Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e629d17a7b304d74947a8ebceb41d989d29082fbfe6ddbff8e66b98ccaaf34a
+oid sha256:47f91a3b530ba97b92a108fb7b13e1e6b147945ea2d0b1354d19191038a4b005
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa3ec49ecefbef5ec314f7b52bfa6d422a71a06691475d5f321d454c0cee4570
+oid sha256:66d1d6163ca8258e76f2f4e1888c7967f7308bb38087ef3e1f64ab9da35d4d2f
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c794a47edc9435384cbc7bbda79d6455642ccecbb17e631e8dfd483567816013
+oid sha256:aab86dd95a356f1542dbcd0bf2738b6f7c908ceaab868ac8fbc768a1bbc33c9c
 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": 0.0003112356053532524,
+  "epoch": 0.00034581733928139156,
   "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": 19.439,
       "eval_steps_per_second": 9.719,
       "step": 9
+    },
+    {
+      "epoch": 0.00034581733928139156,
+      "grad_norm": 0.18487077951431274,
+      "learning_rate": 0.0002,
+      "loss": 0.4807,
+      "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": 2931719644643328.0,
+  "total_flos": 3257466271825920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null