Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f7ef35f5c44722f7a0916299669bf1ea4a015d8557c680696b28164e306535
+oid sha256:114ea38b8c9c73d969702e28b59868a439e96e89444fd8ff80a1691cfa789c26
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150e1ae552b35cc40720f8b36736d1aa6c0f9c23196b9f5cba8a8cd307091036
+oid sha256:206d627b3863f82f7aeaa7ee2101ddae9e4ebae6f070ae9fd9f74ea452665dd5
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524dd2e23117d8b443709151f0c30fd7b12f5af14881b8fbb512d42a7c4c2c9a
+oid sha256:fb8700f03b0419d9986a6e24b443d85912e3a6b7d042961e7ad00c63377cc539
 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": 2.1605775356292725,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 2.146674633026123,
+  "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": 30.243,
       "eval_steps_per_second": 3.784,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 2.126,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 2.146674633026123,
+      "eval_runtime": 207.6555,
+      "eval_samples_per_second": 30.214,
+      "eval_steps_per_second": 3.78,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.009593112553472e+16,
+  "total_flos": 7.298808085997568e+16,
   "trial_name": null,
   "trial_params": null
 }