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:d3de14f08f155ab5012317e0ab6ca05907566ba28980ed01d299c07246532e37
+oid sha256:102c35f0d2d0a8d68e313bff7ab0a4afeda3224deab5c0f9c01ff1dff324705c
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f96ba4d51ba642e51959e86f9bb4544c4930e899c92070faa515407fa6283f32
+oid sha256:b18b6f9f734323ebd3ca9e8bf1c12e83890a01d354add7e695ac7bf7a6cebca1
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df3c3e6d66c14ab5f979071ad4f8c384c7c65af069e4b3c79758858b3a854dc
+oid sha256:dbb19775908c316bf5835393d33748a381150a1b2242bf50b0e2855e185881ca
 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": 1.2375760078430176,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 1.2266868352890015,
+  "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": 15.02,
       "eval_steps_per_second": 1.879,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 1.2266868352890015,
+      "eval_runtime": 417.9231,
+      "eval_samples_per_second": 15.012,
+      "eval_steps_per_second": 1.878,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.781170380374385e+17,
+  "total_flos": 8.104035789088573e+17,
   "trial_name": null,
   "trial_params": null
 }