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:cd2cbfe6873e227853eaed17e372f8ee66a3a9119ecfe3c6ed15d5be8af0d3d3
+oid sha256:8419bd6eb8fdc0110ee56492bdc3db4b3e3bdcb0b8383319f2b8d798cd8bf394
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65257cd4227e57a0ca74aae459aeecc4d0bf49c52ff3c81620529741bbaf7fee
+oid sha256:24f3d0c625477813657ffd63c7289403d57cf9326ad2ae547896346cf5985d74
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89b3b1038011c19b79beb88e553b6515735c6afc0a8600325b75de7187c9820
+oid sha256:cd174834410a5cd0458d2bd83363b3f9b502a6620339122bfa5a56ca57c30614
 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": 0.02706766917293233,
+  "epoch": 0.03007518796992481,
   "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": 31.455,
       "eval_steps_per_second": 15.728,
       "step": 9
+    },
+    {
+      "epoch": 0.03007518796992481,
+      "grad_norm": 1.9218229055404663,
+      "learning_rate": 0.0002,
+      "loss": 2.1572,
+      "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": 450087597637632.0,
+  "total_flos": 500097330708480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null