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:daa9c02ef7fb7f23f3dedb775d918d3f63767389ae1f3cafcca734f6949e076e
+oid sha256:d703fab8dc642d4cbb747c4341251c9ad5c94b2b7d56325c98b2dda1c6454b59
 size 51431872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57fc41d9a1e9d22b661f617dc4e95f842e688fd619768a654e1e656e5ac415cb
+oid sha256:ae189ad7a96f039dae1188251ca6dadb2386d430d002f0709729b7db714cb90b
 size 26550260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef6539bd42c0dce152efffa7664d58b831bb7ebc921fb94bd7cee48d50104952
+oid sha256:beafd21bc81e4c3ee9888f866cd2bd17e4871ab705091760fb1fa36c31f0c349
 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": 0.0018302913213686513,
+  "epoch": 0.002033657023742946,
   "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": 39.783,
       "eval_steps_per_second": 19.901,
       "step": 9
+    },
+    {
+      "epoch": 0.002033657023742946,
+      "grad_norm": 2.2048258781433105,
+      "learning_rate": 0.0002,
+      "loss": 1.4054,
+      "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": 684748858982400.0,
+  "total_flos": 760832065536000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null