Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd913f3a3647753d8b02d7c71d0011daecf4a417e0b54c777c75f2040444788
+oid sha256:326ef1c2b505877314cf7f7e40e5bf682b848f487413c5d12e6dc492aa4a4902
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c734e3a6adcb5ca3140dfa8622bca4293f6da02adc742aa13a108e4d3feaf7
+oid sha256:c259a81a5be43d4f6c90a2a1eb112ac4a43c2ab0cde63033758fa99390ee1947
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a62540b59171433e89b409762ce8a6bf6ed27fcac3f73bdefcaa0e2bfae742d
+oid sha256:c24fefb22ece64cdad3d504b19de27261dc8a3068fc89697813908db1e6de4fe
 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": 0.0028917985380351834,
+  "epoch": 0.0032131094867057595,
   "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": 14.801,
       "eval_steps_per_second": 7.406,
       "step": 9
+    },
+    {
+      "epoch": 0.0032131094867057595,
+      "grad_norm": 2.135014057159424,
+      "learning_rate": 0.0002,
+      "loss": 2.0774,
+      "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": 3561979694284800.0,
+  "total_flos": 3957755215872000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null