Training in progress, step 2500

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Apr23_15-54-20_n136-128-070/events.out.tfevents.1713858963.n136-128-070.1960238.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed5d0d4b272fbabe1e963b87f69c4b2d253485f5c9c538fd3e5ed8b613f848f
-size 47466
+oid sha256:e333b44a1b392a5973f75354565c1033764b4c8e6fd6606810683c3f6389f946
+size 111579

tokenizer.json

@@ -152,6 +152,7 @@
     "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 sha256:68fc3a7e01a1f972df57dda16dff653580f8f62565e152a4811780709f9e6544
-size 6136
+oid sha256:ce2fd167e13d2ed98b2df24741f56e1db29830406234c6bbe7c5bc2a74cfd42a
+size 6200