Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ca589bf3b9907c272e54dc23ae2abaadd6fb9bf9115546413e690c0a854ef7
+oid sha256:5857956683d74557d0b2c42510d37c5238ccf39d67e8768dde62486780a1082e
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81f45f3451dac302f62435612c9f982265f413125caea8d5d394a9f8fc8e1c97
+oid sha256:9a9699b1a583279757e3043b7cb5c86edd97acace9aac06993ed43b2585e492a
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e430790c418395df8ca73708b8c4c3a500f2ad56804e8db2527f4c5b2ee2f2c1
+oid sha256:d6715e79f938c3772d484e1af1debd21a7398c7ee517a31af38185495f5c63d7
 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": 0.00013320111888939868,
+  "epoch": 0.00014800124321044298,
   "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": 33.787,
       "eval_steps_per_second": 16.893,
       "step": 9
+    },
+    {
+      "epoch": 0.00014800124321044298,
+      "grad_norm": 6.095448017120361,
+      "learning_rate": 0.0002,
+      "loss": 5.2252,
+      "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": 216490963894272.0,
+  "total_flos": 240545515438080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null