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/Jul04_01-05-39_n136-082-130/events.out.tfevents.1720026360.n136-082-130.847024.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebc18fd4b2ceaed1e043888606cc1f70d7cab32348eeff9c5feb3cd2134d995
-size 19379
+oid sha256:3b35a2c4f4128f199888c76a0f7d3347d90c90a025cd96d4e723d472f478e1d2
+size 26259

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:cc598fcbeb90fecee46d97b240860d50e1862ba1882728b4821914d98eea173c
-size 6264
+oid sha256:a888c216f19aa313a0798596712b94ba0688298a9efc58c6ec4a6d6f51d3527a
+size 6456