Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d627c478d84d01e96792812de94fe869f10a20de4c82dcf336b35e6e6500c2bc
+oid sha256:bc68cfd27343b2a091337733530cd471e3514bb8952658da53d09396fff40aad
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3adcc97c9208717ab32fdcce16d7e4188827497da8bf83eecef94eb1a84d2cee
+oid sha256:68884c1b1d6b42bf84ddb6433da7b04b5a1a33ae5855b97f540b1944b37c7e59
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42edf9c7109ab209010ee4e740b02f87408b17c068c8d2ba30c0ee1e621d22e8
+oid sha256:090c2b75e05740bc86b1f8f8c7f09eb690b5edd74f523995d63f8760f4d18b6e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+oid sha256:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2135709524154663,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 1.1995476484298706,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.987249544626594,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 47.239,
       "eval_steps_per_second": 5.911,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.1877,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.1995476484298706,
+      "eval_runtime": 132.8652,
+      "eval_samples_per_second": 47.221,
+      "eval_steps_per_second": 5.908,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3840611478920397e+17,
+  "total_flos": 2.4438234279579648e+17,
   "trial_name": null,
   "trial_params": null
 }