Training in progress, step 165, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0a8a3ec4f34418a88a656cab64ce468819986166088766eac291b51c015350
+oid sha256:1af31d62fe7961d7981cc90313d8f2b921e6bc728f41b25e05b784db15723ebb
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5204c920a9c28a65017b7dc19a74b014324204b35ad86defdf6ec3b9bfab5a3b
+oid sha256:da4651a70e13d122e85d8dc112c706bff35297761fdc3aa64ff81ba9a879282c
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026b710e7a787e8533a7b53109192c1ec5bf78162ec26798b66409b9a5f88889
+oid sha256:380ec0b049b37b314671979349104a52b81fba5d4ab1fa2da5437554df1c19ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb01d4f0da8d959e9ca5a4773566e24c639c6b8f18e1285757275e715c7b05f
+oid sha256:76f9fa65284e4b8f8e69031f6dc478e117b8d1a8c08ea32a69c55e7f794584df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.606060606060606,
+  "epoch": 2.865800865800866,
   "eval_steps": 15,
-  "global_step": 150,
+  "global_step": 165,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -445,6 +445,49 @@
       "eval_samples_per_second": 4.439,
       "eval_steps_per_second": 0.595,
       "step": 150
+    },
+    {
+      "epoch": 2.658008658008658,
+      "grad_norm": 1.2263282537460327,
+      "learning_rate": 3.668937158903901e-06,
+      "loss": 1.7352,
+      "step": 153
+    },
+    {
+      "epoch": 2.70995670995671,
+      "grad_norm": 1.3095903396606445,
+      "learning_rate": 2.6599507663574384e-06,
+      "loss": 1.8122,
+      "step": 156
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 1.2558013200759888,
+      "learning_rate": 1.8091892454998594e-06,
+      "loss": 1.6398,
+      "step": 159
+    },
+    {
+      "epoch": 2.813852813852814,
+      "grad_norm": 1.2757107019424438,
+      "learning_rate": 1.1194961006082972e-06,
+      "loss": 1.7014,
+      "step": 162
+    },
+    {
+      "epoch": 2.865800865800866,
+      "grad_norm": 1.1844847202301025,
+      "learning_rate": 5.931764963608866e-07,
+      "loss": 1.8026,
+      "step": 165
+    },
+    {
+      "epoch": 2.865800865800866,
+      "eval_loss": 0.6837310194969177,
+      "eval_runtime": 43.4558,
+      "eval_samples_per_second": 2.232,
+      "eval_steps_per_second": 0.299,
+      "step": 165
     }
   ],
   "logging_steps": 3,
@@ -464,7 +507,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.70877313473577e+17,
+  "total_flos": 8.481582471551386e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null