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:fcf9e36303c060af13761727a0877d29841ad77b15bb60fba8ef702be699b847
+oid sha256:0b3477f0dd3cf84c564be5a23423b739709a7468dde7c132f85af09880b005d1
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4b65d488551588bf7f66f6b44078ade1f9265692ce039dc6d56e2583a25100
+oid sha256:86ab03f43baf05be23def6902ee60da028eddbe9d66490b4f86f307dd2c226f0
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef73aa36afabdfbf7be74c4769cba6429bbaaf8e4ecdfa5b7e9a2a21434f561
+oid sha256:9e651d14e7ee52a338fd24cd91e6b6490d38a4418546e878a83bea1f77d0d566
 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": 0.20725388601036268,
+  "epoch": 0.31088082901554404,
   "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": 2.818,
       "step": 18
+    },
+    {
+      "epoch": 0.21761658031088082,
+      "grad_norm": 0.9972200393676758,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.7529,
+      "step": 21
+    },
+    {
+      "epoch": 0.24870466321243523,
+      "grad_norm": 1.182674527168274,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.7646,
+      "step": 24
+    },
+    {
+      "epoch": 0.24870466321243523,
+      "eval_loss": 2.7139012813568115,
+      "eval_runtime": 0.6506,
+      "eval_samples_per_second": 63.022,
+      "eval_steps_per_second": 32.279,
+      "step": 24
+    },
+    {
+      "epoch": 0.27979274611398963,
+      "grad_norm": 1.1637005805969238,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.6993,
+      "step": 27
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 1.096183180809021,
+      "learning_rate": 0.0,
+      "loss": 2.681,
+      "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": 138837586083840.0,
+  "total_flos": 208256379125760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null