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:fbdd66b36aaafb37ee4f440f72d2913fef40b2bf5619afee24caa1d16b8a57e3
+oid sha256:5f30ab22422d4a7ce09f04657482a3bb63ebf6aa163c84032e8b662cb3da4033
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0f300638e545c9b37c84bdd087732f7874e83d9c5469e2ea4faa10bd332fd2
+oid sha256:95dad1fc3cdf1e2172ff3090c5abedfa5bd206bb80ffbc544e224d22bce73f71
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cde9ca23dfe033d10028cbe0dd91dfa734d0be4761346f37da51e83a1e32cda
+oid sha256:5bcc9dec470456049b85d58761d8b1cb7c00e042c845ac37d7d42f59480fe0bd
 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": 0.001107487848397219,
+  "epoch": 0.0012305420537746877,
   "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": 26.72,
       "eval_steps_per_second": 13.36,
       "step": 9
+    },
+    {
+      "epoch": 0.0012305420537746877,
+      "grad_norm": 1.437125563621521,
+      "learning_rate": 0.0002,
+      "loss": 0.1699,
+      "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": 2173237991571456.0,
+  "total_flos": 2358194416386048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null