Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86089099b0f632f339ca296e8aa9650e23e59509fd1cbe9464ebec42ffebaff9
+oid sha256:4562d5ba27bfcfe942746cdfc9c54b3815c710ad629431394f3db52d6bd80768
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf81ed114fb30b5aed0a1b2752b6812a0ca715e5c3578e778c7a158eddd44b7
+oid sha256:80a3f13f476c346b4ca6e1f06b07990dca5b54cf23815405ee57a9d264e53a88
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab345c2fee9b425debfb2cdeaad87567044e13155a6553627bc07687e45ca9c
+oid sha256:d740007b69299aafed94d2a7a15f725f57b74b4dd2ecb204659a3b705daff261
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4534579515457153,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.5304189435336977,
+  "best_metric": 1.4382610321044922,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 1.6032786885245902,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,13 +301,27 @@
       "eval_samples_per_second": 46.994,
       "eval_steps_per_second": 5.88,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.4388,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.4382610321044922,
+      "eval_runtime": 133.6146,
+      "eval_samples_per_second": 46.956,
+      "eval_steps_per_second": 5.875,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2518315045341594e+17,
+  "total_flos": 1.311400348811182e+17,
   "trial_name": null,
   "trial_params": null
 }