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:da9b87884f5fb0cb262f6510b6199e17f7cef5a0043020e0b3c933cc0235c171
+oid sha256:8c6fad2ead24f11ad2560978142c742890b1df400b9f72c454cfc4dbb473b6da
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d330358b2f48cedf843c05ac7838c90b556839f07bd786cb9651b090a8bf7a9
+oid sha256:76ba9967d8b9a2d3d337d80c82b511047a424909e664f7b172a761ed496e86fe
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb25bc1a471011a6b99c092a09c80d8f1cf3057a62b43a3babae7089834c3bbc
+oid sha256:2fa0bebaaa4e47d35f7f2095d8acf5cf51d0bfd2df3c24da002fe7b0f8a446d1
 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": 0.005491153142159854,
+  "epoch": 0.006101281269066504,
   "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": 41.419,
       "eval_steps_per_second": 20.74,
       "step": 9
+    },
+    {
+      "epoch": 0.006101281269066504,
+      "grad_norm": 1.3870753049850464,
+      "learning_rate": 0.0002,
+      "loss": 5.3684,
+      "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": 291868432662528.0,
+  "total_flos": 324298258513920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null