Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a0b766abb5175cd30070c859be2b9bc6f8b5b4e59602dcd6f1a6e3bbeef46f
+oid sha256:b842935199fe543c72a1eae8bb9fa697fa7d7a13ccb99d56d58b320a268669a3
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e3b4d9b0ddc6b365a94978a107692a9309e745cb5b1110b56ff1f602f36d74
+oid sha256:81bd5a5fdad82b14c308f193a4a67ec78093c7a0c76f81e8099ab0a5890f6489
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a5a857ed41b50df491280680008400b63a0cea9bbaf95bf767f775a18248db
+oid sha256:580a78039b006147c49fed961f84593aff50f8571d4e98d9723902082cb2076d
 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": 0.009242618741976894,
+  "epoch": 0.010269576379974325,
   "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": 96.842,
       "eval_steps_per_second": 48.421,
       "step": 9
+    },
+    {
+      "epoch": 0.010269576379974325,
+      "grad_norm": 6.152303218841553,
+      "learning_rate": 0.0002,
+      "loss": 10.3044,
+      "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": 590026899456.0,
+  "total_flos": 655585443840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null