Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f79a5a0ceca833548e57caa46a79cb807c5e7bf90cfa2afd598e416a9db70244
+oid sha256:4f302302723ee9af13e3716d65d3e4877c8096a513e0215c684c7a170a359d42
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c6a73d2b805c2343457091e2fdbce9e6f0f25131a5c4fd1a11b2b82236ad85
+oid sha256:ccd4c20988fc5856dcbf30f45a7e4205de46e77c021698a02a427664b154a2b8
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b77f278dcace3954c8a0406b8cd521a9f7d5e54485350ef22d7ee85c9deea8
+oid sha256:3cb409ae620b5bbdfeea121938a3b3d9d9f10021e589f8d860427406bb0f91fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001241837505562397,
+  "epoch": 0.00013798194506248857,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 7.407,
       "eval_steps_per_second": 3.704,
       "step": 9
+    },
+    {
+      "epoch": 0.00013798194506248857,
+      "grad_norm": 10.579679489135742,
+      "learning_rate": 0.0002,
+      "loss": 4.6917,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1719982274641920.0,
+  "total_flos": 1911091416268800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null