Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9ca11790735fcabf53acc64f6cee7d3a7e587302f3066d8ab7b794c3897ec3
+oid sha256:dcb8f98ac9ad72c99fe073bb1c6f652bc8460b3a2d433da4a62c065407c31f4c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8092270fb4a8f6a51e23cc8cafadea465a895f9a53b093a6ed029d1e40c75548
+oid sha256:f4443e4b092c1bd508dabb8174fd5a6e4a7584988e375cb8b8294d3471786f41
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cde9ca23dfe033d10028cbe0dd91dfa734d0be4761346f37da51e83a1e32cda
+oid sha256:ade7405352f21c3d4ca15e46ecacef02979b1c2444e0503889766e280e03c62d
 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": 0.00011718521122634323,
+  "epoch": 0.0001302057902514925,
   "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": 14.841,
       "eval_steps_per_second": 7.42,
       "step": 9
+    },
+    {
+      "epoch": 0.0001302057902514925,
+      "grad_norm": 1.6312642097473145,
+      "learning_rate": 0.0002,
+      "loss": 0.5381,
+      "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": 1757086035738624.0,
+  "total_flos": 1942042460553216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null