Training in progress, step 300

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.1",
   "use_cache": false,
   "vocab_size": 32000
 }

runs/Jun22_05-46-25_n136-082-130/events.out.tfevents.1719006421.n136-082-130.2484976.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d7b4c8742280e9ec7dc54c25f7a49480b80fb1c85e892ddf5b7fba6cce5279
-size 19419
+oid sha256:8af985393eb96e18bec47c64ac57e2742655004ff1cf34b62c46659a78b64406
+size 26299

tokenizer.json

@@ -134,6 +134,7 @@
     "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:c87978e0ada8eb8b36aa4ce1da9ce43cac770f96429f7a9823dc55c8256fd717
-size 6264
+oid sha256:3267756347c2c9afb597e20553862a0ac248b214358676d7dfbabc75346c7d63
+size 6520