Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313dcc1cb3837885acfa16f27654fda4d0cab6ae3cdfd89b76002bbdf06f96e4
+oid sha256:0260ee13b18c2ecc01cddf6d26f17f501f78df044bb5b30540f47d870e07922f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e55576cf37e96a963f97147b9550f87ca9154654610a5d73215e36951a8415
+oid sha256:de06df9740b69e2d0a54a7cb2b52b0b9012fddbdf2219745a05816fa6d5c809f
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57fe9322ee192f6ca97876187da096d9083f730f45230a65c47e815b5fed1304
+oid sha256:f05914f49210a573ac7348f6ff076fd88623f6baab1ab01aaad3e64322b8d571
 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": 0.004590080326405712,
+  "epoch": 0.005100089251561903,
   "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": 25.89,
       "eval_steps_per_second": 12.945,
       "step": 9
+    },
+    {
+      "epoch": 0.005100089251561903,
+      "grad_norm": 0.7831794023513794,
+      "learning_rate": 0.0002,
+      "loss": 0.8234,
+      "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": 900175195275264.0,
+  "total_flos": 1000194661416960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null