Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767b6c305e52e1ef5bb73f846c25d6937ce0641611880683d3a75dacf8f0faa3
+oid sha256:21e6bd5e56a5e7e94e80f3017cf1463630efc4245bbde864ac5db2d316656acf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def0859ba3aaaf120d6822b6688669c715488445090b61401a9c05e8a80facc4
+oid sha256:1ff2ee6788361053ca74a17cf918818865b8806b9a7d580e825e071a89867cb8
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54546ab4af031175bc5b88417f5f0cdd4f9908877ef5235c42fa06324bc69e4a
+oid sha256:5ff1786a8d636aa576fd2e4f292710625eb6790c6306bb8eec14916c4b6f6d16
 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": 0.11904459945043332,
+  "epoch": 0.12175015852885225,
   "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": 8.972,
       "eval_steps_per_second": 4.486,
       "step": 88
+    },
+    {
+      "epoch": 0.12175015852885225,
+      "grad_norm": 0.17539910972118378,
+      "learning_rate": 0.0,
+      "loss": 0.3584,
+      "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": 5.253778609369252e+17,
+  "total_flos": 5.373140281715589e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null