Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788c7c8325ec156d6cbde0adb99e5371e6abee7a0a1762916bb2c0e9ad075594
+oid sha256:59dc3b090684250e806769a499e03464c03f4c25fa7282788a2f512df7d647ce
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c1fcb2ce8967d87929f45f7e18f8bb91aa5b64d5d2269a83e2c301720973da
+oid sha256:ad9227d512f7ee2416913db0de0ea430c9066694d5681164a4b9825fc154c201
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f264557876b0b2e68e5761add128bef052298e6e1d88ca0dea4af6b9971bea2
+oid sha256:49af7c9df4cf3f8ebc8ca340dfcaca39304bdad635095a13f46bc2d83975b2f1
 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": 0.0004045898470425606,
+  "epoch": 0.000449544274491734,
   "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": 103.323,
       "eval_steps_per_second": 51.667,
       "step": 9
+    },
+    {
+      "epoch": 0.000449544274491734,
+      "grad_norm": 3.5051205158233643,
+      "learning_rate": 0.0002,
+      "loss": 5.9622,
+      "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": 314114379350016.0,
+  "total_flos": 347769491423232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null