Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74da47094c96896426639c4a8fb962a8e70b5fc806b7d7bd426fd1c9de360e4b
+oid sha256:290bb264066338a7f9c8570118e59c9b08301ac2a0b02bce64054bef0c7d9bf7
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bf1beb84d2af9790cc09a1220fbd623c94e74c5572595f9d6f0c745dfb35987
+oid sha256:f3fd18292f466ccb3ec952f976485af620fa19468e37a0dc41e28d891e191b71
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a3fe4a57e29c75b53b9129d2ed4ef5a4612694ca662c69f8eb13c941fb9762
+oid sha256:e5382b8f90daa2b9cdd2ae396860a276504e4bf53de6e4337cafac3a4b97becd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00855431993156544,
+  "epoch": 0.01283147989734816,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 2.3632,
       "step": 18
+    },
+    {
+      "epoch": 0.008982035928143712,
+      "grad_norm": 0.879787266254425,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.231,
+      "step": 21
+    },
+    {
+      "epoch": 0.010265183917878529,
+      "grad_norm": 1.407170057296753,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.8816,
+      "step": 24
+    },
+    {
+      "epoch": 0.010265183917878529,
+      "eval_loss": 2.5725584030151367,
+      "eval_runtime": 13.8741,
+      "eval_samples_per_second": 70.996,
+      "eval_steps_per_second": 35.534,
+      "step": 24
+    },
+    {
+      "epoch": 0.011548331907613344,
+      "grad_norm": 0.7667973637580872,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.3877,
+      "step": 27
+    },
+    {
+      "epoch": 0.01283147989734816,
+      "grad_norm": 1.2102265357971191,
+      "learning_rate": 0.0,
+      "loss": 2.7211,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 166605103300608.0,
+  "total_flos": 256849534255104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null