Training in progress, step 625

config.json

@@ -1 +1 @@
-{}
+{"d_model": 768, "n_layer": 24, "vocab_size": 50277, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8, "tie_embeddings": true}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bf5130e95dafdc6fe5f61c0308b2b9f3f64f01f072250f89c25628e8f1e88a
+oid sha256:c886a40228ee702faa79028fcba8ed8c0a916e29a121d33f5556b4f8053e0845
 size 516640282

tokenizer.json

@@ -239,10 +239,30 @@
     "use_regex": true
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
   },
   "decoder": {
     "type": "ByteLevel",
@@ -258,6 +278,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea0d5394fa9d22169b986cf6905d4d51e92cb6e3c174b352ad8c7f591665c9a
-size 4920
+oid sha256:22c8e37a8ae745fb7423d205aa2a72d4a795c3ead73244e4f64ce46c6a304039
+size 5112