Training in progress, step 174, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44626cc94e4ae4ef2189f492ec6a02f6a9cf34d81e54c3c0d3c5d06f2b5db83b
+oid sha256:56a2e73c9f0ba15318c013faf0d516ee65831595556a20e8cc91038732cbb63f
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b50b88935790b9e8a1ab3ebd399aafd75c99d1e6cae3998824e30f7299dfba
+oid sha256:79a0e23d7291a4e9f915b30d705155a393e8800f2f6f4e596397adff82be650e
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd41ad516c648e6a91e8eb789b6ec82ae8142cda642d8cd2955159250148cb8d
+oid sha256:77a17188e5eae813466d478a1f96ede6eeeb68c0c6586491c70042c476c86443
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4663923182441701,
+  "epoch": 0.4773662551440329,
   "eval_steps": 500,
-  "global_step": 170,
+  "global_step": 174,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1197,6 +1197,34 @@
       "learning_rate": 0.00014696969696969698,
       "loss": 1.3067,
       "step": 170
+    },
+    {
+      "epoch": 0.4691358024691358,
+      "grad_norm": 0.14815697073936462,
+      "learning_rate": 0.00014621212121212123,
+      "loss": 1.2492,
+      "step": 171
+    },
+    {
+      "epoch": 0.4718792866941015,
+      "grad_norm": 0.13748030364513397,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 1.2281,
+      "step": 172
+    },
+    {
+      "epoch": 0.47462277091906724,
+      "grad_norm": 0.14712287485599518,
+      "learning_rate": 0.0001446969696969697,
+      "loss": 1.1438,
+      "step": 173
+    },
+    {
+      "epoch": 0.4773662551440329,
+      "grad_norm": 0.13734129071235657,
+      "learning_rate": 0.00014393939393939396,
+      "loss": 1.2528,
+      "step": 174
     }
   ],
   "logging_steps": 1,
@@ -1216,7 +1244,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.109386405851054e+17,
+  "total_flos": 2.1599650151780352e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null