Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb6c822a3a6177865ca0ca4fc8c177a2e1bd43a370b67ae9d927a62eb8a0b15
+oid sha256:a1e62f2f239f590523414068ac3b78f63c6fee253a76fec03d20cddf12aa914f
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b516751a13cb2ca744bc59957a31348f38551c71cddf170dcac7645f0cad5af
+oid sha256:56f9edb6f163b9b49c2aeeb241df78b036e0cc0e63405c6676b2160dad0e1783
 size 1324282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39767da2cba1db844d6b51139a6c4463df23eb2b5907ed5c1f6465790e86a403
+oid sha256:ffc12d5df93df04a1713ea6a35c54d130b99b4e5e813de2037292ecda08c3400
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.688015937805176,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.08982932428386066,
+  "best_metric": 11.687907218933105,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.09981036031540073,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 67.222,
       "eval_steps_per_second": 16.821,
       "step": 450
+    },
+    {
+      "epoch": 0.09182553149016869,
+      "grad_norm": 0.098761186003685,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 11.745,
+      "step": 460
+    },
+    {
+      "epoch": 0.0938217386964767,
+      "grad_norm": 0.08001763373613358,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 11.7329,
+      "step": 470
+    },
+    {
+      "epoch": 0.09581794590278471,
+      "grad_norm": 0.12339997291564941,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 11.7327,
+      "step": 480
+    },
+    {
+      "epoch": 0.09781415310909272,
+      "grad_norm": 0.1150989755988121,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 11.7034,
+      "step": 490
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "grad_norm": 0.4080030918121338,
+      "learning_rate": 0.0,
+      "loss": 11.5079,
+      "step": 500
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "eval_loss": 11.687907218933105,
+      "eval_runtime": 31.21,
+      "eval_samples_per_second": 67.606,
+      "eval_steps_per_second": 16.918,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 63539154911232.0,
+  "total_flos": 70584955305984.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null