Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2688a7aabacc4ab9d60ebadbd93728481a703224209993372a346e3af042f858
+oid sha256:ba6602bce01464dad79aba6ef459f102d8f448792a75d07b2d91db95716cdc27
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19224de1727a62cfef363634d8492e89115789c7a5dfc401e8c23d52d97c8f92
+oid sha256:bf554af66095a62896d56ca3678ed3fef053cba467be912b5e77063673c8882c
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9454c9535ad3811e6becd57363e61aef16e6c76875f30d1bdcd4191265ac8ce1
+oid sha256:a16dbd92b02a89cf372eb0be8faed673d0065b4c507cdb24698df320c511fb2f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
+oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1863455772399902,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 2.171632766723633,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,13 +399,27 @@
       "eval_samples_per_second": 30.554,
       "eval_steps_per_second": 3.823,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 2.116,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 2.171632766723633,
+      "eval_runtime": 205.19,
+      "eval_samples_per_second": 30.577,
+      "eval_steps_per_second": 3.826,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.971491799484416e+16,
+  "total_flos": 8.255440339421184e+16,
   "trial_name": null,
   "trial_params": null
 }