Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c48021eb278551ecbcda136b7761c33b86001ee8ed591c4aeed340ce193c2e
+oid sha256:0fb81b246398bc782f2eefa4868560e65b1577df30ace7550be22d24999f5645
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:341a3978de80dd85c3ac7433ddd0566b20e6d22ce1d87cf96269676403d6945d
+oid sha256:7c4302d91626e8f7c9083c78914677113aa75435642b731fd9dab79d4a9c60cf
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c82605a01ce7f2425dfa398cab2f93bde1f3b9bfd9a3df554d9fc68721cd00b3
+oid sha256:8b17726bf4924e2e3669e973dbbdd33c2cca6c199fefe136519cdc6a63dcd906
 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": 0.0002979836440088733,
+  "epoch": 0.000331092937787637,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 11.353,
       "eval_steps_per_second": 5.677,
       "step": 9
+    },
+    {
+      "epoch": 0.000331092937787637,
+      "grad_norm": 2.8212287425994873,
+      "learning_rate": 0.0002,
+      "loss": 2.9612,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 452766958878720.0,
+  "total_flos": 501714738216960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null