Training in progress, step 61875

logs/attn_layer_mapper=all, attn_loss_fn=logsum, attn_projector=miles/events.out.tfevents.1724541604.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864065087982f39f4177fd00dbbcf3c73d12327316e97f2405a07c5858b4100e
+size 29625281

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4e12deaeab134bd4bfa52f1550a57b8d68ded99389617b8a73665515c24aed
+oid sha256:424703a70c6de33f4ea2c85dd1f2be0add3d5c47fbb2f81a48da75dd8c22aeee
 size 248894656

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": 50256,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 50256,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e8f4d6c8a98709c31aaccd719d69d1f82ff7f7d0023a62fe646d14320a8512
+oid sha256:c0206f9d17505ba45df67cf2279065f851a908ed967be6f43a621173ad6cc3b7
 size 5432