Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782caf14db274fa1d450055398a2100f5df25ad368b15ef071ab2dbc9a9b4cc8
+oid sha256:121bbb2c13d701f42625ad0c6de2eefea30223fc36c4d81a25e3cf6092107d3c
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f31c9c8bc0c1404d6d702a0727adb0ff7663f28bcc306f277f888c62afafabc
+oid sha256:537b2686d206a5dd57a55f2cd7c47bb4fed16414db974f786837388376d4a57e
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
+oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
 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": 0.000781725006514375,
+  "epoch": 0.0008685833405715278,
   "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": 80.724,
       "eval_steps_per_second": 40.362,
       "step": 9
+    },
+    {
+      "epoch": 0.0008685833405715278,
+      "grad_norm": 8.082724571228027,
+      "learning_rate": 0.0002,
+      "loss": 18.937,
+      "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": 67562687692800.0,
+  "total_flos": 75069652992000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null