Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218c9daac938214cd843ccdfecf57b3fe165d9e543ac1f905c55d1767fc33921
+oid sha256:41e8904c9788ea6fd2059a3166397a3af87759355b4d3edb0ecc5af412efb0dd
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92204a79f589c00460b38537a7e5732a71e81b487a2fec1fbb8d83c4d2b511e7
+oid sha256:57bccf63b007147ea09ea01039e3c9c753b0b66ce888cffbcfa55455aef6e671
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23577b175b24b0fdde80f49011165773c0809072b02d6ab6a7a9a4c4ac0b3faf
+oid sha256:3a325212b44b5ebaee8992af1440367106354501c210249b130d74ab9a6fae7d
 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": 0.001463057790782736,
+  "epoch": 0.0016256197675363732,
   "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": 123.497,
       "eval_steps_per_second": 61.772,
       "step": 9
+    },
+    {
+      "epoch": 0.0016256197675363732,
+      "grad_norm": 0.5640869140625,
+      "learning_rate": 0.0002,
+      "loss": 2.544,
+      "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": 50581659451392.0,
+  "total_flos": 56582873284608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null