Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102c35f0d2d0a8d68e313bff7ab0a4afeda3224deab5c0f9c01ff1dff324705c
+oid sha256:fb90b4a01c2b1f6a1dee1a7ee71eee274538d61adb1808da614d4b82be99c789
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b18b6f9f734323ebd3ca9e8bf1c12e83890a01d354add7e695ac7bf7a6cebca1
+oid sha256:72931b28bd75ed18775198c2152512ff9b31630990ab6c77e8e49354210c1960
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb19775908c316bf5835393d33748a381150a1b2242bf50b0e2855e185881ca
+oid sha256:442bafcbf0d292ca19eedeb960e51c5d7ecd5eec12507df91524cb8e1081a81b
 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": 1.2266868352890015,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 1.216168999671936,
+  "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": 15.012,
       "eval_steps_per_second": 1.878,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 1.2106,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 1.216168999671936,
+      "eval_runtime": 417.7189,
+      "eval_samples_per_second": 15.02,
+      "eval_steps_per_second": 1.879,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.104035789088573e+17,
+  "total_flos": 8.428488053895383e+17,
   "trial_name": null,
   "trial_params": null
 }