Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260ff4eacc1fb8454c181b1ad210b503af0f2f12667389db1ae0fcbd92172408
+oid sha256:aa145b3a8c478d44e3cf1214e5534497dc50da6e52cb8dbb0762a48b0037dd81
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83737ee32edadbcce3f276aea492bdb04b2ef6ddbceb9538e468174bd95eb9cf
+oid sha256:6fa6e64d25aea27735911d11e789a3c010f3203e2d6f3a96dce4616154684e24
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
+oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
 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": 0.023936170212765957,
+  "epoch": 0.026595744680851064,
   "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": 321.186,
       "eval_steps_per_second": 161.603,
       "step": 9
+    },
+    {
+      "epoch": 0.026595744680851064,
+      "grad_norm": 0.06460735946893692,
+      "learning_rate": 0.0002,
+      "loss": 10.3791,
+      "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": 177799987200.0,
+  "total_flos": 193963622400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null