Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790ca75f18615358abeafefae73b7e01e2cafb2c1eb5f31bad5f30bdfe6c9bbc
+oid sha256:142f9b9bed5809ceeaee2975a0410839e1c494f516d6ddd0690d894df0aaef5d
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4f4ed69a4053dc92ddfd54ca7b16750c41df6b5cfc815d2642fb53d8efa951
+oid sha256:82e92575c34a78283e76453ea84b382444bfa518cb25afa5a30828d963f20243
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bf2a06b5e98d5a67322ab0990abee79d95dab6ba372a5b994bcadd0728b6f42
+oid sha256:69c664c9fda983f1616ad3af5db22b7f5007cc469a1cdf58cada8de6369f50dc
 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": 0.17848767192748938,
+  "epoch": 0.18254420992584142,
   "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": 10.596,
       "eval_steps_per_second": 5.301,
       "step": 88
+    },
+    {
+      "epoch": 0.18254420992584142,
+      "grad_norm": 7.835686206817627,
+      "learning_rate": 0.0,
+      "loss": 24.8061,
+      "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": 4.674029369520292e+17,
+  "total_flos": 4.779211465036923e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null