Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499c942ccafd9eb4fc9555ddcac4a52e687e7b77fe891dc4e25f37136678acee
+oid sha256:7c75176a5f65d7310d1585911c2db9cdf8b64abe533e068ad63240600e2edbae
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcca118a9a69cf39b3f0f9a944075862e3af9530ccdfe6ab3c927370b2d199c1
+oid sha256:b954a25e8da86ffafe1fa1ca5112c5e2a341a36a5c3ab5ff5d878020c868b09a
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c101bb52e4f809de6487fd71b71482099d5184955d481f2aa26d4c99dfba27
+oid sha256:235e2b274e45cb42011531c413e588ab273642c45a34eacf5c891a9e9fb91087
 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": 0.003236536905511103,
+  "epoch": 0.003596152117234559,
   "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": 6.035,
       "eval_steps_per_second": 3.02,
       "step": 9
+    },
+    {
+      "epoch": 0.003596152117234559,
+      "grad_norm": 3.328113317489624,
+      "learning_rate": 0.0002,
+      "loss": 10.3796,
+      "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": 2849583755427840.0,
+  "total_flos": 3166204172697600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null