Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402a1852fc7cac9700e5ee0d0dce99f73adcfe23aad307515a1ae3e70e3b0f8c
+oid sha256:ad3bbf907000a385c3ca8f29fd24f6700a0a653aaf45e32872367117791f5af3
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3c0a3600c9d6481528afc62e45771c88c6e35d0ca84c0bf2587b0d774162fb
+oid sha256:ca6b5b4aa7049d008dabdf36acbd57aa681e2367f2960cdbcb5e4c8ce0ad216b
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6697f228e01d9570a9ca8a159a36858b53464b14af2c48a02d573db55895bf97
+oid sha256:bad42f29ee4bfe82d4249e5bb72e70b397cd827dde13dffb870b00764b56914e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
+oid sha256:5416093c744b622c4436f38b8545546a70241fb2d36e53a533c7ae67d7ced8b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8389830508474576,
+  "epoch": 0.847457627118644,
   "eval_steps": 9,
-  "global_step": 99,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -236,6 +236,13 @@
       "eval_samples_per_second": 18.855,
       "eval_steps_per_second": 2.379,
       "step": 99
+    },
+    {
+      "epoch": 0.847457627118644,
+      "grad_norm": 0.5222312211990356,
+      "learning_rate": 0.0,
+      "loss": 0.7123,
+      "step": 100
     }
   ],
   "logging_steps": 5,
@@ -250,12 +257,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.5349125663739085e+17,
+  "total_flos": 1.549997702161367e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null