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:c7f49cd3906fd147acd3466bbb6a6a964fc1c1ba8245c0ca525d1481af503147
+oid sha256:0a3a0c13a7bdcb4b5df9738be06c444935a7cd2a56adb1fb919cdbfdfd4b39a5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb9f5d6f4872a5dd23064c9a9e71edbca78a36f255c2d1530cf86b2a2888fa8
+oid sha256:7cfdfcc2ce8b488d1ed5efecaf6c920971d2b07d9475c98489ee387de6dee66f
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54088f61daf67ba3987886527d2520040d63916cf72a674a3a58d1cc4e57624a
+oid sha256:1a88f2e66a4bb1f8fee525e81aad5015f8f23c0ac0909a1062c301d2128857fe
 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": 0.014937759336099586,
+  "epoch": 0.016597510373443983,
   "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": 19.989,
       "eval_steps_per_second": 9.995,
       "step": 9
+    },
+    {
+      "epoch": 0.016597510373443983,
+      "grad_norm": 0.35051751136779785,
+      "learning_rate": 0.0002,
+      "loss": 0.2549,
+      "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": 2711820020219904.0,
+  "total_flos": 3017993248309248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null