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:b73288492c25a6f34fd808ef5258e459c65e8fad04e7eb5889019412cad5ece7
+oid sha256:40c9926f4160badcac8e3293bdd614e4e35f11ea31c60c3abee18be30f0e9d81
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11f5078d8ddda2c300229be74e67d4359bca2330374e4414bb3195c0f3a1e73
+oid sha256:84541b2335714955a16497776e4c9abd718a79d81a8d3ecef07db13666061c20
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e46f00160fa18deeea92c3c5c6cc9fe8ff25e9938d6ee8acdc58e371c80a6f30
+oid sha256:c5e9478aa48e4b65b27c05dabb1850199f14951b7f32afddf46352ce933f5ac7
 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": 2.4813461303710938,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.002940419744918587,
+  "best_metric": 2.473581075668335,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.004410629617377881,
   "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": 128.946,
       "eval_steps_per_second": 64.473,
       "step": 20
+    },
+    {
+      "epoch": 0.0030874407321645164,
+      "grad_norm": 4.689139366149902,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 9.8381,
+      "step": 21
+    },
+    {
+      "epoch": 0.0035285036939023046,
+      "grad_norm": 4.1957831382751465,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.0301,
+      "step": 24
+    },
+    {
+      "epoch": 0.003675524681148234,
+      "eval_loss": 2.4748778343200684,
+      "eval_runtime": 22.1667,
+      "eval_samples_per_second": 129.203,
+      "eval_steps_per_second": 64.601,
+      "step": 25
+    },
+    {
+      "epoch": 0.0039695666556400925,
+      "grad_norm": 5.930145740509033,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.2039,
+      "step": 27
+    },
+    {
+      "epoch": 0.004410629617377881,
+      "grad_norm": 4.439353942871094,
+      "learning_rate": 0.0,
+      "loss": 10.3096,
+      "step": 30
+    },
+    {
+      "epoch": 0.004410629617377881,
+      "eval_loss": 2.473581075668335,
+      "eval_runtime": 22.2351,
+      "eval_samples_per_second": 128.805,
+      "eval_steps_per_second": 64.403,
+      "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": 99156039303168.0,
+  "total_flos": 149811841990656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null