Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6b044c4ab53e420ef6cb9c56fc10c91493d0ff5ff9c29e9210a326a214952b
+oid sha256:60896e49920d577d2894678cc3280e3ec017e13d846705f8a993efe555c3c38b
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1231af57e07e438de8d67a9c871a7f87723cafe20bc36d8be53f6594228271
+oid sha256:f3576a7b36d73006c66470e6c5fe9f13ddfc155934dd9bbead34cf48158ced13
 size 400714

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb2ba3b1524210890e0b917c7d0bdf0832f16fbba8778b1bbe3b3b24d97d094
+oid sha256:b0fb0c68abaf13cf6e3c825a941fa2c18b846bc37490880c8e2a09c0b84ead0f
 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": 0.047345767575322814,
+  "epoch": 0.04782400765184122,
   "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": 321.346,
       "eval_steps_per_second": 40.201,
       "step": 99
+    },
+    {
+      "epoch": 0.04782400765184122,
+      "grad_norm": 0.08554812520742416,
+      "learning_rate": 0.0,
+      "loss": 10.3287,
+      "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": 22254356791296.0,
+  "total_flos": 22477458112512.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null