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:d5622eb52859b0d4101e82f0f9a26c5abec4ad32fc60124e72a4dc02960df434
+oid sha256:4702f46748ea15a3b69007d04f15f886db4ed64074ba8b7aa34333e40089bbc8
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6c518bb255fe60720133c817f8e71b3035c2b4c397f9319986b320b8c860aa
+oid sha256:c9d649326e5d9b409b6e34e21a81dff48b760bf2be90c991d24dadf04abb9944
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971b3c8cf853f22869b90ddddf63ef0566b6ceb377f3b57b66478e5d06e3e51b
+oid sha256:b3df234e5aaf8c4946e213550320cfa641d06d78d6188e95560495eed9123ce4
 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": 0.004611246317407455,
+  "epoch": 0.0051236070193416165,
   "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": 4.577,
       "eval_steps_per_second": 4.577,
       "step": 9
+    },
+    {
+      "epoch": 0.0051236070193416165,
+      "grad_norm": 1.1007012128829956,
+      "learning_rate": 0.0002,
+      "loss": 0.8434,
+      "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": 6291348239941632.0,
+  "total_flos": 6990386933268480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null