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:ee4401ee85060645b9859fc1c9ffcafdb717a9e27abcaa73cae55baf0fd07484
+oid sha256:0baf3600250d7dd148b2a7506413466fb63822752e1a91a2be241564408eaf7c
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e6f2d676530731ed90e8af67b4882e3679aa13b319f4e5b98d63edc3caa235
+oid sha256:c17fca9117ec4a63b21db77e40c58c5c1762e00fd1bb1a9ad6853a4d5ce84f80
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24268d68cd2144d5eb0a6d21f8cf0b27030c12131d82df42a3468a1c5df11630
+oid sha256:edfa4a30562ce22486a45a8f0e2d6ac45fd06d7769b2e23c5a93834a207b67c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0721370604147881,
+  "epoch": 0.10820559062218214,
   "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": 22.425,
       "eval_steps_per_second": 11.308,
       "step": 20
+    },
+    {
+      "epoch": 0.0757439134355275,
+      "grad_norm": 571.6266479492188,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 10.7429,
+      "step": 21
+    },
+    {
+      "epoch": 0.08656447249774572,
+      "grad_norm": 35.94160842895508,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.1588,
+      "step": 24
+    },
+    {
+      "epoch": 0.09017132551848513,
+      "eval_loss": 2.5596375465393066,
+      "eval_runtime": 5.1868,
+      "eval_samples_per_second": 22.557,
+      "eval_steps_per_second": 11.375,
+      "step": 25
+    },
+    {
+      "epoch": 0.09738503155996393,
+      "grad_norm": 6.185794353485107,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 9.787,
+      "step": 27
+    },
+    {
+      "epoch": 0.10820559062218214,
+      "grad_norm": 64.7603530883789,
+      "learning_rate": 0.0,
+      "loss": 10.0356,
+      "step": 30
+    },
+    {
+      "epoch": 0.10820559062218214,
+      "eval_loss": 2.549482822418213,
+      "eval_runtime": 5.202,
+      "eval_samples_per_second": 22.491,
+      "eval_steps_per_second": 11.342,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 489185718829056.0,
+  "total_flos": 750843196342272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null