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/Jul03_15-29-09_n136-082-130/events.out.tfevents.1719991781.n136-082-130.634611.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c80b4195fb8d4ed2ccf52a021f5bdd6556161ccaf462fb6567f75bad28c0fc
-size 12055
+oid sha256:26018087b7a84b08d98b9aadcc1723f0d0004889c511e67a41557ef42872499c
+size 18935

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:baf23ee842b7b36acdc3eabed1c4ad834b65768370cfd530feec554b8bcba32c
-size 6328
+oid sha256:3097d7a227720d08613fda0662f59952b3be18b3ae46095e30d08c7d4de3b7a3
+size 6520