Training in progress, step 300

config.json

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

runs/Jun22_05-26-45_n136-129-074/events.out.tfevents.1719005226.n136-129-074.366828.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478c4c24fd6311fbc33a044c182486929d0cd8daccea543bd54f06b59b8700f1
-size 19219
+oid sha256:6dc853f4da6780b28efae8568a6d4f95e2f7e7bbe28ca8d16b5307bd9314219a
+size 26099

tokenizer.json

@@ -134,7 +134,6 @@
     "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 sha256:3267756347c2c9afb597e20553862a0ac248b214358676d7dfbabc75346c7d63
-size 6520
+oid sha256:47a21b5563dec2beb9a160ae932f9047a37bb854766f66095441d6c75a856221
+size 6264