Training in progress, epoch 3

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47b1b201ef8320841651d189fa2a04d1847c44df97e42363fb2ae0a5c8cd8abe
+oid sha256:16c0c47103351969fb000f9300207536eef5fdcc26d55c3b817dde8af0b5c081
 size 3567808

train_log.csv

@@ -1,3 +1,5 @@
 loss,grad_norm,learning_rate,epoch,step
 1.4885,2.976400136947632,3.336666666666667e-05,1.0,500
 1.1504,4.292872428894043,1.6700000000000003e-05,2.0,1000
+1.0006,7.022700309753418,3.3333333333333334e-08,3.0,1500
+11730.008,4.092,0.128,1020745916282304.0,1.2131712443033855,3.0,1500

train_log.jsonl

@@ -1,2 +1,4 @@
 {"loss": 1.4885, "grad_norm": 2.976400136947632, "learning_rate": 3.336666666666667e-05, "epoch": 1.0, "step": 500}
 {"loss": 1.1504, "grad_norm": 4.292872428894043, "learning_rate": 1.6700000000000003e-05, "epoch": 2.0, "step": 1000}
+{"loss": 1.0006, "grad_norm": 7.022700309753418, "learning_rate": 3.3333333333333334e-08, "epoch": 3.0, "step": 1500}
+{"train_runtime": 11730.008, "train_samples_per_second": 4.092, "train_steps_per_second": 0.128, "total_flos": 1020745916282304.0, "train_loss": 1.2131712443033855, "epoch": 3.0, "step": 1500}