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:ec8ea4240868ab68021d7c618fd481db422fd28ae24a14fa4a4975ad91922b4c
+oid sha256:4e09f777fd0a5ccaebe77d2338a8026e847e881dde8f1db11e32d0345ce3babc
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6860bc3f496e1bfe2eb6c361346c64e597e874fa4c92bd35b27e2f1cd30c171c
+oid sha256:2e1fe659b8ff3e64f774b343d8a631ac31b573b55cac7c934e4b9ae6c33cfabb
 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": 0.011368480886741509,
+  "epoch": 0.017052721330112264,
   "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": 10.3758,
       "step": 18
+    },
+    {
+      "epoch": 0.011936904931078584,
+      "grad_norm": 0.05505520850419998,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3725,
+      "step": 21
+    },
+    {
+      "epoch": 0.013642177064089812,
+      "grad_norm": 0.05461163446307182,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3733,
+      "step": 24
+    },
+    {
+      "epoch": 0.013642177064089812,
+      "eval_loss": 10.372425079345703,
+      "eval_runtime": 2.4429,
+      "eval_samples_per_second": 303.324,
+      "eval_steps_per_second": 151.867,
+      "step": 24
+    },
+    {
+      "epoch": 0.015347449197101038,
+      "grad_norm": 0.05005059391260147,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3728,
+      "step": 27
+    },
+    {
+      "epoch": 0.017052721330112264,
+      "grad_norm": 0.04543205350637436,
+      "learning_rate": 0.0,
+      "loss": 10.3697,
+      "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": 536100077568.0,
+  "total_flos": 810687922176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null