Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6ce519700ca591073c20b9c7f2dcbb805c3797371f8c01879f04a0bf3930a7
+oid sha256:d48189559254b1d9f3121c68607346d6bb4e457960c2be5a3968974359133919
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c0c6346abba0b386479dfd6ecda75e6e86bb73feaf647d6e3833fd92428940
+oid sha256:9f26a2ca6c46914bddd6642774787de9c0f6e5faabb3ff45d90b1707934800d8
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f2583e3ee9d1bf82a865ecce9740ec6634d3e1966fe5fe08ffb30b04ce0e7f
+oid sha256:dba2dba8083c66fc0d2aeb786e658b4b6752c9b3d645135a768253e6d260da31
 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": 0.012418075198344257,
+  "epoch": 0.024836150396688513,
   "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": 7.142,
       "eval_steps_per_second": 0.895,
       "step": 9
+    },
+    {
+      "epoch": 0.016557433597792343,
+      "grad_norm": 4.505770683288574,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 1.0678,
+      "step": 12
+    },
+    {
+      "epoch": 0.020696791997240428,
+      "grad_norm": 3.744687795639038,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.7375,
+      "step": 15
+    },
+    {
+      "epoch": 0.024836150396688513,
+      "grad_norm": 3.299644708633423,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.9198,
+      "step": 18
+    },
+    {
+      "epoch": 0.024836150396688513,
+      "eval_loss": 0.21940629184246063,
+      "eval_runtime": 170.9547,
+      "eval_samples_per_second": 7.142,
+      "eval_steps_per_second": 0.895,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5312661952528384e+16,
+  "total_flos": 5.062532390505677e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null