Training in progress, step 61875

logs/attn_layer_mapper=all, attn_loss_fn=cos, attn_projector=orthogonal, attn_weight=5/events.out.tfevents.1724510390.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88723b89ef131a153a80b81285f7955a4f78917972fe7de8547540c5a637bf9e
+size 29625351

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7d7727abfa160a03b1932b595fa82dea9e9a6de0d7e299192a5f99c0c2788a
+oid sha256:0684412439814634d91d22abd503340a0d94b214d6ba8ef058e6030cab49af12
 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:a4ff44b3871953b465130242e9a530d42be863fcb71a24931a89de23ecaa295f
-size 5560
+oid sha256:fba949610247c9f3686f3d18b3ac80cd2f9bfce0cc8a973afa76a7fad57324be
+size 5496