Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773a0c099e3bab603d1738d85daa4f89e7ec125d05cf7ce0f7ecab17bd0d4be7
+oid sha256:42945e19228f3ef98eab87f75096b218273653592110b56cac8ccb3ba4d1f74c
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be811a81ea89828b6c64676e5c4a025e39ea6647111c8ce0578a4fcca7263959
+oid sha256:222f4370b979d58b0636f641ff52aa63580e75bb8df84a3efc0c8c25ccb09194
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e66cf5a33bf8bb539c7200d98de9dd45217a1abdef461b0233678a72776a5e0a
+oid sha256:64dfdcc12c4e6680bd38fd369ad70bcf926f9bdc1549f489e7b7c82f4b010786
 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": 3.2186026573181152,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.12030075187969924,
+  "best_metric": 3.150834560394287,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.18045112781954886,
   "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": 30.353,
       "eval_steps_per_second": 7.588,
       "step": 20
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 1.5489070415496826,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.8736,
+      "step": 21
+    },
+    {
+      "epoch": 0.1443609022556391,
+      "grad_norm": 1.7707982063293457,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.008,
+      "step": 24
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "eval_loss": 3.1601390838623047,
+      "eval_runtime": 4.6131,
+      "eval_samples_per_second": 30.348,
+      "eval_steps_per_second": 7.587,
+      "step": 25
+    },
+    {
+      "epoch": 0.162406015037594,
+      "grad_norm": 2.0040459632873535,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.1299,
+      "step": 27
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "grad_norm": 2.284895896911621,
+      "learning_rate": 0.0,
+      "loss": 3.1871,
+      "step": 30
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "eval_loss": 3.150834560394287,
+      "eval_runtime": 4.6277,
+      "eval_samples_per_second": 30.253,
+      "eval_steps_per_second": 7.563,
+      "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": 5514278983434240.0,
+  "total_flos": 8271418475151360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null