Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172a2d2df9217845dc5eed7be99b3b1d88c8ad57bb5e4778673af07ba0223edb
+oid sha256:1af171cf8804289546e9817b2c7f6e65cb18724fffeca48114709ca9534b3dbf
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32514f59643a512c840363f4d21054ffbe51751e47eee08d8a865fddb8715b0
+oid sha256:a50598dded007b631c5924a45f03b2d9c1368524ebb9f13fe3bb579d6c5afa4f
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bb659d872e51cdcf51d1386f1d5644386953ebd4919b30d517a420347b48ff
+oid sha256:044b668881824267e820e546f78bf616b04426da94fcebca597f4b032f81ad04
 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": 0.042105263157894736,
+  "epoch": 0.04678362573099415,
   "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": 37.684,
       "eval_steps_per_second": 18.842,
       "step": 9
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 1.040130615234375,
+      "learning_rate": 0.0002,
+      "loss": 0.7316,
+      "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": 475092464173056.0,
+  "total_flos": 525102197243904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null