Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18315fac3571ac36561455ec2d7806f357b4592d0b21cc6e0434db03930c1e10
+oid sha256:ecbc76c469b0b948f7c87dbc4f906f87480aebc06bcdbbdfcea7145bfe39f9ee
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57b6d80acd2ff19ba3ce2b413f731da582ae91afc4d114c4229cb5ceb23fa968
+oid sha256:13518ce5c76a956c270644162a9373e5c8c625805ea0700c4cde7918b3cad9d2
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d9dc84d78e3645ec20519129705be658990eee7ca0807fd521f04d55017cab
+oid sha256:7b511f4a8dc304f3d7243a67a0ceace000eb97059e5a3e380accad9715a5d239
 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": 0.001828278903946797,
+  "epoch": 0.0027424183559201956,
   "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": 1.8149,
       "step": 18
+    },
+    {
+      "epoch": 0.001919692849144137,
+      "grad_norm": 0.427301287651062,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.803,
+      "step": 21
+    },
+    {
+      "epoch": 0.0021939346847361565,
+      "grad_norm": 0.38913968205451965,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.7879,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021939346847361565,
+      "eval_loss": 1.7518465518951416,
+      "eval_runtime": 1454.9335,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 1.584,
+      "step": 24
+    },
+    {
+      "epoch": 0.0024681765203281763,
+      "grad_norm": 0.4009721875190735,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.7076,
+      "step": 27
+    },
+    {
+      "epoch": 0.0027424183559201956,
+      "grad_norm": 0.41326427459716797,
+      "learning_rate": 0.0,
+      "loss": 1.7267,
+      "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": 6132638865162240.0,
+  "total_flos": 9178378972692480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null