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:baa4b65a4897063a37bc667f8767f44f5857a984d564e9c6fa6f33a29cf886b6
+oid sha256:6f5ce85faf2ed372a9f24e3e1f2fcdef1fc2f3ed813c9f1c7f45ccec2e605fac
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d27fdcb1ffb48ea3a88e637d91fa542f319d07cabba17dfd81b25066152081e
+oid sha256:8d237350cbd7231370e1a32c0fcff812f691b63fe52d76fab6d670bd11257db4
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eacaf126875d012a3f9f4bdf60d2fff46f053b87a7d5774e37ae5621d3495b
+oid sha256:f5253772cd86b47b6517739cd8b4acf306f270c181d7d1ad9df7570086f33c99
 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": 2.5565531253814697,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0017191361340926185,
+  "best_metric": 2.541264295578003,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.002578704201138928,
   "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": 28.346,
       "eval_steps_per_second": 14.176,
       "step": 20
+    },
+    {
+      "epoch": 0.0018050929407972495,
+      "grad_norm": 4.8288798332214355,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.6334,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020629633609111422,
+      "grad_norm": 4.014038562774658,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.7247,
+      "step": 24
+    },
+    {
+      "epoch": 0.002148920167615773,
+      "eval_loss": 2.543771266937256,
+      "eval_runtime": 172.8549,
+      "eval_samples_per_second": 28.342,
+      "eval_steps_per_second": 14.174,
+      "step": 25
+    },
+    {
+      "epoch": 0.002320833781025035,
+      "grad_norm": 4.200413227081299,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.4773,
+      "step": 27
+    },
+    {
+      "epoch": 0.002578704201138928,
+      "grad_norm": 3.890751838684082,
+      "learning_rate": 0.0,
+      "loss": 10.0493,
+      "step": 30
+    },
+    {
+      "epoch": 0.002578704201138928,
+      "eval_loss": 2.541264295578003,
+      "eval_runtime": 173.2231,
+      "eval_samples_per_second": 28.281,
+      "eval_steps_per_second": 14.144,
+      "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": 1202020417536000.0,
+  "total_flos": 1803030626304000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null