Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0da9b07898489de75988422bff9d7ad28744399ca778f243d83ef4f862df31
+oid sha256:686be625ccdfb7eef82aaa607229ccafc67a81504b9f9b47d26e95c13035b679
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e744e2e1bc722c56d8e58d8b1625d77c284778ef8f763fabfd4c6ab0722be2a
+oid sha256:9bfb9404e5936b5eea85ea5df8706014658302068e4a225418642d35e7861cdb
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56674b36d851f5b84d74ee0b7bc6b81712a9b3f3b2e8a9062cccfeda3e1f9d38
+oid sha256:49caa7693c19fefdecf084507da64d4a2a48e318629d15b1327b5de698c3dd3b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:95758e6aadaa863940ee26d7d4bc2716664c72b77251097ec968b5c9819c88ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009224383119378891,
+  "epoch": 0.011530478899223614,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,28 @@
       "learning_rate": 9.372094804706867e-05,
       "loss": 1.893,
       "step": 18
+    },
+    {
+      "epoch": 0.009685602275347836,
+      "grad_norm": 0.612069845199585,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.8113,
+      "step": 21
+    },
+    {
+      "epoch": 0.01106925974325467,
+      "grad_norm": 0.6409688591957092,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.697,
+      "step": 24
+    },
+    {
+      "epoch": 0.01106925974325467,
+      "eval_loss": 1.803785800933838,
+      "eval_runtime": 70.5929,
+      "eval_samples_per_second": 19.407,
+      "eval_steps_per_second": 9.704,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -92,7 +114,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4170173481222144.0,
+  "total_flos": 5204100790616064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null