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:d64a8f10aeddd8db4e420d1aa6c4f88d4d1a2903d7fbd337a132af8aac3084cd
+oid sha256:629960ba963d8368f53b3c9c86648178c4e13d00373576f97ba090bd1d89b842
 size 124756544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbf71e6d36097b002ff0303edbd91d5fdf3cef07e6c903c0b5393f0068faf94
+oid sha256:f189acc7a432a0109736b473889496fc25914649b4d7dfee43722b91bc9fcd8a
 size 63958740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dba9286d84416e7d5a19cf385fa24463f4be8dc1077de4409bcaaeb85f0000c
+oid sha256:de261cf14bf471f874635ad43a1b0ee64598628fb26c1befdcf88fd0f8acfbd4
 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": 0.004771371769383698,
+  "epoch": 0.005301524188204109,
   "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": 12.003,
       "eval_steps_per_second": 6.009,
       "step": 9
+    },
+    {
+      "epoch": 0.005301524188204109,
+      "grad_norm": 0.514535665512085,
+      "learning_rate": 0.0002,
+      "loss": 1.1227,
+      "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": 5029561462947840.0,
+  "total_flos": 5689176081039360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null