Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ea2e13943e20796577be056c05ee543a933f353f5332acad7a63d0766bb74c7
+oid sha256:129d05f7019042beba11b748e3aedd8956c391611525111e5286ede463acf481
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:156468a9244bdd69abd5afcb2d01abac7695c08236b11ec63482e3db4be27cf6
+oid sha256:bf0f6236fe42410c235b8cc7c897dfb9353f7807bdcc82701b40923afb7680ab
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc9b47b3ddbba5ee05716509f1870fbbce3c84b7c4fae2df6046aef0fa02c05
+oid sha256:fc5a222a7943acbcd99526d2d945d0d1570eb179861b9643d35f48b41f593c2a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
+oid sha256:cc8fda128404f5cc7285a078c14dccabc8f3e7d949516ad102b12752c4b2742a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4717568159103394,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.07600067556156055,
+  "best_metric": 1.4702097177505493,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.0844451950684006,
   "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": 11.084,
       "eval_steps_per_second": 2.773,
       "step": 450
+    },
+    {
+      "epoch": 0.07768957946292857,
+      "grad_norm": 2.2478957176208496,
+      "learning_rate": 4.144998534599878e-06,
+      "loss": 2.7015,
+      "step": 460
+    },
+    {
+      "epoch": 0.07937848336429656,
+      "grad_norm": 2.600090265274048,
+      "learning_rate": 2.3382067214827915e-06,
+      "loss": 3.0485,
+      "step": 470
+    },
+    {
+      "epoch": 0.08106738726566458,
+      "grad_norm": 2.7953197956085205,
+      "learning_rate": 1.0413166446519713e-06,
+      "loss": 2.9653,
+      "step": 480
+    },
+    {
+      "epoch": 0.08275629116703259,
+      "grad_norm": 3.734795570373535,
+      "learning_rate": 2.6064662219881083e-07,
+      "loss": 3.1589,
+      "step": 490
+    },
+    {
+      "epoch": 0.0844451950684006,
+      "grad_norm": 5.725466728210449,
+      "learning_rate": 0.0,
+      "loss": 3.0986,
+      "step": 500
+    },
+    {
+      "epoch": 0.0844451950684006,
+      "eval_loss": 1.4702097177505493,
+      "eval_runtime": 223.9171,
+      "eval_samples_per_second": 11.138,
+      "eval_steps_per_second": 2.787,
+      "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": 1.44902656622592e+17,
+  "total_flos": 1.6100295180288e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null