Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b7dab2d2546bc9b5584cd70aecf27fd01c0ec429f54ed0da1544788df34146a
+oid sha256:1f4f1a3c3a966d512bb3fcb40966a371627ab743a3d0e76f3703072504d49d72
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7ae030246005df73d9ebd1f4db1803862407102f7541754e56bc9aba74e4b6
+oid sha256:92b85f98308b5a85deda05b37cd2105081702740c4a3d4c0125ad18de2879874
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591b68cb553c7eec0aa1f6e0e433f89cdb637b97e8f51bc7213f85b31dd88afe
+oid sha256:14dabd6ac5b413b42d35c286b0d19e23ed4fec71087c81558b454fea8c926535
 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": 2.1847541332244873,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6029143897996359,
+  "best_metric": 2.1721720695495605,
+  "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": 30.25,
       "eval_steps_per_second": 3.785,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 2.1507,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 2.1721720695495605,
+      "eval_runtime": 207.158,
+      "eval_samples_per_second": 30.286,
+      "eval_steps_per_second": 3.789,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.427567056218112e+16,
+  "total_flos": 6.719177798387712e+16,
   "trial_name": null,
   "trial_params": null
 }