Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e29737b22ee3020d5d30eeca844705b6cd0bbb341970662ca1d9fb1601a7c7b
+oid sha256:09b280c349418a70d19d165ede87ea095dd6778e9ece47a758878ab61eb43797
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c113900dd87ed7a7519b0c863c07eaf4f440df20954e0a387dfdedfa3fa9c1e1
+oid sha256:7b27aa39923b061bf24fc385c8e40c8602a8c396211a9d3fdd059b95bfc40acc
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27917d88cdf4e1cd610266e1bad5287f7c270415c57a7781c0adaab154ebaaf5
+oid sha256:0609e366e59bea0a2fe4425b265a00afc11366ee6e27181a09300127ce600c4f
 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": 0.0006467840459935322,
+  "epoch": 0.0007186489399928135,
   "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": 13.466,
       "eval_steps_per_second": 6.734,
       "step": 9
+    },
+    {
+      "epoch": 0.0007186489399928135,
+      "grad_norm": 0.6182520389556885,
+      "learning_rate": 0.0002,
+      "loss": 0.5491,
+      "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": 291868432662528.0,
+  "total_flos": 324298258513920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null