Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bc98d14f263a9fe3b3d6d5a00c20b8cce3da729ab53bbdee0bc2b68d422780
+oid sha256:b972f4c05147a7248768b26d90a9b57c8113b918bfafc0b84d7cb74ab2b1021e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544289726416487cbd830cba48eef5ca71930be5ec68999ad302d2a6dfb080bc
+oid sha256:8afe5efeab7683eb6fe16ee2f36482702b7bf903fbead03e112b44bd197b78ff
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d6cf770dc5c91beec142044fe54debcca422ff6cb3cf7c5f74a7081f005e7b
+oid sha256:84b4b93b80f2f863f1227b74a2459863279ee895de0abcfd4b5921551e484253
 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": 8.996738682227693e-05,
+  "epoch": 9.996376313586325e-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": 24.355,
       "eval_steps_per_second": 12.178,
       "step": 9
+    },
+    {
+      "epoch": 9.996376313586325e-05,
+      "grad_norm": 0.5714200139045715,
+      "learning_rate": 0.0002,
+      "loss": 0.7475,
+      "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": 2405646792130560.0,
+  "total_flos": 2668080987635712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null