Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e83cefdcc6203ee4a2b508c9b199ee1a40e6b9873e26be0636b98161739e7df
+oid sha256:3011bb582041041228b9218006158b27007720ce9203b08898f0702b9084f663
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364a4a3dc2e3b2a980a391a9cb8f8f04d1fdafa0632f2cee248933d77f9dd4a7
+oid sha256:8279fcd4b2cbb8c821967685a10d1ef8db7d5a5390e4a994334e0070353e2556
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acaabd0241bdb4b71e1d0732da71569e99114da61db10e89ea929a99ec596161
+oid sha256:7b0bee0f47e046288a8ab410015fc2b2510b7d505ae807cb056407e3f2c1143e
 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": 0.09207161125319693,
+  "epoch": 0.10230179028132992,
   "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": 47.43,
       "eval_steps_per_second": 23.715,
       "step": 9
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "grad_norm": 21.405139923095703,
+      "learning_rate": 0.0002,
+      "loss": 3.0455,
+      "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": 69051422343168.0,
+  "total_flos": 76723802603520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null