Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/new_world/v1-distill-round2-0.5-lr58",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/new_world/v1-ultral",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.38.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Jun06_13-29-12_n136-129-074/events.out.tfevents.1717652376.n136-129-074.1035360.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3038a15ec7983b5aeeaf93e3c5f4de23e71198323ab2629cc878806d290e224
+size 12302

tokenizer.json

@@ -152,7 +152,6 @@
     "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 sha256:4ab0d2ab5fad688425813e23c6e2b9f01a1ff29a0fb544a932591b142890b321
-size 6520
+oid sha256:0fca5a261a54300d1452b13f8cd6d979be181e6f4026bf678536b29a267ee051
+size 6264