Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199db503da642984774aff6f3c403a24878267a8059adc4cd112349723728078
+oid sha256:52a2021e5fa79671f7286d35a1bbe2a89b1fdd2905aeaf711c4799702ceec381
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf23f2f8d7707a229ebf74a87216d6a599f49e6f6013025a6ca0b052a0de48f4
+oid sha256:e2ce656bd0b7917f6e614c2cba366f1f5b3b44011eadfacf4a42ab7c0fcf2743
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
+oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
 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": 0.0013530197710014038,
+  "epoch": 0.0020295296565021057,
   "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": 10.3828,
       "step": 18
+    },
+    {
+      "epoch": 0.001420670759551474,
+      "grad_norm": 0.04169446974992752,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3719,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016236237252016845,
+      "grad_norm": 0.05514679104089737,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3866,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016236237252016845,
+      "eval_loss": 10.384563446044922,
+      "eval_runtime": 19.4305,
+      "eval_samples_per_second": 320.321,
+      "eval_steps_per_second": 160.16,
+      "step": 24
+    },
+    {
+      "epoch": 0.0018265766908518951,
+      "grad_norm": 0.046471867710351944,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3803,
+      "step": 27
+    },
+    {
+      "epoch": 0.0020295296565021057,
+      "grad_norm": 0.07241968810558319,
+      "learning_rate": 0.0,
+      "loss": 10.3867,
+      "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": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null