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:d949b8f9f8167d5ba7b401703d84c6d353cf22473acb4b2aa2a100c9a985fe58
+oid sha256:c14582e7de2eb10d18b36c2ee4d79901b7b2addc60c41b210569b73ed76d7ab6
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f08122247da99ed8e28880f02e7bd81fd7e698a2fe282e14df568bda6ee5cf
+oid sha256:772de744b81c0f8d47097535a11575e792f20ac94d390a701039411698b35b5f
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ac3d2b522a45fffa5206c5d7a821c451a2d4e38cb61393c89b930eaeff3109
+oid sha256:42edf9c7109ab209010ee4e740b02f87408b17c068c8d2ba30c0ee1e621d22e8
 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": 1.2340775728225708,
-  "best_model_checkpoint": "./outputs/checkpoint-3900",
-  "epoch": 2.841530054644809,
+  "best_metric": 1.2261732816696167,
+  "best_model_checkpoint": "./outputs/checkpoint-4000",
+  "epoch": 2.9143897996357016,
   "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": 43.296,
       "eval_steps_per_second": 5.417,
       "step": 3900
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 0.0002,
+      "loss": 1.2027,
+      "step": 4000
+    },
+    {
+      "epoch": 2.91,
+      "eval_loss": 1.2261732816696167,
+      "eval_runtime": 143.9516,
+      "eval_samples_per_second": 43.584,
+      "eval_steps_per_second": 5.453,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3245805220581376e+17,
+  "total_flos": 2.3840611478920397e+17,
   "trial_name": null,
   "trial_params": null
 }