Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9175322bc6867ab876e379996f998151d5bdd150b530aa315433d589b147412a
+oid sha256:8a98dc61c78f1f2b59df2fb978ecdcdcaef0808a51efec87317f16c11896f866
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a6734ac33c3dbfca7663369d547c070e14b58427764d736ec1b1c353386236
+oid sha256:03fc9b281d2c8992ebd459ca721186e8d782d786aa1df663fb9922c173e16aab
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97515219b64565278ca5b2eaf900697e87a3099f561176e685a51985c0152cae
+oid sha256:c9c2be43e1c25fa3a1735c8fb968b77a19d319e27f44dcde02befc966a56b19f
 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": 0.001366535074400243,
+  "epoch": 0.0015183723048891589,
   "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": 26.142,
       "eval_steps_per_second": 13.071,
       "step": 9
+    },
+    {
+      "epoch": 0.0015183723048891589,
+      "grad_norm": 2.5859363079071045,
+      "learning_rate": 0.0002,
+      "loss": 4.4639,
+      "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": 2902025746513920.0,
+  "total_flos": 3215758259650560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null