Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd444f845ed248eb96f0fa3e6ee81eee2d6d692489e5672cb209815d555012a
+oid sha256:ec75d357cde5567704b791994fad0e1a3eb1a8391dfa19116e8cb2431baf2259
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba32eb26aaa1ccb646bc51624067da3ecbb99d18c52206f0c0da5a238fb25d73
+oid sha256:6a06cc922a6a80a6d4f89dc0cf773bba228e9a6e8c18ad907e76fa2159052acc
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da371ed384dd48ba3f51b4afee7d61db3dfdb18617828b0330774642ccc5f0e8
+oid sha256:aac52a5fbf7563a7bcb3d6eef192e260910b8c56eef104747fc841eca3de59f3
 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": 0.003788676068196169,
+  "epoch": 0.004209640075773522,
   "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": 6.624,
       "eval_steps_per_second": 3.315,
       "step": 9
+    },
+    {
+      "epoch": 0.004209640075773522,
+      "grad_norm": 1.5563174774308864e+19,
+      "learning_rate": 0.0002,
+      "loss": 1.6918,
+      "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": 1852863789662208.0,
+  "total_flos": 2058737544069120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null