Training in progress, step 120000

logs/dataset_max_seq_length=1024, dataset_sample_size=1000000, dataset_subset=sample-10BT, dataset_uri=HuggingFaceFW_fineweb, learning_rate=6e-05, per_device_train_batch_size=8/events.out.tfevents.1727279209.1c1a426a2fee

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0562c809edd707c5b246291851a8cb05b213c623b1e2c6d6187266aa11e27270
-size 3163672
+oid sha256:c4891c7a0be0633dacd04cf41253a8843d659c45455203efd37d0bdf77577037
+size 3301568

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5d885bc2039c67f1ed2b307a7b284895bee4a8d04a839037a850dd0b3d033a
+oid sha256:07a0ba312ebfee65e879dcb53d2688df3305284cbfb37e047eb2432e4193a1bb
 size 325669528