Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b19177125d28ed5fd93477ac1adaccaa6b094a99d38e75a7bb40d97b8dcc2f9
+oid sha256:ffc4ca3235a2f9ded6aaec26e0dc6fad123a2d7fb6b4d00e53375a581baad38c
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0122bd14526ba8816be64a2e3b32087388d63f4c68549a4a663243d2a8a6336e
+oid sha256:cb004d6f3b0d5275aa2b737a13e0d5d2dc14acf0014b12a356f81f04c9491ea1
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc527ae92339ea167c2945496cfde8562215165c21050204ee36547f80f22391
+oid sha256:eab0aa09bbb2059eef409050846e568360b5b777e22dcbcc22066ef429c07f97
 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": 0.002639876805749065,
+  "epoch": 0.0029331964508322946,
   "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": 36.894,
       "eval_steps_per_second": 18.447,
       "step": 9
+    },
+    {
+      "epoch": 0.0029331964508322946,
+      "grad_norm": 0.805048942565918,
+      "learning_rate": 0.0002,
+      "loss": 1.3546,
+      "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": 450087597637632.0,
+  "total_flos": 500097330708480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null