Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b97ac5ebef64bd50840c2ffa86b792ae28cb985a21b7ecded20513ae724768
+oid sha256:22625156e33d77836a441f869ae0f66ead539be00753923bc42c3f20278d1277
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2807781351b0d0fc8e02a04076ccfdd74f3b6876e9780ed49ba5454f43c3a80
+oid sha256:3ae06a8046de07116d217583971c60da35928a5b2a8841492a40223da2859f2b
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a81cc94bb9784a99b66a3847a12e5edc941dafcbd050831d68c21b46d0ac7a
+oid sha256:2343ae5ff828c34e3305a42016ad344256fbf938ac207504145e5fbdf0daff67
 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": 0.024324324324324326,
+  "epoch": 0.02702702702702703,
   "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": 3.237,
       "eval_steps_per_second": 3.237,
       "step": 9
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 0.26503047347068787,
+      "learning_rate": 0.0002,
+      "loss": 2.1022,
+      "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": 3098020115644416.0,
+  "total_flos": 3467932965273600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null