Training in progress, step 200

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.38.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/May29_23-11-40_n136-129-074/events.out.tfevents.1716995522.n136-129-074.2191665.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8f9c431378b5fc41ac74967c1c6efa87ebc59add99c11fd06d86e3feb252bc
-size 13068
+oid sha256:ec14532cca599cb58b92da0403689fe36c762daa761875d1efd18d410a00d02b
+size 20664

tokenizer.json

@@ -152,7 +152,6 @@
     "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:df9dd9975041330cb3031003f27f8952f7657e67478afc48ee43616047d272ea
-size 6520
+oid sha256:dadd16e859cce8223cbc036d0b14a858573a3c16794cd0290547847afa9ddb52
+size 6264