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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ea11e0b109f95ccb929a99315a09da1f4c0333c8fd4dbc07e83a17fd4d4f6c
+size 140509

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7027dade237cc34c1fe1e5665a672c949815fca8bbc0df8d3bbdec24cc732533
+oid sha256:04ccde75028f60080bfc4be957bbd2c788df78c233244c1120c479eb9dff963d
 size 325669528

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1023,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66494727ec03541c5c991424dd80273f96b4325bc02006dd5123394dcf73c030
-size 5624
+oid sha256:489ac1c599f8c23dd19af80387679fc021366579b87b8a776b5ebb68da3da2a3
+size 5688