Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd03a5da6d4809e7f0a9d9e6a0e16a257f9ad04be0c487ab044ce38ec7e3666
+oid sha256:75afd6fff82af3bcbeba29c4fc4667b737f70bb900fe028479230269d5a269cc
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4516dfcae819e403c33f6ea4146c9594117c150cbee0c094f8b45a4517055d0b
+oid sha256:92b3eb802423d917f53b08c0d9e148357fcf5c1c013c2da9787d863d3c9e90b2
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09fd6cb9ac2d98795ed909e34d9e0389b57abc4b9dbb733b729cef7ccaaf990b
+oid sha256:24a15f0d52840c1cea507a09f69c1a0f48a12549bffa0560dab871abb1fa6487
 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": 0.022072348252605765,
+  "epoch": 0.024524831391784182,
   "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": 106.677,
       "eval_steps_per_second": 53.339,
       "step": 9
+    },
+    {
+      "epoch": 0.024524831391784182,
+      "grad_norm": 9.887947082519531,
+      "learning_rate": 0.0002,
+      "loss": 8.9486,
+      "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": 38213120950272.0,
+  "total_flos": 42459023278080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null