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:cc314d6126061e518e64b0148120b9c1e455b46f95ec79cb3baea196d4ea998d
+oid sha256:c2d82c583173e76bb544f7777f0437d47eee97f5ccc2191d759bee55cbce7ff8
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed174b27fe4bb29daf3e1d343737471f477e67f2920c20a74baf3f1153c56f3f
+oid sha256:411b1fce49d99cebe9d8140e8a7e476a3d26d905b2f3f16f0461c6a6deb34a96
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c06efc10773599d893a1e104eed47d27bc8f0e7295971358509d202ad2e084
+oid sha256:85452346cdefc6d074f6e7139e2f661389b447a23cb0762ed2662b5abaf38690
 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": 0.00307771223390613,
+  "epoch": 0.0034196802598956996,
   "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": 35.044,
       "eval_steps_per_second": 17.522,
       "step": 9
+    },
+    {
+      "epoch": 0.0034196802598956996,
+      "grad_norm": 0.12862572073936462,
+      "learning_rate": 0.0002,
+      "loss": 1.1519,
+      "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": 326134772269056.0,
+  "total_flos": 364503569006592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null