Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f34e33ba1cbed0160af5c5593143e3e8b38e70fe96482a2977d0f63263da34f
+oid sha256:4cf422fdfb0c22a4e52258b42c1bcb9519218362a7656ef782dcd5751427a71c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c67de520f57e300affbc221b1aae6fd0aa44e79e593afad93c33f9d2772417
+oid sha256:d92e21c9f8399c0cd285cd695c9f76f59c0a66e0be2def62de7f7b34a1f7341e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bc72a2dd61fde2bf7e35b38e131fc7660ee3fdebf98f8b23ba292ea3eb99170
+oid sha256:b83d451a7d2201b5472bb63276fd396f894278db57fcb29bd3dd23fcc3da5182
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.531459331512451,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.2185792349726776,
+  "best_metric": 2.497565746307373,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.29143897996357016,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,13 +49,27 @@
       "eval_samples_per_second": 25.549,
       "eval_steps_per_second": 3.197,
       "step": 300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002,
+      "loss": 2.5133,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 2.497565746307373,
+      "eval_runtime": 244.6469,
+      "eval_samples_per_second": 25.645,
+      "eval_steps_per_second": 3.209,
+      "step": 400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8808208295362560.0,
+  "total_flos": 1.17553968451584e+16,
   "trial_name": null,
   "trial_params": null
 }