Training in progress, step 3600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a160da10e15a9c43cf0d561ef60ecd20d339c88fa704cfacb0935c3fb8bd71
+oid sha256:e17afdd5ee88313e3bb7f01e153b4d1ebe56021d4123305e609e23d3cd06fd74
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c59787d95804c75a161af0a03d182d0281a83afb6392b486e1fa88928c307b
+oid sha256:76585761215f7c28b01c08237b1a8e04a0a675a97605ae7ab28746453d9762fe
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5111e44aa3c7fb3d2679f29ed14de9b378a43fa023e1e3c7c0e2bac399b6ea6f
+oid sha256:63998d98da08278c470436d7f3090e0552bc25f2e2fd93ff495fe8ccda5df6f6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
+oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1295558214187622,
-  "best_model_checkpoint": "./outputs/checkpoint-3500",
-  "epoch": 2.5500910746812386,
+  "best_metric": 1.1208428144454956,
+  "best_model_checkpoint": "./outputs/checkpoint-3600",
+  "epoch": 2.6229508196721314,
   "eval_steps": 100,
-  "global_step": 3500,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,13 +497,27 @@
       "eval_samples_per_second": 15.025,
       "eval_steps_per_second": 1.88,
       "step": 3500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002,
+      "loss": 1.1054,
+      "step": 3600
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 1.1208428144454956,
+      "eval_runtime": 437.4502,
+      "eval_samples_per_second": 14.342,
+      "eval_steps_per_second": 1.794,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.134669408060162e+18,
+  "total_flos": 1.1670242076660173e+18,
   "trial_name": null,
   "trial_params": null
 }