Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00eb982cee410fb9b2078c106598c9c79f9ab9b140c4797e6e261b1304a226d2
+oid sha256:f1b84fba871fb46b6fd805632c9e440ad75ca8afec328fc2d34b8f991acdc9e8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8c908a211eb04276137e069fbc250ed7c7504fa4468494f6e0322186432878
+oid sha256:669c0936ebc8a58e899f73ee7cd9e2408394ceaca972bb7c155c31ab2a92fee2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
+oid sha256:deed864d9094dd276975b1a0b401102b49095b3b4735cef2dfce0c737a2bfd46
 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": 0.004287756074321105,
+  "epoch": 0.004764173415912339,
   "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": 18.249,
       "eval_steps_per_second": 9.124,
       "step": 9
+    },
+    {
+      "epoch": 0.004764173415912339,
+      "grad_norm": 1.0647661685943604,
+      "learning_rate": 0.0002,
+      "loss": 2.5559,
+      "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": 3329215646662656.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null