Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4226bd98d5b0d2b04698262c16f4b05634e0cb5e5b1af55543784e04b3f5566e
+oid sha256:b7eb37af6ff6a59d1061060fc9f40831c860b63da3e1ebcee8979a5bfc2d8ffd
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21589b404e15592d9f9ba2b0b9acc7852e0973e0b73d2eba005c4f0205eec4dd
+oid sha256:afe10651526d8c89532608e35d70bcc8fa59f317274dee170f19c15034889ea9
 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": 2.24958872795105,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6029143897996359,
+  "best_metric": 2.2403359413146973,
+  "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": 30.633,
       "eval_steps_per_second": 3.833,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 2.2233,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 2.2403359413146973,
+      "eval_runtime": 204.8335,
+      "eval_samples_per_second": 30.63,
+      "eval_steps_per_second": 3.832,
+      "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
 }