Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5574b8b779893f55727b832ffb472da68c853ae52580a806a5ee13e840ab7e63
+oid sha256:0a47c00c92de6fe85c26ea75972f4cf342ef3feafd3f4ecab8d256880fbb61b3
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72bf240c3c602fe5cd97fb48d89a204031a490c803dbc3bc20691a42d656087d
+oid sha256:cd92d0202d251ec954369b88e8a15ef8b55bca87e5c3d6244f345bde9480dba7
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b516ee8f10ceccfbca5101eaa83b15aeaaf0d99aae9917e9c1ed5d270eb8c37f
+oid sha256:5ecbc91a0af9de02cc759e822266269d602c7670b0237cd904b92ebe72d844f1
 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": 0.0005143151037202125,
+  "epoch": 0.0005714612263557917,
   "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": 11.577,
       "eval_steps_per_second": 5.788,
       "step": 9
+    },
+    {
+      "epoch": 0.0005714612263557917,
+      "grad_norm": 38.98322677612305,
+      "learning_rate": 0.0002,
+      "loss": 5.961,
+      "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": 3642998670753792.0,
+  "total_flos": 4053477394219008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null