Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48189559254b1d9f3121c68607346d6bb4e457960c2be5a3968974359133919
+oid sha256:1d742f4f1595ee20efe17d0ac5aa90e245eff278670c7dec1e625d3c0f709a8c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f26a2ca6c46914bddd6642774787de9c0f6e5faabb3ff45d90b1707934800d8
+oid sha256:64f1d264f262afd040af001c80f143841649dfdb44c697e75aeb5d9df49ed41c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba2dba8083c66fc0d2aeb786e658b4b6752c9b3d645135a768253e6d260da31
+oid sha256:ee72bd09c897a7f5e116ce252acd7632733fa6243262029b30575a43ee85c2a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
+oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024836150396688513,
+  "epoch": 0.03725422559503277,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 7.142,
       "eval_steps_per_second": 0.895,
       "step": 18
+    },
+    {
+      "epoch": 0.028975508796136598,
+      "grad_norm": 2.6757843494415283,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.8649,
+      "step": 21
+    },
+    {
+      "epoch": 0.03311486719558469,
+      "grad_norm": 3.3077943325042725,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.8514,
+      "step": 24
+    },
+    {
+      "epoch": 0.03725422559503277,
+      "grad_norm": 3.4696767330169678,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.7777,
+      "step": 27
+    },
+    {
+      "epoch": 0.03725422559503277,
+      "eval_loss": 0.20136968791484833,
+      "eval_runtime": 171.0507,
+      "eval_samples_per_second": 7.138,
+      "eval_steps_per_second": 0.894,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.062532390505677e+16,
+  "total_flos": 7.593798585758515e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null