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:e2c36d5d59d7d63c0b350c8485ae0a9fa879dc35b3783ec5fff0ea2c73c66bbc
+oid sha256:8b63998dbaa431350943a7e12321f5279bc2186efc8e352c11d51c56fcc146be
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1f8aa4c54f13c60713c94d94c7fd0376af868342a0cd75deeeb8f80c8c60d1
+oid sha256:3167e885e4d92e032c4a129be37878331f2a753d432b07e57a6cc9476f53e003
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847f62533773bb63c647a3104c4f86b39bcd90a0e316a795dce3a1e0de6e416b
+oid sha256:aa3200449edf9aed39d75970ca63c44139ed1ded7545de8cbeb0885bee2baf2a
 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": 0.0002615385733070826,
+  "epoch": 0.00029059841478564733,
   "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": 63.706,
       "eval_steps_per_second": 31.853,
       "step": 9
+    },
+    {
+      "epoch": 0.00029059841478564733,
+      "grad_norm": 3.020841360092163,
+      "learning_rate": 0.0002,
+      "loss": 6.7184,
+      "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": 365987912220672.0,
+  "total_flos": 395864476483584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null