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/Jul01_20-10-18_n136-082-130/events.out.tfevents.1719836135.n136-082-130.4100769.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b63f55689fbba47d3c3026553c408d45d22d4560818ca9b968529ed9c9f94e
-size 19445
+oid sha256:819488e7c1f4f638c0755409a1e5bcd6549eeda6d865c5c376799e66076fde4f
+size 26325

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 sha256:9014cab4050e7c57bcaa9835becfbc167b338a80016d63ef825502379e3f526b
-size 6328
+oid sha256:847c6da2aa515f5fcece2384c5beb447b87cf5c9401e04c0c57b3c11eaa4843c
+size 6520