Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade17cac2e4e83416faba4de0585be2155883553dd29252ad4024d5b7ed24a4d
+oid sha256:85d0ed7b0f1d8f01a21bcb8d16b98423e8fe3f504546f331219eb03eb9b7dde8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b16be9cd3559a570e027792fa701ef9cdae97963551e1267cd480e2ca252e3
+oid sha256:1e8c667cc4401a3433b82ec9ec09f74f680e812d94750f1ec0d9591c4293b53f
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332759cf7b5cf921f7c9ebfe29466512b01ff3dba8f0377398688b0a48981a95
+oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001591371231544514,
+  "epoch": 0.003182742463089028,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 14.096,
       "eval_steps_per_second": 1.763,
       "step": 9
+    },
+    {
+      "epoch": 0.002121828308726019,
+      "grad_norm": 7.4701151847839355,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 3.6782,
+      "step": 12
+    },
+    {
+      "epoch": 0.0026522853859075237,
+      "grad_norm": 5.40271520614624,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 3.4578,
+      "step": 15
+    },
+    {
+      "epoch": 0.003182742463089028,
+      "grad_norm": 5.472065448760986,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 3.1924,
+      "step": 18
+    },
+    {
+      "epoch": 0.003182742463089028,
+      "eval_loss": 0.811770498752594,
+      "eval_runtime": 675.7606,
+      "eval_samples_per_second": 14.095,
+      "eval_steps_per_second": 1.762,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656345471778816e+16,
+  "total_flos": 2.531269094355763e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null