Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a659f1b7a7bb5bffed4195828fea71881a51cf4a4aab99339eb043f7ab19730
+oid sha256:c8e552dc2c7f5fe0fbb918ed0170fe10d98b27e2b00b65d30993ff62cd699d48
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196c11170d7cd42863c2e47150868f1c407d945b0dc5a1edd6c9c07090a8907f
+oid sha256:fe01f4af3d47cd1b72eaa20a8b8745cf6ad437cbbfa7cf284f66ed93fa1c637b
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0220ebf3414f9dfe76a7ef242f02d9b694cdf9392096eeea27065cd9eace6c04
+oid sha256:df57d6841e8ddbcad8278fb4cf52def3f65baee8e3f17bdf8e641207eec0ed31
 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": 0.0008540722640032265,
+  "epoch": 0.0009489691822258072,
   "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": 10.617,
       "eval_steps_per_second": 5.31,
       "step": 9
+    },
+    {
+      "epoch": 0.0009489691822258072,
+      "grad_norm": 0.008199266158044338,
+      "learning_rate": 0.0002,
+      "loss": 12.461,
+      "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": 11098128384.0,
+  "total_flos": 12331253760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null