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:bc419c589901224a30a7105d858aae62550abef02026bf4c986743206d549c73
+oid sha256:1b71588175761c0452a3c3d0f8d77b4e79e1ff68394a45e810bb8e76b437f1dd
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4c80ed4a5adb35e1f7bb831d93cffaa9397e9af6762394fed31207ce19effc
+oid sha256:a9379177df4f8dff47329e2625730c9950f0055535f55974bb9edfe527ccacda
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee20c2c505fab0536a0ec11d207ab1b18ac24ed0491c671a58d742747220d84
+oid sha256:ae5811829ac84a7bea61f0066227367c1bdc6c720b4b6ec768e66c7c6382cb4f
 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": 0.00014433138485963774,
+  "epoch": 0.00016036820539959748,
   "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": 118.365,
       "eval_steps_per_second": 59.183,
       "step": 9
+    },
+    {
+      "epoch": 0.00016036820539959748,
+      "grad_norm": 0.9210301637649536,
+      "learning_rate": 0.0002,
+      "loss": 4.7986,
+      "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": 30863385427968.0,
+  "total_flos": 34292650475520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null