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:aa71b791f602ae1b4f5ce8587506378a0e51b52ad35d1a5bfacf5d3745651631
+oid sha256:8aa13a44cb5fa7398efc25d14ec161697f4e0b32e1b13354e91c11726cc55da1
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:669d9786d1eb44323df3e750ba1886c2dfa4d589ab14b33b081e73a9daa708e0
+oid sha256:cc895517579eb4120987a61426713077595205131abd90d9a379a2acc037f011
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7b64f3aa00f9880ea05d8fae45c424ac738ffe20f043970aba83c9f4b0840b
+oid sha256:71b9445452b0f4ec2e34ecc2a5014eb62a4d39167a4355d4fcd661626ad65a5d
 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": 2.1313953399658203,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 2.1183180809020996,
+  "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": 30.438,
       "eval_steps_per_second": 3.808,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 2.1011,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 2.1183180809020996,
+      "eval_runtime": 206.302,
+      "eval_samples_per_second": 30.412,
+      "eval_steps_per_second": 3.805,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.05520114725888e+16,
+  "total_flos": 7.346343543662592e+16,
   "trial_name": null,
   "trial_params": null
 }