Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a6c117fcebc346afcaab4d0322082fc1877b4c08589df490df20c4d109b85f
+oid sha256:24e1cfa0796413f2a20b1210cfa55afe839243998236520eae9b5a9839e79827
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b61fdd74363c24badeaedb8f79ae3a9f217324b92e1ac4884cde3443d56c8e3c
+oid sha256:458b976a9e6917c92fe095a8af68cd9eae669c805ab7b11a161dabeaa0a6026b
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44f3accc9718d33f1cfd01495b3b3e230de6a63835cc6d9d5c4dfcf7e6902d7
+oid sha256:34f94f93946fa70219dc57feec9df7e95a95c8ba1ad9793d5f7b1e15e7abf140
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
+oid sha256:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035283356930748896,
+  "epoch": 0.036085251406447735,
   "eval_steps": 8,
-  "global_step": 88,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -306,6 +306,13 @@
       "eval_samples_per_second": 8.71,
       "eval_steps_per_second": 4.355,
       "step": 88
+    },
+    {
+      "epoch": 0.036085251406447735,
+      "grad_norm": 0.2886866629123688,
+      "learning_rate": 0.0,
+      "loss": 0.7468,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -320,12 +327,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.378735360106824e+17,
+  "total_flos": 5.498097032453161e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null