Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342fe9e007cde1c58af39ecdd254f17e12fbcc80a0663e59948c3ba8b5c9b2d3
+oid sha256:55a43cd488e5b6b2ab4fa7c5b7c44446629df38e9f0b8d72adeea1079594b802
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6a2498677656768b3bd64f171d0ffdd323a40cc62a12b43bc925cdcc0163a6
+oid sha256:0dca206f12f097252be3b2dca4e66ed7fa0a92090dab0e8effbb20cb27f66d38
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a65bb0b6374f59af3bba0a9c31166487467c2958451ecf53efed0a4c87baf89
+oid sha256:347166517ad7a63c9efb1647a0f54936248b4800068ed3fc7098bea0835a8e98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8139163255691528,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.08629989212513485,
+  "best_metric": 0.7668939232826233,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.12944983818770225,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 18.482,
       "eval_steps_per_second": 4.644,
       "step": 20
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.9415351152420044,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.6762,
+      "step": 21
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 1.2864136695861816,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.689,
+      "step": 24
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "eval_loss": 0.773655116558075,
+      "eval_runtime": 10.5644,
+      "eval_samples_per_second": 18.458,
+      "eval_steps_per_second": 4.638,
+      "step": 25
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.7668249011039734,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.6941,
+      "step": 27
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.8627511262893677,
+      "learning_rate": 0.0,
+      "loss": 0.7026,
+      "step": 30
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 0.7668939232826233,
+      "eval_runtime": 10.5656,
+      "eval_samples_per_second": 18.456,
+      "eval_steps_per_second": 4.638,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.483774567120896e+16,
+  "total_flos": 2.225661850681344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null