Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cecddaeac34b39c2187580e6da01f0284d7f69be66a4a59d274c21b94695fb0
+oid sha256:c232c282aef799b754b5dd6fe99a8c90f16af19d0d17bac40757888f4da2a7c4
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:417ea53da3f835d76119ba2ce4643c4b11c4cc218c35285787b8e6ac6377ce47
+oid sha256:a6c64250ce5f0741d7c28e75143f06154853754d992081c9d6a509d51ea83995
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ac3d2b522a45fffa5206c5d7a821c451a2d4e38cb61393c89b930eaeff3109
+oid sha256:42edf9c7109ab209010ee4e740b02f87408b17c068c8d2ba30c0ee1e621d22e8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
+oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2367302179336548,
-  "best_model_checkpoint": "./outputs/checkpoint-3900",
-  "epoch": 2.841530054644809,
+  "best_metric": 1.2278679609298706,
+  "best_model_checkpoint": "./outputs/checkpoint-4000",
+  "epoch": 2.9143897996357016,
   "eval_steps": 100,
-  "global_step": 3900,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,13 +553,27 @@
       "eval_samples_per_second": 43.665,
       "eval_steps_per_second": 5.463,
       "step": 3900
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 0.0002,
+      "loss": 1.2049,
+      "step": 4000
+    },
+    {
+      "epoch": 2.91,
+      "eval_loss": 1.2278679609298706,
+      "eval_runtime": 143.5851,
+      "eval_samples_per_second": 43.695,
+      "eval_steps_per_second": 5.467,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3245805220581376e+17,
+  "total_flos": 2.3840611478920397e+17,
   "trial_name": null,
   "trial_params": null
 }