Training in progress, step 166, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b9ed82bd6604b8703ecc08e076c740ba470f1bb55d87371e3bacba4441f425
+oid sha256:ac262481cc9553d1e7db45250003ea7127f9e527ddd9a7421a6046ed77aa9424
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d50bcb1a70c76622db3253039acf943b407ace0e58f77f5002d84fc3e055d8d
+oid sha256:425e796513afd4fe02b8fa6f67121459dd8a9915f7bd15ef9b0d7ebd1dec6173
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57c57a3464a3724ed13829b887c7a0d95f13cbca3f2afa05f432b825c23a8cd
+oid sha256:523ed79f519ac71c24fed641c0fb962cd1d7cc2cc6b60736901cbae3ef1c80fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4444444444444444,
+  "epoch": 0.4554183813443073,
   "eval_steps": 500,
-  "global_step": 162,
+  "global_step": 166,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1141,6 +1141,34 @@
       "learning_rate": 0.00015303030303030304,
       "loss": 1.1901,
       "step": 162
+    },
+    {
+      "epoch": 0.44718792866941015,
+      "grad_norm": 0.2013212889432907,
+      "learning_rate": 0.00015227272727272727,
+      "loss": 1.2106,
+      "step": 163
+    },
+    {
+      "epoch": 0.4499314128943759,
+      "grad_norm": 0.16856490075588226,
+      "learning_rate": 0.00015151515151515152,
+      "loss": 1.1806,
+      "step": 164
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "grad_norm": 0.18135228753089905,
+      "learning_rate": 0.00015075757575757576,
+      "loss": 1.2848,
+      "step": 165
+    },
+    {
+      "epoch": 0.4554183813443073,
+      "grad_norm": 0.18058203160762787,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2576,
+      "step": 166
     }
   ],
   "logging_steps": 1,
@@ -1160,7 +1188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.009710507880325e+17,
+  "total_flos": 2.0588771572748698e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null