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:e8ed5817cf867b4833eb27cdc0b4db91c1ded5d6eaea04777f3e511270be77e5
+oid sha256:a8f2798efc12d19b6f5672b2f30b7bd0776985f7c2209a8126b6d302139ba817
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5406bb35c7ba7a42bcc07f539e1a4f688b82a47ba6a649b68c84b10827468b
+oid sha256:117657fb90cef5493b472e902e8122096d39744a984ed6790a71b7ca582e4faf
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
+oid sha256:9c4e103f057cbf52631a0f74dec69e271b2b990ec70bac9b6694c66ba4e1959d
 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": 0.008356545961002786,
+  "epoch": 0.009285051067780872,
   "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": 451.084,
       "eval_steps_per_second": 225.542,
       "step": 9
+    },
+    {
+      "epoch": 0.009285051067780872,
+      "grad_norm": 3.5456247329711914,
+      "learning_rate": 0.0002,
+      "loss": 43.894,
+      "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": 7097548800.0,
+  "total_flos": 7844659200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null