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:c7a79b84e518dc9be68a0f9e30bbc382d9593d7dcbb75b1e178c014420f02603
+oid sha256:5335f7b12f6f512f562a12cbc564519ed8633383c04dcfd1ec81f552cc0b9652
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b13edcfeae14cda70e2cdc7ad8c907c258f66621c42142db4dc4d8f0b2b94d73
+oid sha256:a9fb61604e3e1d7df027958e6c0943af0ced2c632fc30c2667c00827999974a9
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe9292b93acc5d120d0451081c1f103c87e36ea135c3d8cfd8c43ee2bd7d77a
+oid sha256:2b68f1810f307b6c09a05380ad28538ade3ddba69d60f15cc139749d53368f14
 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": 0.0005741260525644297,
+  "epoch": 0.0006379178361826997,
   "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": 50.018,
       "eval_steps_per_second": 25.013,
       "step": 9
+    },
+    {
+      "epoch": 0.0006379178361826997,
+      "grad_norm": 0.30160751938819885,
+      "learning_rate": 0.0002,
+      "loss": 0.3464,
+      "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": 158042740752384.0,
+  "total_flos": 175850373513216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null