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:a6763f7fa966829986d7ea637479b5bbacabe7b0a1aef55f8ae5f668c7eb9976
+oid sha256:db5d7abe23d1d395ba23bfd7c8fa1e8bfa6be98480e7b3ac1c00c363373aab8e
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c14f6137aa5e1bec3dbe096f040ea182633a807890f188cf0224ebbe05129a0
+oid sha256:676c584cebe53a23e98b32592b925b05238d3faf04beab3fc7dd521aaabbe1c3
 size 101107578

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f80da0abebe5d837811a3b085c794790b62e7dfac1a6180113afe7c70c0dddd
+oid sha256:0ac477f11169e3514e3bb7ecfb7780cebfc83118b6a24e39428e3a829300f9ed
 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": 0.005866392901664589,
+  "epoch": 0.008799589352496884,
   "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": 1.2476,
       "step": 18
+    },
+    {
+      "epoch": 0.006159712546747818,
+      "grad_norm": 0.5970500111579895,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.3623,
+      "step": 21
+    },
+    {
+      "epoch": 0.007039671481997507,
+      "grad_norm": 0.5337055325508118,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.2924,
+      "step": 24
+    },
+    {
+      "epoch": 0.007039671481997507,
+      "eval_loss": 1.2639437913894653,
+      "eval_runtime": 49.9586,
+      "eval_samples_per_second": 28.744,
+      "eval_steps_per_second": 14.372,
+      "step": 24
+    },
+    {
+      "epoch": 0.007919630417247196,
+      "grad_norm": 0.6507274508476257,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.2819,
+      "step": 27
+    },
+    {
+      "epoch": 0.008799589352496884,
+      "grad_norm": 0.47197991609573364,
+      "learning_rate": 0.0,
+      "loss": 1.2989,
+      "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": 1029368772034560.0,
+  "total_flos": 1544053158051840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null