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:c232c282aef799b754b5dd6fe99a8c90f16af19d0d17bac40757888f4da2a7c4
+oid sha256:00b77288d7de9928f0d4944f30ceaa295b505628b9edd8e5d47eb8a4bd9e9692
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c64250ce5f0741d7c28e75143f06154853754d992081c9d6a509d51ea83995
+oid sha256:3217a20517ef38c58a8da957d08c71a1c0546fe4766b19a5c5e8998ff14a0214
 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": 1.2278679609298706,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 1.2136116027832031,
+  "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": 43.695,
       "eval_steps_per_second": 5.467,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.2033,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.2136116027832031,
+      "eval_runtime": 146.7958,
+      "eval_samples_per_second": 42.74,
+      "eval_steps_per_second": 5.348,
+      "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
 }