Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363144cf38251484b629869983ed44f133019678ea2089ea9222edc61d94ea7e
+oid sha256:f36b6df9a16b5803e2a96c5aa01355b1d4ab66063d87b664dc1c85e07d225693
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d2ac61f8efdc286da39761c5e2fc7609d9c7855d885bc1eda79163605a4d9d
+oid sha256:7a91c322820f9ab1862299ea83b9e7b841723c3228f827659a1c8829de835fa5
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7567ae8a1ec33e28c23869de794452faaab4545ecafbc1b4920ceae179c9547
+oid sha256:f34cad3af4891ba4d35d6fef0d4d3a99903a2b740801a9646aa2f6b99de9be9e
 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": 0.0003142759866956499,
+  "epoch": 0.00034919554077294433,
   "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": 16.829,
       "eval_steps_per_second": 16.829,
       "step": 9
+    },
+    {
+      "epoch": 0.00034919554077294433,
+      "grad_norm": 2.771148443222046,
+      "learning_rate": 0.0002,
+      "loss": 1.4844,
+      "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": 324429435371520.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null