Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f5a2178236c0b47df536e1b431584b0b052ee27175697529b9286f1d64e8a4
+oid sha256:a776a47fb02400c06be9012ec52d382b6701d1cd2473eb2548df38ccaf39a508
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa994e29f25a46581c29d6e3b3184132e3f1d8582959b76e1c6c3f2037b3e0e
+oid sha256:05a94505c9ad7233bc84f3e9bcc9dfc25a3dc7bebaf335b69a02f2ba610cf033
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a434fa2478e58592908e5f1cc53dc10fd07fe28ea2b87f64160779bd08c4a0
+oid sha256:ade3539adbe7197226065a369a265f6f0f1e7d107ccc3030d3acbbd888426eb0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2802278995513916,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 2.263134479522705,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 1.092896174863388,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,27 @@
       "eval_samples_per_second": 30.449,
       "eval_steps_per_second": 3.81,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 2.2387,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.263134479522705,
+      "eval_runtime": 205.9604,
+      "eval_samples_per_second": 30.462,
+      "eval_steps_per_second": 3.811,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.118366969063424e+16,
+  "total_flos": 4.412678068463616e+16,
   "trial_name": null,
   "trial_params": null
 }