Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523730488df60d5e54b6d67849fa0ae390bf1208931a698d76199828b6a08f74
+oid sha256:ad691ac6d2fc1e0e3a5201df708d4cfee6260fd89efca3634f07128ed442bc46
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5090939cdc16e753ecb8e51b4b76115046dfbb852a14306724635e8ad794f997
+oid sha256:8e792bce28adb52a972d1da0fd894a4f9f0697ff068ac581b2abfba7acb0d982
 size 52046596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:696b7e2ff11d56cfda2a07d9a2a018bce54cf0c1cfd963087bfdb6600e0ce5ee
+oid sha256:4f3c48c26b22b8eff8e3ac55a811b89695de14f630a8d517211346253708e53a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004308797127468581,
+  "epoch": 0.005745062836624776,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 23.097,
       "eval_steps_per_second": 2.889,
       "step": 27
+    },
+    {
+      "epoch": 0.0047875523638539795,
+      "grad_norm": 0.5452908873558044,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 1.7306,
+      "step": 30
+    },
+    {
+      "epoch": 0.005266307600239378,
+      "grad_norm": 0.5148115754127502,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 1.658,
+      "step": 33
+    },
+    {
+      "epoch": 0.005745062836624776,
+      "grad_norm": 0.5095010995864868,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 1.7653,
+      "step": 36
+    },
+    {
+      "epoch": 0.005745062836624776,
+      "eval_loss": 1.6911619901657104,
+      "eval_runtime": 457.3928,
+      "eval_samples_per_second": 23.074,
+      "eval_steps_per_second": 2.886,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.827444064518144e+16,
+  "total_flos": 2.453055546064896e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null