Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a4bda59c28deb9c8ce2b5ea32115712d08dda9b80b999ebd634855767986719
+oid sha256:08a960d5dbc1ca18946db0a2b5f0304083b8cbc76ce3d4a03f1f9c451f080382
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9543c7deeaec4382645b7b1aed0ed4688edd9136eb9e041fe58d8b54accd3a
+oid sha256:0fb6111cc5ae96b4a8d358649754552a7031ed55d53fe146f7361fc343cc5944
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b68c240df99005b4953409aa7c52161db6b8b35e9abfde46531de4bfe3403b8
+oid sha256:1d740bd7949b18870ce1ee00a99f674ad6b9c829a035d26342b204066c9c9455
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c50acebbdd320cdbda27b93feb5d91578ce2eb03d7fc0517b7bfffd55baef8
+oid sha256:10e175ebe60f1a6bbd43d635188097fdd53bf710ff976db3f946328fc19cf4ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002311387193470331,
+  "epoch": 0.0026003105926541226,
   "eval_steps": 2,
-  "global_step": 16,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 7.074,
       "eval_steps_per_second": 3.538,
       "step": 16
+    },
+    {
+      "epoch": 0.002455848893062227,
+      "grad_norm": 34.9987907409668,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 12.4402,
+      "step": 17
+    },
+    {
+      "epoch": 0.0026003105926541226,
+      "grad_norm": 39.801536560058594,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 9.872,
+      "step": 18
+    },
+    {
+      "epoch": 0.0026003105926541226,
+      "eval_loss": 2.25581955909729,
+      "eval_runtime": 412.3441,
+      "eval_samples_per_second": 7.069,
+      "eval_steps_per_second": 3.536,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5227717154832384.0,
+  "total_flos": 5881181799186432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null