Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a81979bb326122ed67f37de24ac5353732bbca127eb76224e346002a66d96dc
+oid sha256:08c547a2a0ae73505419c1315313948e46ba5757465db6da6f633033e035f7d7
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31608b97ffd5f5c6c10b7511e262dc0783ded483abeeeffdee67fd92443f66e9
+oid sha256:b4fa90fb8d06fc9a824e8d2a37f909580a32dd0a56d5db93e3a1ff7b6ef00a68
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b020b021da6db34f0bdc2798b38574178b103b70a0dd6fc7add3933179026d
+oid sha256:d5ede5e246826bb185fe31bbf4bd02cabc96099050433bd4ca27c6f953f8d602
 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": 7.58915678143861e-05,
+  "epoch": 8.432396423820676e-05,
   "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": 7.22,
       "eval_steps_per_second": 3.61,
       "step": 9
+    },
+    {
+      "epoch": 8.432396423820676e-05,
+      "grad_norm": 0.3528674244880676,
+      "learning_rate": 0.0002,
+      "loss": 0.9766,
+      "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": 1127566914355200.0,
+  "total_flos": 1230072997478400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null