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:fdcb717cb3df5ed4fffa5a0a923e973e7fff71d7a7a342698b5993cfb1d08692
+oid sha256:c6d61a0e78d731fb45494492379db128c8ef1936336b1bad19eb9fbd1ecd3e24
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33f1d2fdc3310cd87fdeeac33bb1450a7e16ba3ae87ba23a71690b6e91754a8d
+oid sha256:e427bd7746647ff3574e19048d5e813c16429569d31047579dbba4184b522888
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
+oid sha256:894ae9e2dd56efcd745c69d81e84d269bfa54a0f8cbcf8e14a4428f929aae407
 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": 7.993232396570903e-05,
+  "epoch": 8.881369329523226e-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": 12.432,
       "eval_steps_per_second": 6.216,
       "step": 9
+    },
+    {
+      "epoch": 8.881369329523226e-05,
+      "grad_norm": 26.927465438842773,
+      "learning_rate": 0.0002,
+      "loss": 7.0072,
+      "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": 1752669785948160.0,
+  "total_flos": 1927936764542976.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null