Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321f481b8b4a58983b9f6624e65166552cb63280916a540d4755343cc7fd03fa
+oid sha256:109077240286b268e4ed1dbfbee81df6ca96e2ac469518850c30780ead455051
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a49c594da750c4aff7a997ff7c7a2056881bfe5f8e33ee1a99479f7ce2838e2
+oid sha256:1249d1e2125bd02ddeb942f9c9043bd5499ef724c582be29b385627eaee0c5a0
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abc1651d90c08f1d53ebb2646d6c02484bede312b64b6066690c8bbd1412627
+oid sha256:7bc86ae6bba74148ebf449b0cef4649049d351c03ea9858e52427b4760626666
 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": 1.3450849056243896,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 1.092896174863388,
+  "best_metric": 1.3320348262786865,
+  "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": 14.981,
       "eval_steps_per_second": 1.874,
       "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 1.3214,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 1.3320348262786865,
+      "eval_runtime": 418.8397,
+      "eval_samples_per_second": 14.979,
+      "eval_steps_per_second": 1.874,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.8636182340681216e+17,
+  "total_flos": 5.18778342943104e+17,
   "trial_name": null,
   "trial_params": null
 }