Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b638f9214b8161aba38bc4e5bf8beb08d045a939e9f75f34f61387c74601c84
+oid sha256:451ad039b3a0cc6e7c2b2b32516602225252b157439beba0dffd8bffa6ea0560
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d2c18317e21291d3b33251a3af808ca35659bb5ea8f5922c0fa99056c124cc
+oid sha256:3a7f3ccb0bccc33c0a63c16e74466867be71d6055878eb2cf605d70cd19773c3
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287ecd53a1d24297ce2f39c80b9d4d5380a3ef651a2a854cd0e76d3d6c05c66d
+oid sha256:4e6c4200ccca10ea8b6f9434b5519b04298a5a50059ad9d30023dc92d017a866
 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": 0.02708803611738149,
+  "epoch": 0.030097817908201655,
   "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": 37.03,
       "eval_steps_per_second": 18.515,
       "step": 9
+    },
+    {
+      "epoch": 0.030097817908201655,
+      "grad_norm": 0.26784640550613403,
+      "learning_rate": 0.0002,
+      "loss": 0.9529,
+      "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": 583736865325056.0,
+  "total_flos": 648596517027840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null