Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb3df576d4871816a8c8cc002a4416728cac67d0da0b747a0e5dfe2e18c753d
+oid sha256:0fa8172e1838e6b5dad9e029c72ae68e0ef4f2b24f1afc1be72b51bea035d51b
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263d59f3d80b2d6269466dc4cde3204d8c1fd2ab018e96950e83c79b7f1fa564
+oid sha256:3feac52cdfffd1a114d1f563f2e8e80effe2a06e8506a364ccdba2f8bde3b35d
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f223f24880f37fd2ed16958fd86fcb77dc1dad47e8870e3786c5bb9b67f6ab7
+oid sha256:6b4134525da3a464178bcd4cc0411260275e9d82eba875b1bc772f5db2d3e90d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002498091735479842,
+  "epoch": 0.004996183470959684,
   "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": 9.185,
       "eval_steps_per_second": 1.149,
       "step": 9
+    },
+    {
+      "epoch": 0.003330788980639789,
+      "grad_norm": 0.23466083407402039,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 0.4373,
+      "step": 12
+    },
+    {
+      "epoch": 0.004163486225799737,
+      "grad_norm": 0.20258335769176483,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.4476,
+      "step": 15
+    },
+    {
+      "epoch": 0.004996183470959684,
+      "grad_norm": 0.22826525568962097,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.4442,
+      "step": 18
+    },
+    {
+      "epoch": 0.004996183470959684,
+      "eval_loss": 0.42058902978897095,
+      "eval_runtime": 660.3378,
+      "eval_samples_per_second": 9.189,
+      "eval_steps_per_second": 1.149,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.852452537316147e+16,
+  "total_flos": 3.844712813297664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null