Training in progress, step 400

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/Jul02_19-58-26_n136-082-130/events.out.tfevents.1719921527.n136-082-130.323326.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb1373e59ddaa28e382a2ec2c3435a0942cbb936d0c1e3c6ab8b242e9d9755d
-size 26339
+oid sha256:110951fa4c3732fc3738517ea58800ec4d18bc2ddfaf232c52feb8244b5883a5
+size 33219

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:fa239968c49fa713bd02b2a6b92d8e050b66dd940258509bf0c4d483fb8aa932
-size 6328
+oid sha256:5e59046c62a4268c638d9db20426708311674006cbf03244741370a8d86cc804
+size 6520