Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88d96aa2bcbe4fed0ade7d3e26f85ba08c04e3a700a6817eb795a7b38929543
+oid sha256:384802c27c18b781898e24b12f0f7fe3ff1aa608fef68ba21239271190c3cce8
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2a1f1198d8ab61503e0bb2e72a84b32f5c81a571dcd7023c2d864ec126ad8c
+oid sha256:5ddf0309e8477eb8e18c1a5ab0c56c0c7b63b9077fae65c7762d877d18860040
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71128331774d3b754a22777700176c9e9d829274c21a3111675887d72431a159
+oid sha256:0b1f8f96bc9f36513b798a2fc8903d08628df1f9eaa24d3e62b6ceae12d09b57
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42424f90eb68391066979b79f87ab18e2fce2a0abc640b46cf1b3f4c12c720a
+oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.268664002418518,
-  "best_model_checkpoint": "./outputs/checkpoint-3900",
-  "epoch": 2.8422586520947175,
+  "best_metric": 1.2541390657424927,
+  "best_model_checkpoint": "./outputs/checkpoint-4000",
+  "epoch": 2.9151183970856103,
   "eval_steps": 100,
-  "global_step": 3900,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,13 +553,27 @@
       "eval_samples_per_second": 47.132,
       "eval_steps_per_second": 5.897,
       "step": 3900
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.0002,
+      "loss": 1.2321,
+      "step": 4000
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 1.2541390657424927,
+      "eval_runtime": 133.1492,
+      "eval_samples_per_second": 47.12,
+      "eval_steps_per_second": 5.896,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3248377037320192e+17,
+  "total_flos": 2.3844554931253248e+17,
   "trial_name": null,
   "trial_params": null
 }