Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b66b111a0b1abfa1c70d2742dbbce83d9963b0bb5024a02f015bb9f528012e
+oid sha256:e277ebb388fa8641caa7eb84047607b95a929a3ef22591600376b89bd912f869
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:658a21e87b472274b51128294045aa60ac45ea31d180172e261a19b4b2d650ac
+oid sha256:fb4eba9e8d32b2f6ba2f2a90415cf15daf991ba87d99cd781140d3709fc27e85
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
+oid sha256:731356647582c8ef90f666e46f0dafaa099438d483cb22a0268abc589e0178cb
 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": 0.012907852276801721,
+  "epoch": 0.014342058085335245,
   "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": 74.567,
       "eval_steps_per_second": 37.283,
       "step": 9
+    },
+    {
+      "epoch": 0.014342058085335245,
+      "grad_norm": 0.12192214280366898,
+      "learning_rate": 0.0002,
+      "loss": 11.9502,
+      "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": 2221517832192.0,
+  "total_flos": 2471829700608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null