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:e0afcbb45190929647e30a0679643ba239b6b9d4010e0c171135f1651be6ce2f
+oid sha256:f5c2db81fab040db4eddcafc202aca07973e5716f10ff9713637c21f87213314
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86b8ffbf9707e0928db1c75e6a92d457d049e54e0ce7a6494e231f73bf52ea0
+oid sha256:4c9b067455a92588942f1f886be96505aa5fb34298e6eb205abb65e65b81bc23
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b706875855f2be5f34e8de6609fc6e1b16fd875f08c9910f48619db8c936bf46
+oid sha256:f299d7d715a9da57119827362cd20a3ee73249d6a1cc12c0e77d7674bfec06b3
 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": 0.000188197900547865,
+  "epoch": 0.00020910877838651668,
   "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": 30.232,
       "eval_steps_per_second": 15.116,
       "step": 9
+    },
+    {
+      "epoch": 0.00020910877838651668,
+      "grad_norm": 18.652639389038086,
+      "learning_rate": 0.0002,
+      "loss": 3.1872,
+      "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": 1708853041299456.0,
+  "total_flos": 1884120019894272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null