Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:114ea38b8c9c73d969702e28b59868a439e96e89444fd8ff80a1691cfa789c26
+oid sha256:3360d7fb8c65da5fde7b34972de67b5b2ff7db00592051e2d7377d00d753d4ff
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206d627b3863f82f7aeaa7ee2101ddae9e4ebae6f070ae9fd9f74ea452665dd5
+oid sha256:2c96b7ef407f108e3c17996c2fe7f653ce01e198a2ed72ecda1070c8af5ef141
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8700f03b0419d9986a6e24b443d85912e3a6b7d042961e7ad00c63377cc539
+oid sha256:85a355cfb19d81e3463ec580a4d7cbcf7f7cfb13b0254e266e3297bbafa58661
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
+oid sha256:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.146674633026123,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 2.1346609592437744,
+  "best_model_checkpoint": "./outputs/checkpoint-2600",
+  "epoch": 1.8943533697632058,
   "eval_steps": 100,
-  "global_step": 2500,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,13 +357,27 @@
       "eval_samples_per_second": 30.214,
       "eval_steps_per_second": 3.78,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 2.127,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 2.1346609592437744,
+      "eval_runtime": 208.0228,
+      "eval_samples_per_second": 30.16,
+      "eval_steps_per_second": 3.774,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.298808085997568e+16,
+  "total_flos": 7.590446666901504e+16,
   "trial_name": null,
   "trial_params": null
 }