Training in progress, step 5000

logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=sample-10BT, dataset_uri=HuggingFaceFW_fineweb, logits_loss_fn=liger_kl, per_device_train_batch_size=8/events.out.tfevents.1727261283.1c1a426a2fee

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ea11e0b109f95ccb929a99315a09da1f4c0333c8fd4dbc07e83a17fd4d4f6c
-size 140509
+oid sha256:2766267e55c7273d417ca994e3f78cef4e526991ec8f4fd26480eab73b3a9876
+size 183880

logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=sample-10BT, dataset_uri=HuggingFaceFW_fineweb, logits_loss_fn=liger_kl, per_device_train_batch_size=8/events.out.tfevents.1727265841.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e5b8dd43f459fa02b85916a27e932fa92bf4951c9661c0c62f513c4c2e4dd9
+size 28240

logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=sample-10BT, dataset_uri=HuggingFaceFW_fineweb, logits_loss_fn=liger_kl, per_device_train_batch_size=8/events.out.tfevents.1727266615.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ab459c4ea00bf0ec54305b6a79e68860447099ff56f1567e28f6fdb6ee8b97
+size 140780

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ccde75028f60080bfc4be957bbd2c788df78c233244c1120c479eb9dff963d
+oid sha256:5c6b543d0b2210018ba972399f2834c98acd00db5b0ac8d279cb6de7641fa2b1
 size 325669528