Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ecafc2d1b4e9e2c606e3052f35c69009a2eb706cbf1de2e4e99dc52de4e6ad
+oid sha256:7828c0801be1edde3ce1af18c01090a8fe006c3b71fcd7c864e1bb27f4d11d91
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5335c7aac9050a345c4afa63d40f90deb9999fe6511659cefbfe43b5dca863
+oid sha256:158c69d76b6266095b3b4ee13b7d361e97babc421b56d218092c56ea1c73fe47
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
+oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
 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": 0.0003495349243645261,
+  "epoch": 0.0003883721381828068,
   "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": 185.173,
       "eval_steps_per_second": 92.587,
       "step": 9
+    },
+    {
+      "epoch": 0.0003883721381828068,
+      "grad_norm": 0.07338559627532959,
+      "learning_rate": 0.0002,
+      "loss": 10.3845,
+      "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": 116378173440.0,
+  "total_flos": 129309081600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null