Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de543f42a8abb4cb8e9dd09d039525e203dedc7a7bd91c415eeadaae4f2776a
+oid sha256:159211f53cad6543f11807bc61ed30dee1427be4d3c63d5ca22635f7d1262258
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ba863b187e607ef384544a77872b58f6d7edb94ea8f2a6e193f23f3d167e78
+oid sha256:42da710037cd5ff00af306c1f46889f77df73cdc2e717fbfe69a9d69d3635b8a
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe072b43116ea6af1d9839ff9078df37c5fb13f3285b4cbe739c3c5d14228bdf
+oid sha256:8a0d9d4b9143f23093465c736b344edb94f3988c049bd9c6571469763fcf7a30
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+oid sha256:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.969947099685669,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 1.9582247734069824,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.987249544626594,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 30.439,
       "eval_steps_per_second": 3.808,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.938,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.9582247734069824,
+      "eval_runtime": 206.5559,
+      "eval_samples_per_second": 30.374,
+      "eval_steps_per_second": 3.8,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1744177835220992e+17,
+  "total_flos": 1.2037527679500288e+17,
   "trial_name": null,
   "trial_params": null
 }