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:c14582e7de2eb10d18b36c2ee4d79901b7b2addc60c41b210569b73ed76d7ab6
+oid sha256:57dbce7f50e64aa2c5e2064d718367b5f7840ec840a5befffec7ae47533ec9af
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772de744b81c0f8d47097535a11575e792f20ac94d390a701039411698b35b5f
+oid sha256:cdc1e64456c90b172de1e205e78870b15fb9167d42cd51998aa297967dfda8a7
 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 sha256:1ef51ed05818f33aebca9592cb64baf0df006aad2a34a7cf944f4a48b70afce3
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2261732816696167,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9143897996357016,
+  "best_metric": 1.2130030393600464,
+  "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": 43.584,
       "eval_steps_per_second": 5.453,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.2013,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.2130030393600464,
+      "eval_runtime": 143.9131,
+      "eval_samples_per_second": 43.596,
+      "eval_steps_per_second": 5.455,
+      "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
 }