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:a421b7b84866b0fbcd4ab086174ae25b76fe154a2efd9c173230a9007c5fa725
+oid sha256:de75fbc145d113d93c661dbeedac9025714cd6ac26eb3b69791702c3b1580c3e
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c23c4f35e3887cf2a57fff6630040917861544fdc59c4904654ba03c9f689e6
+oid sha256:6e4285d3ff867c40d14c933121bdedddd7cedd02d21867a9363a63a3e049f47e
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3253e1657e0e5e1dce4606e0080d6574b33a3e708581e44bc5526ab5260da9
+oid sha256:46a26cffb30d94dfb85a910a3e3a744db87392e329b9566998aa7724bb44f185
 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": 0.004257835600236547,
+  "epoch": 0.004730928444707274,
   "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": 20.371,
       "eval_steps_per_second": 10.185,
       "step": 9
+    },
+    {
+      "epoch": 0.004730928444707274,
+      "grad_norm": 4.384667873382568,
+      "learning_rate": 0.0002,
+      "loss": 2.3632,
+      "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": 1847154255593472.0,
+  "total_flos": 2052393617326080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null