Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8318210ff4c8886716617375f8289a7cf0285cbe8ef968cb0393a4e12f85a0a2
+oid sha256:9fdf8691be4d9f407feec0440890a48aee42a579e9f6157f435d707b6c39cd22
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c3edeefbebb02589ed7da8af1aef36e8173e68c390272b407aa1e82e4a5626
+oid sha256:0eefa75e66da55bd426ddb3da2711ca6dfc529e22193ae2ce1f75ad35c563ea9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8663185886d8ed8b32a9a7663e77c6f1b4b58e1ee68a5b61088d4f00a0dffd
+oid sha256:b5c2d63dea053348e8fd5bf01076f2a5708c04d86cae79e488be63be4a9b0c83
 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": 2.2098121643066406,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 2.197718620300293,
+  "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": 30.65,
       "eval_steps_per_second": 3.835,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 2.1964,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 2.197718620300293,
+      "eval_runtime": 204.9105,
+      "eval_samples_per_second": 30.618,
+      "eval_steps_per_second": 3.831,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.123829358901248e+16,
+  "total_flos": 7.408408364292096e+16,
   "trial_name": null,
   "trial_params": null
 }