Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f355ef5d2c35e0bd1d46cfc68af87f1ff7521c858663f090c04c0dfc2a1957
+oid sha256:585b13934547e52daea6068d994fa14bfb64b20f4f6d873790fc4b84fc5e8aa4
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aafa149309bbe7c085a4b0754fd97ecbc2a0886a0fca3f3ba71ec138d6fdaae
+oid sha256:63833b82f3965e1fa14cf9765485ecc34e74ad608ed06cb76bc11ed9af076954
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66f33b1e5b2c0ef27fc599d33982d25847a4ce9cf07845c46b50ef9632d1f27
+oid sha256:aea9f7dd5933a797009671ad3be72edbb764132812c859d1cf32f1a5ad2e397f
 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": 0.0007736112603416783,
+  "epoch": 0.0008595680670463093,
   "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": 81.552,
       "eval_steps_per_second": 40.784,
       "step": 9
+    },
+    {
+      "epoch": 0.0008595680670463093,
+      "grad_norm": 24.619142532348633,
+      "learning_rate": 0.0002,
+      "loss": 11.5977,
+      "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": 268889078366208.0,
+  "total_flos": 298765642629120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null