Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a0245329389413087635f731bd5595279a2bc72d02b293b25f79b7ca4242d14
+oid sha256:2ad9ef0b33e388c45891e247caf5b69a9a5c09e58277589bd4f669b0bf45050b
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55111eaf928039085d581324bc1f66749c4dbc73d2ccb772f8cc8199ec67cd3
+oid sha256:68f84d026aec9221155564b547fd3f8b057d6fd633fb292c1c396dd1aec97d5e
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aab7eab66f1882b6e84399d84b8de667bd5cc56d488036b16665904da7aecfa
+oid sha256:f1a19754d2d8f111cb6890235f322d2a92de9841b0c5d172ef1f5ef75e7ff15f
 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": 0.009793253536452665,
+  "epoch": 0.01088139281828074,
   "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": 18.528,
       "eval_steps_per_second": 9.288,
       "step": 9
+    },
+    {
+      "epoch": 0.01088139281828074,
+      "grad_norm": 0.17300285398960114,
+      "learning_rate": 0.0002,
+      "loss": 0.1476,
+      "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": 1394082730475520.0,
+  "total_flos": 1558092463472640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null