Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd7f58e1200259dc7dd50b5686d1e58a48fac1194dedd1145103080e18e5880
+oid sha256:02706c27adb8ca7ae4ae5e13625d8ff44068fc18e6dc6047d289a0baf0ecbc9c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3142d7ba859a940cb52a274f34142d29102c0dc2d76787a6090fd708c84a6e
+oid sha256:fce2b4e1c425c24fb3babf7bd8c8824f6e546b5013d980178575e78d82bf11e3
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225d338513df9b3c96bfa51035af41455d9ed58f0d399244944c7e6aaaa43616
+oid sha256:0bab3959305628610ea59050049ccf445cc768a7b69d4a2972396e289560e3b8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
+oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2520592212677,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6029143897996359,
+  "best_metric": 2.240290880203247,
+  "best_model_checkpoint": "./outputs/checkpoint-2300",
+  "epoch": 1.6757741347905282,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,13 +315,27 @@
       "eval_samples_per_second": 30.634,
       "eval_steps_per_second": 3.833,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 2.2266,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 2.240290880203247,
+      "eval_runtime": 204.7035,
+      "eval_samples_per_second": 30.649,
+      "eval_steps_per_second": 3.835,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.273785068959744e+16,
+  "total_flos": 6.55823470611456e+16,
   "trial_name": null,
   "trial_params": null
 }