Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958dd913d4f89d315f08e4a6a0251b8b39c90a814521d21a5f58033e8ba7b610
+oid sha256:fb1a5fdc8d64fd9e7fc3b07ce874a8347d275ac5319a3b153e424387ee1d1582
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016ef43af3c56f0a7eb87a2d432ca9a6c6476757c3487b7a65aba7ac9f1f4fd6
+oid sha256:19cc027c0153a39d642936a6f6d3fdcea495eb16ca9c2b5ec675726fdd0a6887
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1719fa6ec87d36176081793d1e7e5b701a50bca7359da17f151490755b222cce
+oid sha256:ce8663185886d8ed8b32a9a7663e77c6f1b4b58e1ee68a5b61088d4f00a0dffd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
+oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.22774338722229,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 2.2125885486602783,
+  "best_model_checkpoint": "./outputs/checkpoint-2500",
+  "epoch": 1.8214936247723132,
   "eval_steps": 100,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,13 +343,27 @@
       "eval_samples_per_second": 30.628,
       "eval_steps_per_second": 3.832,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 2.1995,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 2.2125885486602783,
+      "eval_runtime": 204.9544,
+      "eval_samples_per_second": 30.612,
+      "eval_steps_per_second": 3.83,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.841646122235904e+16,
+  "total_flos": 7.123829358901248e+16,
   "trial_name": null,
   "trial_params": null
 }