Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767091f0e9f773e87e72d9e50e96723d819787fd607eae2cd9cf5b9a391ada06
+oid sha256:74398bd4f40fb9925b74773d5c290b79b9aabd3c86b36d32055f700dec3a0888
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a796ff184b26aa6a13aa3c1204c503552eee1940d16182eca180f571c5ef48
+oid sha256:0c4cd920eb17055e0b5d122d24927c3e23e77893a11687722ed8b5b907bf5aa7
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542392e3213e4489396b825863b3f4f2e478a06bd117d8c0415eec21839c65a4
+oid sha256:7d92f409c180d2c710612d3a304b5c3de0e3b702fdcb3cc87a2bcdb78457bd37
 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": 0.000745141059342206,
+  "epoch": 0.000827934510380229,
   "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": 9.175,
       "eval_steps_per_second": 4.588,
       "step": 9
+    },
+    {
+      "epoch": 0.000827934510380229,
+      "grad_norm": 4.991492748260498,
+      "learning_rate": 0.0002,
+      "loss": 1.1139,
+      "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": 4353558419865600.0,
+  "total_flos": 4670180850401280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null