
+      "step": 430
+    },
+    {
+      "epoch": 0.210224558050645,
+      "grad_norm": 15.640246391296387,
+      "learning_rate": 8.731908778097302e-06,
+      "loss": 1.8951,
+      "step": 440
+    },
+    {
+      "epoch": 0.21500238891543239,
+      "grad_norm": 7.856279373168945,
+      "learning_rate": 6.09104530062326e-06,
+      "loss": 1.9909,
+      "step": 450
+    },
+    {
+      "epoch": 0.21500238891543239,
+      "eval_loss": 0.8030063509941101,
+      "eval_runtime": 11.7799,
+      "eval_samples_per_second": 74.874,
+      "eval_steps_per_second": 18.761,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3725608982937600.0,
+  "total_flos": 4191310105804800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null