Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa8172e1838e6b5dad9e029c72ae68e0ef4f2b24f1afc1be72b51bea035d51b
+oid sha256:b75ea170e3816f4ca2bb07000f2ed8e249c16835adf9268059fed6bd23533a1e
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3feac52cdfffd1a114d1f563f2e8e80effe2a06e8506a364ccdba2f8bde3b35d
+oid sha256:e2a29460a70268141b3ece4618536d4a0665b28a7e4370d3f42d0fdfaddf5e4e
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4134525da3a464178bcd4cc0411260275e9d82eba875b1bc772f5db2d3e90d
+oid sha256:76ac2ce848992a96d8e3c8ad11a38658fb83c3bc2382c8a6c064530346900cbe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
+oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004996183470959684,
+  "epoch": 0.007494275206439525,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.189,
       "eval_steps_per_second": 1.149,
       "step": 18
+    },
+    {
+      "epoch": 0.0058288807161196304,
+      "grad_norm": 0.20002856850624084,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.4395,
+      "step": 21
+    },
+    {
+      "epoch": 0.006661577961279578,
+      "grad_norm": 0.21906918287277222,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.423,
+      "step": 24
+    },
+    {
+      "epoch": 0.007494275206439525,
+      "grad_norm": 0.1747865527868271,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.4055,
+      "step": 27
+    },
+    {
+      "epoch": 0.007494275206439525,
+      "eval_loss": 0.39028802514076233,
+      "eval_runtime": 660.3218,
+      "eval_samples_per_second": 9.189,
+      "eval_steps_per_second": 1.149,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.844712813297664e+16,
+  "total_flos": 5.732117285280154e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null