Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a46c57a46cef8a3511fa1b40cc550fc709c18e2b4dda11531a5c0adb98ac23
+oid sha256:5ebdab700abc155329f144941e4d374e59d8008e3d5310712f7a82098531640d
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca8c7d35dc6277d9ea116f834738d3b6acfa3ee3f191af8cb075b10d1c85062
+oid sha256:6b37efe099da6cecf506ef3f25bdde56f267c0064c66778692e33c6caba5e6bb
 size 400714

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d7638315e3e0a14cff55b75bcf9d18fa85d487a83a898f3906ffbf5885ed30
+oid sha256:0e24b96fe81a7ba92d3e59714ad06f0a9469a930b3dca5959f4862b3dc96b663
 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": 0.08208955223880597,
+  "epoch": 0.08291873963515754,
   "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": 353.418,
       "eval_steps_per_second": 44.177,
       "step": 99
+    },
+    {
+      "epoch": 0.08291873963515754,
+      "grad_norm": 0.1632109433412552,
+      "learning_rate": 0.0,
+      "loss": 10.2782,
+      "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": 22087030800384.0,
+  "total_flos": 22310132121600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null