Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039db4adeb8cd1b6bb0ec007ed3c006bcbdcea9b09c0987fd0ea3a02fc671feb
+oid sha256:1fcf40764db523771739328a3bd8edf0f09346f5cf80ca2b3b503e156dcb44db
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81944db0af75ec0e56e629a9109e10e3fd144e4ac69ffa21c621a23bb16c945
+oid sha256:9726494e019dd6a5135b6f19f889f17403a6938f4aa6c091cdb8602e409c7dd5
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68529ee711356fd9d47647e5bd3dd9d92d8d90801ebf2381a18d532f68111077
+oid sha256:3bf26d2680b85dcd667f80e96b5cc6e90865b5e4d06d5ef11eb1400f3de4c7b7
 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": 0.07775377969762419,
+  "epoch": 0.0785391714117416,
   "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": 19.379,
       "eval_steps_per_second": 2.422,
       "step": 99
+    },
+    {
+      "epoch": 0.0785391714117416,
+      "grad_norm": 4.896818161010742,
+      "learning_rate": 0.0,
+      "loss": 2.9994,
+      "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": 1.4934284429583974e+17,
+  "total_flos": 1.508513578745856e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null