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:b0b8bb193e24030b8354775942d3b461797e03b118e05215685a25ab4f05a909
+oid sha256:113655ecdfcd5c120cc1f07b5571d2b9b4aab693059ab0785eb1d787794c9238
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9785116d32ec567a73de364c9b9ff82e17beb784ebe79d0120ea50b24added
+oid sha256:6175588e049b76613130a3bd09031ea0151b6bdf10a485e0458378257ee4d424
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
+oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
 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": 0.004067337024065077,
+  "epoch": 0.004519263360072308,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 19.005,
       "eval_steps_per_second": 9.502,
       "step": 9
+    },
+    {
+      "epoch": 0.004519263360072308,
+      "grad_norm": 0.0413544699549675,
+      "learning_rate": 0.0002,
+      "loss": 11.9455,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1861042176.0,
+  "total_flos": 2067824640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null