Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ec54c60773a764d5465f9fea421e4da459e8c8c2d9948f7544e21229cbf924
+oid sha256:6d4bc2d972e4028b4243693e501899733167396008fd0e03777e1c50e246b005
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3225c651180dc4c9b22485a13d425d3caaa78282678d622863b642c8e9b85a3
+oid sha256:ca0bfab0d929200466ad1cba51c2c7ee899f285eb11a9be7c745dd63751580be
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23d8c54930bcfa400a42faf2dd8310c9fa2fc3255471da30515ca920d46e8eb
+oid sha256:d9f374fe33a833157bc0fe68f1a61502c8d1b0351ef41041f615d672f76ffaab
 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": 0.0005811138014527845,
+  "epoch": 0.000645682001614205,
   "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": 6.436,
       "eval_steps_per_second": 3.218,
       "step": 9
+    },
+    {
+      "epoch": 0.000645682001614205,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0002,
+      "loss": 2.6989,
+      "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": 1852863789662208.0,
+  "total_flos": 2058737544069120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null