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:f9ab71f6aabfbf8c6ff6bde370de03471039f6bc9a6893fb6e94f79e7c749b8b
+oid sha256:cdde3a22b1568152b68860753f702142808588653095024ec1f237e949a1abf4
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629cdfbe44cf8ff7b378e1a89fcb51a5335e410f4a32f3b82a4d211b3f41d71f
+oid sha256:0496ad6b0652bf3d4f39c9700ed850e7c8ddfce4a336af7e624ad627d7e1f7f2
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446f86ec2d710de4e25bb65aa3702d3d6d34aaf5102619f692e1fb433a8cb9a7
+oid sha256:bf196c982a99d97fa9a8f9e373dc1cebd41e956f613251cd97f2727479322c66
 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": 0.08314087759815242,
+  "epoch": 0.09237875288683603,
   "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": 36.267,
       "eval_steps_per_second": 18.134,
       "step": 9
+    },
+    {
+      "epoch": 0.09237875288683603,
+      "grad_norm": 2.517549753189087,
+      "learning_rate": 0.0002,
+      "loss": 2.4696,
+      "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": 462590030905344.0,
+  "total_flos": 512599763976192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null