Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7228aad5cf88c91f72f6c4c8be9a1fd949a4e4a03f11e1253ed957a6d4bd69f1
+oid sha256:cd3cecf1a2ea99a6f0df030e6aa59d2f7fee69a6197dbda612887cf95f999399
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18faf23103458d173e46410706d233b2a8ffc5e6e0dc792de41f6295f5b1ab0d
+oid sha256:fbdc31a493459939a4bb4dd9fda3dc92bda4945e230ecffcee40c04ff2dcfa3e
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb79989f0b6ef3fd37f867a5b814d6aca11d21de163825e3e0b00f3a404b965
+oid sha256:0064abddf0cde94e55b4a018a307a3998e7b06f076da5b984d950e6478296ff0
 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

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004557712028561662,
+  "epoch": 0.0005064124476179625,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,13 @@
       "eval_samples_per_second": 6.672,
       "eval_steps_per_second": 3.336,
       "step": 9
+    },
+    {
+      "epoch": 0.0005064124476179625,
+      "grad_norm": 0.7870314717292786,
+      "learning_rate": 0.00018,
+      "loss": 3.0758,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -117,12 +124,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2567524822548480.0,
+  "total_flos": 2852805358387200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null