Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75911dd042b0427dee24dcb9321c7b50b5ce9356cf31fb08e109efa4101a1f2f
+oid sha256:3c02d967b0763481fff7dfbc473abbae7ee4377ef6e7d27c75eb2c97957be96d
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f809699b39576aa332a27d83711ee2d4ed777683b4f521f19df7137dd6d3dce
+oid sha256:568613bfd6f2201bf68636864bcc0ac3e268e4387922b9b2e8210e1857946ac7
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d46b6ef7ca2c27dbd6779326446a3edbfe63f588b2738801236c0928f47f3c1
+oid sha256:2ccc130877759bb0810f92b4124bff00525f0b084f97190b1328e4c2c6ce5e94
 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": 0.014748054076198279,
+  "epoch": 0.01638672675133142,
   "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": 3.261,
       "eval_steps_per_second": 1.637,
       "step": 9
+    },
+    {
+      "epoch": 0.01638672675133142,
+      "grad_norm": 1.7251274585723877,
+      "learning_rate": 0.0002,
+      "loss": 1.6624,
+      "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": 1741900625215488.0,
+  "total_flos": 1935445139128320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null