Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd42f7e277ea73eeb24cc6785874493fb6203372e9dd599b99b055b24f1fc82
+oid sha256:1e9746171f832097d6457da6ed9f1a576ac4bbd4dc16cf3b96bf4e60080ea6d9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145390c4ddf1514f3d6f2263d50fd0fafdb2f5af12a8c48fe4f855769caf212c
+oid sha256:947c49409410dbea009305e6bea316bcc90666497f85365c37d5f7a627cc9bed
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809ae7b7c0b89bf58347a7c2b39be06ead95e77ac55e0c214b98278e7ce66603
+oid sha256:927e08927f37ea4af9a349e532e3fe8772a1f852b703e9692faae370d8e4f54e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11843876177658143,
+  "epoch": 0.12920592193808883,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 7.816,
       "eval_steps_per_second": 7.816,
       "step": 44
+    },
+    {
+      "epoch": 0.12113055181695828,
+      "grad_norm": 0.6449961066246033,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.1167,
+      "step": 45
+    },
+    {
+      "epoch": 0.12382234185733512,
+      "grad_norm": 1.3696563243865967,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.3693,
+      "step": 46
+    },
+    {
+      "epoch": 0.126514131897712,
+      "grad_norm": 1.968651294708252,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.4617,
+      "step": 47
+    },
+    {
+      "epoch": 0.12920592193808883,
+      "grad_norm": 0.8639482259750366,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.231,
+      "step": 48
+    },
+    {
+      "epoch": 0.12920592193808883,
+      "eval_loss": 0.26753100752830505,
+      "eval_runtime": 10.1196,
+      "eval_samples_per_second": 7.807,
+      "eval_steps_per_second": 7.807,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7805294805450752e+16,
+  "total_flos": 1.947454119346176e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null