Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a427a3560750d80f1896a1c1b75081170106cfa39485a14df51c39300fe8ae
+oid sha256:525cfdfd6d0f5c35d91364f88a533315447db5d80de05fcd09e1a7510025e6d2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908c2f1b856c37fddec282faa3327d0f596a1f64e44f1938657182f09356c730
+oid sha256:4069c8bb0ea4cf1cc6cdd28534279893f4483751e500da1ae860dad1bc7c47db
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6806389118ec16be45f91f2597dc80c85380e866e2552fc0b165cbd873f66c65
+oid sha256:31995c67bfda050712f83583fcf743559da363f2474b549c2a360b8ebee98d92
 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": 0.022072348252605765,
+  "epoch": 0.024524831391784182,
   "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": 18.366,
       "eval_steps_per_second": 9.183,
       "step": 9
+    },
+    {
+      "epoch": 0.024524831391784182,
+      "grad_norm": 1.31636381149292,
+      "learning_rate": 0.0002,
+      "loss": 1.5509,
+      "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": 2809564659449856.0,
+  "total_flos": 3135311286632448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null