Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ce2e0172da67c0bbaad728c85cf9e7a738e3987c9f2dbbb24bb8a9729af664
+oid sha256:a2e0d0637f1bf4b136ace7f37c001710e8f68619abb093fb93d21be5fa9ad7b2
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e496a86d9e18e433097172f26589b1b2c359968aa577ba2efe2d942f86c06e
+oid sha256:d4e48c3b6d17b73aab3669d02c562d8313bcad6d2ecabab208e4b8738d0d7a97
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d52c1bc6ea42c69efec50a9fdb93109c150d0f5358a667cf5ce03d6e6f892e
+oid sha256:591b68cb553c7eec0aa1f6e0e433f89cdb637b97e8f51bc7213f85b31dd88afe
 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": 2.1937856674194336,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 1.530054644808743,
+  "best_metric": 2.1781294345855713,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 1.6029143897996359,
   "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": 30.624,
       "eval_steps_per_second": 3.832,
       "step": 2100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 2.1584,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 2.1781294345855713,
+      "eval_runtime": 204.973,
+      "eval_samples_per_second": 30.609,
+      "eval_steps_per_second": 3.83,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.134610229364736e+16,
+  "total_flos": 6.427567056218112e+16,
   "trial_name": null,
   "trial_params": null
 }