Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd94b64c749938cedc6d49fb203ac7caaee63e31868e4a29f2dca3f4aac4761
+oid sha256:66df58c9e5b45675fb705a6dbf7e14562718a0d26b7119a84ee23136216ac573
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb76d22306bca6213d18559edc432e03b188a24f3ede4dd5138de2e2d22e5c2
+oid sha256:dfb44276777c1669589cbe6627155b854b71d6cdc61d4ba671594f08c647bb3e
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b002e4c9be3408966e80316809a5beca5538b31ac9988922de1a1dbee77b184
+oid sha256:9aa5c3da712b10227cdd51fd19dc753de2275e10dbe876ecd817d1589e4a99d8
 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": 0.001113379105585452,
+  "epoch": 0.0012370878950949465,
   "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": 55.33,
       "eval_steps_per_second": 27.665,
       "step": 9
+    },
+    {
+      "epoch": 0.0012370878950949465,
+      "grad_norm": 1.4655866622924805,
+      "learning_rate": 0.0002,
+      "loss": 2.5086,
+      "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": 537778156732416.0,
+  "total_flos": 597531285258240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null