Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:293f00987975e9f8d7139b552a8bbd9f48e6ef9b7cec2779dd5df4d1e827f9db
+oid sha256:7ce36c5d8ede19d1ab2cfe8489c1908ce8606c7d32648bd7b55a2676247d1448
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b80bac010b1143c0efe9b5df41089dacc17da4f3423fca7dd84c08c0630d3b
+oid sha256:32f49241d68766aabbb8428bd29166fd0711c9f600d9a3d103ae9acae1e463ce
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e29f9713a065a74a2801021e806b28fad70505ccf74d9acb846b6c7f8d981e
+oid sha256:590f5ba26b18aa501b480fcf1ffece194294db4678e04a54256a212c4bf79f73
 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": 0.000384204909284952,
+  "epoch": 0.00042689434364994664,
   "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": 0.00042689434364994664,
+      "grad_norm": 0.202046200633049,
+      "learning_rate": 0.0002,
+      "loss": 0.4599,
+      "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": 358108769550336.0,
+  "total_flos": 390082766831616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null