Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50130f37929c944bc47afc3c27b305546a69de671aa00a31fb99df835b7bc311
+oid sha256:a8e46be1d1a10ddefaa4ee128b7361b675543607663f4f8920e6224d60dfd71b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa103b86be51b745eeb2e9e596f03afd778007239939319b7b6fad9b8aa572e
+oid sha256:acfff7c6ff23933242aa7fc55d8f71e2730df4d6ad0833f97e6a1ae138ed7659
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19394caac0370dc5eb8bb3d271a9b6d245fc10d68ceffd549459fcf4f2e70bc9
+oid sha256:163020c3a5e3deb0c9f202a04693b11d0b5de442bd4ef423bf0f0a2016603d4d
 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": 0.0003590735901374454,
+  "epoch": 0.0003989706557082727,
   "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": 23.749,
       "eval_steps_per_second": 11.874,
       "step": 9
+    },
+    {
+      "epoch": 0.0003989706557082727,
+      "grad_norm": 8.625518798828125,
+      "learning_rate": 0.0002,
+      "loss": 1.8661,
+      "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": 2450672628793344.0,
+  "total_flos": 2774346372218880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null