Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9c2090937e6f30c3df460b6dc525639d0f6a061218c85244bbd344774af34b
+oid sha256:e475e22400bf950a7c7ca76503958299029f5f8012270bfd055550b832da0615
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c515e6a7156130717274dcb9a2525fcd70f2572e443372a9c447f856418156f
+oid sha256:b05b21541fbf6175f974c3e6cbfdb02a46b9f2897ef60b7aa3d83b3eaa60e437
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0bb62c383dd93bb7277f2f4f3ecc51f45d7c7b1a6c0012d26a10c5589360f2
+oid sha256:6122816c42780a868d77d7c48cf66d125e516c03075f49e683bda8693a41f3d6
 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": 0.18181818181818182,
+  "epoch": 0.36363636363636365,
   "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": 36.293,
       "eval_steps_per_second": 4.753,
       "step": 9
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 3.3855478763580322,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 4.3757,
+      "step": 12
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 2.789888858795166,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 4.1669,
+      "step": 15
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.9098223447799683,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 3.689,
+      "step": 18
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "eval_loss": 3.8252432346343994,
+      "eval_runtime": 2.3162,
+      "eval_samples_per_second": 36.267,
+      "eval_steps_per_second": 4.749,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2351283906281472.0,
+  "total_flos": 4702567812562944.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null