Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3864e5e1b1010f24d519e43f4a9890823e34eb95b43eb84c59ef5fcc1fb0614d
+oid sha256:d2e668934b242274bde54b6b8bea3496abf521c134eab67e3897f5b82151ca39
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1e922427b0d1445375a60d808fbf578e6cd7b784824ce294ac00136582bc5c
+oid sha256:fe7b17c1a35e1bd33ab38c889d0010301210c21ef02967172e88f6e470639d15
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60c40a7ec38defa6f3b82f360cbc03080a806e541e97adde1e243000f5a63b3
+oid sha256:0d0da3873d0775bf81b7bdee3955da665b473c4317959da28b057b61212854f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
+oid sha256:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08579088471849866,
+  "epoch": 0.08774067755300999,
   "eval_steps": 8,
-  "global_step": 88,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -306,6 +306,13 @@
       "eval_samples_per_second": 149.38,
       "eval_steps_per_second": 74.69,
       "step": 88
+    },
+    {
+      "epoch": 0.08774067755300999,
+      "grad_norm": 0.047215670347213745,
+      "learning_rate": 0.0,
+      "loss": 11.7444,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -320,12 +327,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 144219800862720.0,
+  "total_flos": 147497523609600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null