Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b08eb0f20294562fc3c3b017ac9136c461896ebc74dc2b67904e821d8c81b794
+oid sha256:d11e5e3792b1f39a43439d7fa6b6f6fe9ffa3041120e42071aea80b27ba735f3
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfa0564db07fb04ed1ae077badbf12b119e32ddd205674e483a8f2828764459
+oid sha256:1307ea7e48f53fed60313cc667efad8a472dfb0e61f1c5ef0d4178104d8d289d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c42f02805f05255b8fcfb4fa3b8e8ef15f6edcb5701c96a5484d4d1911b2fc
+oid sha256:c3f14f26e1c82af1569197c946ee60a682af9d056666c7fed1d76396f3ef87dc
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.284607172012329,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 1.092896174863388,
+  "best_metric": 2.2680861949920654,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 1.1657559198542806,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,13 +217,27 @@
       "eval_samples_per_second": 30.675,
       "eval_steps_per_second": 3.838,
       "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 2.2518,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 2.2680861949920654,
+      "eval_runtime": 204.3902,
+      "eval_samples_per_second": 30.696,
+      "eval_steps_per_second": 3.841,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.384226881972224e+16,
+  "total_flos": 4.676360009803776e+16,
   "trial_name": null,
   "trial_params": null
 }