Training in progress, step 2000

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Apr21_01-36-46_n136-148-198/events.out.tfevents.1713634703.n136-148-198.682627.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de044e6747a42087ae71926a25fc09e7c79bc8d3a2785184974b37545d0839b7
-size 68819
+oid sha256:051428e8c71a8694cb9a0725725c7b2f24ddfc12ac4e57b4f6a44be144840f4a
+size 90190

tokenizer.json

@@ -152,6 +152,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0d1860a8699ef12a9fb178408ee4b12bf54aba671d7e715a9313b88d8a2182
-size 6136
+oid sha256:8644b5b12460c8432c39d68f8e01741f67061742d4361b9fd3d667b08c873f9b
+size 6200