Training in progress, step 300

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/May28_02-13-45_n136-112-146/events.out.tfevents.1716834544.n136-112-146.326388.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419730be98ba66a4bc9ddc42f37c4d64ea667fe8c22fb5fc60a6e7f0adb1f615
-size 20727
+oid sha256:a712b7a97539c383168f6e5e3530ecfe86d5b039a3a87ba7fd6b692854b1ad7d
+size 28347

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 sha256:2ba26fafd03dc99e7d3db95db6c6e4c6d32ca5324c807136077205b8734c2180
-size 6264
+oid sha256:233762ce2f7a1cfa30251c51e84fc095bdb7579faa7bbc23d8ce39a8e51f366d
+size 6328