Training in progress, step 162, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b462fa6b90ee8aa41cdcb817969f69412fd9073e3b79a7860595893b4570436e
+oid sha256:36b9ed82bd6604b8703ecc08e076c740ba470f1bb55d87371e3bacba4441f425
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5c8205f0ffedb61b97b75d7af894c0726835db65155b4976937117e1d018e2
+oid sha256:9d50bcb1a70c76622db3253039acf943b407ace0e58f77f5002d84fc3e055d8d
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ad30ac47097af40828a09f9a43d6f06d675ca443c64afa20a38795f419018ab
+oid sha256:f57c57a3464a3724ed13829b887c7a0d95f13cbca3f2afa05f432b825c23a8cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.438957475994513,
+  "epoch": 0.4444444444444444,
   "eval_steps": 500,
-  "global_step": 160,
+  "global_step": 162,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1127,6 +1127,20 @@
       "learning_rate": 0.00015454545454545454,
       "loss": 1.2895,
       "step": 160
+    },
+    {
+      "epoch": 0.44170096021947874,
+      "grad_norm": 0.16663017868995667,
+      "learning_rate": 0.0001537878787878788,
+      "loss": 1.2847,
+      "step": 161
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.17813093960285187,
+      "learning_rate": 0.00015303030303030304,
+      "loss": 1.1901,
+      "step": 162
     }
   ],
   "logging_steps": 1,
@@ -1146,7 +1160,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9852396600762368e+17,
+  "total_flos": 2.009710507880325e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null